TYPE Review

PUBLISHED 29 November 2024

DOI 10.3389/fmed.2024.1471527

The digital transformation of

OPEN ACCESS nursing practice: an analysis of
EDITED BY
Hosna Salmani,
Iran University of Medical Sciences, Iran
advanced IoT technologies and
REVIEWED BY
Raphael Oladeji Akangbe,
smart nursing systems
Lagos State Government, Nigeria
Kirubakaran Ezra,
Karunya Institute of Technology
Boyuan Wang1*, Xiali Shi2 , Xihao Han3 and Gexin Xiao3*
and Sciences, India 1
Beijing Xiaotangshan Hospital, Beijing, China, 2 University of Shanghai for Science and Technology,
*CORRESPONDENCE Shanghai, China, 3 National Institute of Hospital Administration, Beijing, China
Gexin Xiao
Gexin_xiao@sina.com
Boyuan Wang
2109853pia30001@student.must.edu.mo
Facing unprecedented challenges due to global population aging and the
RECEIVED 27July 2024 prevalence of chronic diseases, the healthcare sector is increasingly relying
ACCEPTED 06 November 2024
PUBLISHED 29 November 2024
on innovative solutions. Internet of Things (IoT) technology, by integrating
CITATION
sensing, network communication, data processing, and security technologies,
Wang B, Shi X, Han X and Xiao G (2024) The offers promising approaches to address issues such as nursing personnel
digital transformation of nursing practice: an
shortages and rising healthcare costs. This paper reviews the current state
analysis of advanced IoT technologies
and smart nursing systems. of IoT applications in healthcare, including key technologies, frameworks for
Front. Med. 11:1471527. smart nursing platforms, and case studies. Findings indicate that IoT significantly
doi: 10.3389/fmed.2024.1471527
enhances the efficiency and quality of care, particularly in real-time health
COPYRIGHT
© 2024 Wang, Shi, Han and Xiao. This is an monitoring, disease management, and remote patient supervision. However,
open-access article distributed under the challenges related to data quality, user acceptance, and economic viability
terms of the Creative Commons Attribution
License (CC BY). The use, distribution or
also arise. Future trends in IoT development will likely focus on increased
reproduction in other forums is permitted, intelligence, precision, and personalization, while international cooperation
provided the original author(s) and the
and policy support are critical for the global adoption of IoT in healthcare.
copyright owner(s) are credited and that the
original publication in this journal is cited, in This review provides valuable insights for policymakers, researchers, and
accordance with accepted academic practitioners in healthcare and suggests directions for future research and
practice. No use, distribution or reproduction
is permitted which does not comply with technological advancements.
these terms.

KEYWORDS

Internet of Things, healthcare, smart platforms, technical challenges, international

cooperation, policy recommendations

1 Introduction
Medical care involves the utilization of pertinent clinical data in conjunction with
physicians to deliver effective treatments (1). Globally, healthcare systems face challenges
such as an aging population, the prevalence of chronic diseases, shortages of healthcare
personnel, rising medical costs, and increasing patient expectations. According to United
Nations data, population aging is a distinct global trend of our times, In 2021, there were
761 million people aged 65 and over globally, and this figure is projected to rise to 1.6
billion by 2050. The population aged 80 and above is growing even more rapidly. Regarding
cardiovascular diseases, in 2016, 8.4 million people died from cardiovascular diseases in
South Africa (one of the BRICS nations). Between 1992 and 2016, the age-standardized
mortality rate for cardiovascular diseases in the BRICS countries declined by −17%, which
was less than the decline seen in North America (−39%) (2). For chronic respiratory
diseases, between 1990 and 2017, the incidence of CRD, COPD, pneumoconiosis, and

Frontiers in Medicine 01 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

asthma declined, whereas the incidence of interstitial lung disease 2019. These smart devices not only improve the efficiency of care
and sarcoidosis showed an upward trend. Elderly individuals but also reduce costs.
are particularly susceptible to CRD, except for asthma. The The integration of IoT technologies into healthcare has
acceleration of population aging and increased exposure to risk significantly enhanced the quality and safety of care, while also
factors such as particulate matter pollution will contribute to driving the digitization of nursing processes (18). In terms of
the growing burden of chronic respiratory diseases globally (3). process digitization, IoT devices have enabled many automated
The International Labour Organization (ILO) estimates that by management functions (19, 20). This paper will analyze key IoT
2030, there will be a global shortage of 18 million healthcare technologies, discuss the design framework for a smart IoT nursing
workers (4). To address these issues, the United States enacted platform, and explore future technological advancements.
legislation in 2009 to promote the comprehensive development
of healthcare informatics (5), and China’s 14th Five-Year Plan
emphasizes the role of information technology in driving high- 2 Key IoT technologies
quality healthcare (6). The COVID-19 pandemic has further
highlighted the importance of quality healthcare (7), while the rapid IoT (Internet of Things) technologies encompass a range
development of 5G technology has increased the demand for high- of essential components, including sensing technologies,
quality care, accelerating the progress toward smart healthcare. networking technologies, data processing technologies, and
The Internet of Things (IoT) offers the potential for intelligent security technologies. Sensing technologies utilize various
care through the collection of information via sensors and sensors (such as temperature, humidity, and light sensors) to
the transmission of this data for the intelligent monitoring collect environmental data, forming the foundation of IoT
and tracking of patients. IoT’s terminal sensing layer, including systems. Networking technologies transmit these data via
smart bracelets, remote monitoring devices, and wearable sensors, wireless communications (such as Wi-Fi, 5G, and LoRa) and
enables healthcare professionals to obtain real-time health wired communications (such as Ethernet) to cloud or local
data from patients. servers, enabling device-to-device connectivity. Data processing
This data includes vital signs such as heart rate, blood pressure, technologies leverage big data analytics and artificial intelligence
glucose levels, and sleep patterns, which can help in early detection (AI) to extract valuable information from vast datasets, enhancing
and timely intervention for health issues. Umer et al. (8) utilized system intelligence and automation. Lastly, security technologies
IoT to construct an ET-CNN model for remote monitoring of heart ensure data privacy and security, preventing cyberattacks and
rate in cardiac patients with an accuracy of 0.9524. Alshammari data breaches, which is a critical aspect of IoT applications. These
(9) employed an IoT-based MQTT model for accurate detection of technologies collectively form the technical framework of IoT,
patients’ vital signs and secure data transmission. Moreover, IoT driving its widespread adoption in smart homes, smart cities, and
technologies can be combined with artificial intelligence (AI) and smart healthcare.
big data analytics to provide personalized health recommendations
and treatment plans tailored to each patient’s unique health needs.
Astell et al. (10) provided personalized tablets for long-term 2.1 Sensor networks and data acquisition
care residents to enhance their quality of life. Ni Ki et al. (11)
used a Latent Dirichlet Allocation model based on IoT to tailor Sensor networks and data acquisition are core technologies
treatment plans for diabetic patients, improving their outcomes. in IoT. A sensor network consists of multiple sensor nodes
This approach not only enhances the precision and effectiveness of connected through wireless communication protocols (such as
treatments but also empowers patients to better manage their own Zigbee and LoRa) to enable real-time collection and transmission
health, improving their overall quality of life. of environmental data (such as temperature, humidity, and
The application of Internet of Things (IoT) technologies pressure). These data are uploaded to the cloud or local servers,
plays a crucial role in enhancing nursing efficiency and reducing processed through big data analytics and machine learning, and
costs. Traditional nursing models often require substantial human transformed into valuable information for smart decision-making
resources and time, particularly in geriatric care and chronic disease and automated control, improving system efficiency and reliability.
management. Through automation and intelligent means, IoT
technologies can significantly alleviate the burden on healthcare 2.1.1 Biomedical sensors and wearable devices
providers and decrease medical expenses (12, 13). Partners Recent advancements in biomedical sensors and wearable
HealthCare (14) provided home monitoring for over 3,000 patients devices focus on addressing challenges such as power supply, sensor
with congestive heart failure, resulting in a 44% reduction in sensitivity, selectivity, and communication. Li et al. (21) leveraged
hospital readmissions over six years and saving more than $10 the flexibility of liquid metal gallium to seamlessly integrate it
million. Mullins et al. (15) found that through the application with human tissue, enabling real-time health monitoring and
of IoT in healthcare, consultation times were reduced by over early issue detection. Wang et al. (22) reviewed nanomaterials-
two minutes, and patient out-of-pocket costs decreased by $1,229 based stretchable self-powered technologies, achieving intelligent,
to $2,700. Smart pillboxes can remind patients to take their miniaturized, and wireless wearables. Tricase et al. (23) utilized
medications on time, ensuring continuity and effectiveness of printed electrode technology to prepare graphite electrodes
treatment and reducing complications from missed or incorrect for monitoring L-lactate and D-glucose, with sensitivities of
doses (16). Furthermore, El-Saleh et al. (17) noted that the global 1.32 mA/mM and 28.4 µA/mM, respectively. Nguyen et al. (24)
digital health market was valued at approximately $175 billion in developed freeze-dried, cell-free genetic components integrated

Frontiers in Medicine 02 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

into flexible materials for biosensors that achieve high sensitivity the significant impact of mobile health solutions in enhancing
and specificity without power or liquid handling, suitable for remote patient monitoring across various medical domains.
wearable applications. Despite the enhancement of telemonitoring in various
healthcare domains through mobile health solutions, there are also
2.1.2 Environmental sensing sensors in hospital several limitations associated with these technologies. For example,
environment monitoring the reliability and accuracy of the devices may be affected by
Environmental sensing sensors play a critical role in hospital environmental factors, and data privacy and security remain critical
environment monitoring, especially in intensive care units and considerations. Additionally, given the rapid pace of technological
refrigeration facilities. These sensors monitor parameters such as advancements, ensuring that the devices are always up-to-date
temperature, humidity, carbon dioxide levels, and acoustic noise, poses another challenge.
providing real-time data to maintain optimal conditions. Yasin
et al. (25) conducted real-time monitoring of indoor air quality
using IoT sensors, demonstrating adaptability across various 2.2 Wireless communication
work environments. Sivakumar et al. (26) used Ubidots IoT to technologies
monitor temperature, humidity, and refrigeration equipment in
specialized hospital areas, issuing alerts when limits are exceeded. Wireless communication technologies are integral to IoT
Abubeker and Baskar (27) employed a wireless sensor network applications in smart agriculture, smart homes, smart cities, and
and wireless body area network-assisted biosensors to track volatile smart healthcare. Various wireless communication technologies,
organic compounds and other atmospheric constituents, limiting such as 5G, WiFi, ZigBee, LoRa, NB-IoT, and Bluetooth, are widely
the spread of non-ventilator-associated pneumonia in hospitals, used in IoT systems as shown in Figure 1.
achieving good results in computing, communication, storage, and
energy utilization. Wilson et al. (28) used CO2 detection to quantify 2.2.1 High-speed wireless communication
ventilation in hospital environments, effectively reducing the risk of networks
airborne pathogen transmission between healthcare workers and High-speed wireless communication networks are crucial for
patients. Alabere et al. (29) used the HC-SRO4 ultrasonic sensor optimizing the interconnectivity of medical devices and improving
to monitor intravenous fluid bags in hospitals, transmitting fluid healthcare services and supply chain management. Srinivasu et al.
level information via web, alleviating real-time monitoring issues (36) proposed a 6G-driven networking framework for healthcare
for intravenous infusions. Liu et al. (30) utilized superconducting applications, enabling fast and efficient communication among
material sensors and deep learning for environmental monitoring, medical devices for smart diagnostics, patient-centered treatments,
detecting humidity levels with a sensing accuracy exceeding 93%. and remote monitoring. Donghua et al. (37) introduced a novel
Although these sensors offer significant benefits, such as real- cross-ring neural network model for image compression and
time monitoring and automatic adjustment, they also possess security in wireless body area networks (WBANs), demonstrating
certain limitations. For instance, wireless sensor networks may efficient high-speed data processing capabilities. Sodhro et al.
encounter issues such as signal interference or battery life (38) proposed an adaptive QoS (Quality of Service) computation
constraints. Moreover, some sensors require a continuous data algorithm for efficient monitoring of medical data processing,
connection, which can present a challenge in remote areas. enhancing network performance in medical applications. Donghua
et al. (37) introduced a cross-ring neural network for image
2.1.3 Mobile health solutions in remote patient compression and security in WBANs, demonstrating efficient data
monitoring processing and resistance against attacks. These studies collectively
Mobile health solutions have made significant strides in highlight the importance of high-speed network connections in
remote patient monitoring. Alasmary (31) integrated IoT using the optimizing medical device interconnectivity to improve healthcare
Scalable Digital Health framework for real-time tracking of health services and supply chain management.
parameters, enabling remote patient monitoring through delay-
aware edge computing, enhancing accessibility and responsiveness. 2.2.2 Low-power wireless communication
Raparla et al. (32) used Dozee.ai and Qure.ai devices for remote protocols
monitoring of COVID-positive patients, significantly assisting Low-power wireless communication protocols, such as
doctors in tracking patients’ physical parameters and reducing ZigBee and Bluetooth Low Energy (BLE), are used for medical
healthcare costs. Ren et al. (33) observed response pattern trends device communication, particularly suitable for wireless wearable
in remote patient monitoring for concussed adolescents, indicating sensor systems due to their low energy consumption and
that demographic factors, injury history, and time post-injury good network range. Rehman et al. (39) proposed a reliable
influence higher evening incidence rates. Kedwan (34) discussed bidirectional data transmission method using ZigBee for secure
the implementation of a remote physiological monitoring system medical IoT, enhancing network performance and security
in cardiac care centers, showcasing the impact of health informatics for effective communication among medical devices. Rehman
on improving patient care efficiency. Vaghasiya et al. (35) proposed et al. (40) illustrated that ZigBee technology can enable efficient
an integrated FePS3/rGO and Ti3C2 remote healthcare platform communication among medical devices but requires enhanced
for remote health assessment, demonstrating a wearable device security measures to prevent various network attacks. Padma
for real-time monitoring of physiological parameters, facilitating and Babu (41) achieved efficient and secure communication in
remote patient monitoring. Overall, these case studies demonstrate ZigBee networks using DNA sequence encryption, optimizing

Frontiers in Medicine 03 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

FIGURE 1
Major communication protocols in IoT technology.

encryption for limited computational resources and enhancing integration of mobile edge computing with 5G technology in
communication security among medical devices. Yu et al. (42) healthcare services, exploring how this integration improves service
combined topology structure and hybrid routing strategies responsiveness and efficiency, providing faster and safer patient
to optimize load balancing in BLE networks, improving data processing and analysis. Hemmati et al. (48) systematically
communication efficiency among medical devices compared reviewed the implementation of edge artificial intelligence for
to traditional methods like ZigBee. Wang et al. (43) studied a healthcare big data, focusing on real-time activity recognition
novel CTC protocol designed with pseudo-random sequences and patient monitoring. They emphasized the importance of edge
for low-cost direct communication between WiFi and ZigBee in computing in reducing latency and accelerating the processing of
noisy indoor environments, achieving synchronization times less medical data. Urblik et al. (49) proposed a modular framework
than 0.5 ms and accuracy greater than 84% at channel occupancy for edge computing that supports real-time data processing and
rates up to 50%. Sriram (44) developed a low-power BLE protocol analysis in healthcare. The study highlighted how edge computing
enabling efficient communication among medical devices in reduces latency and bandwidth usage, allowing for more direct
wireless sensor networks (WSNs) with a maximum data transfer and effective responses to patient data. Verma and Fatima (46)
rate of 8.4 Mbps and extended communication ranges up to reviewed how edge computing improves the security and reduces
400 meters. Kozhubaev et al. (45) developed BLE5.0 technology latency of IoT healthcare systems by processing and analyzing data
supporting multi-node data collection, high-speed transmission, near the source, avoiding the need to transmit all data to a central
and low power consumption, enabling efficient communication cloud. These studies collectively illustrate the crucial role of edge
among medical devices suitable for wearable medical applications. computing in enhancing the real-time responsiveness of healthcare
systems, enabling better and faster patient care.
Although edge computing brings numerous advantages, it
2.3 Edge computing and cloud also entails certain limitations. Firstly, edge devices typically have
computing limited computational capabilities and storage capacity, which may
constrain the execution of complex data analysis tasks. Secondly,
Edge computing and cloud computing play complementary since edge computing necessitates maintaining software updates
roles in IoT systems. Edge computing processes data near and service consistency across a distributed network, it adds to
the source or at local nodes, reducing latency and bandwidth the management complexity. Lastly, the widespread adoption of
requirements, making it suitable for real-time and latency-sensitive edge computing could lead to increased investment in hardware
tasks. Cloud computing provides powerful centralized processing infrastructure, including the deployment costs of edge servers and
and storage capabilities, ideal for large-scale data analysis and gateway devices. In summary, while edge computing enhances the
long-term storage. Combining both approaches allows IoT systems real-time responsiveness of healthcare systems, it is also imperative
to achieve efficient data processing and transmission while to overcome these technical challenges.
maintaining system flexibility and scalability.
2.3.2 Cloud computing
2.3.1 Edge computing Cloud computing plays a key role in managing large volumes
Edge computing enhances real-time and sensitive tasks in IoT of medical data and providing flexible services for the healthcare
systems. Verma and Fatima (46) explored how edge computing industry. Cloud technology integrated with artificial intelligence
enhances smart healthcare applications through real-time analysis, and distributed data analysis models improves the efficiency of
highlighting the benefits of reduced latency and improved data managing electronic health records, ensuring continuous access
privacy, enabling healthcare providers to respond faster and to personalized healthcare information. Lakhani (50) reviewed
more effectively to patient needs. Ghadi et al. (47) discussed the how cloud integration in healthcare can handle massive medical

Frontiers in Medicine 04 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

data and provide flexible services, enhancing patient care, treatment plans, and improve diagnostic accuracy. Prajapati and
operational efficiency, and the overall potential of healthcare Prajapati (55) reviewed various AI-driven CDSS, emphasizing
delivery. Himanshu and Punhani (51) illustrated how cloud their applications in diagnosis and treatment planning across
computing provides flexibility, scalability, and cost-effectiveness different medical fields. Ferdush et al. (56) surveyed the role
for managing healthcare data, enabling personalized medicine and of AI language models, such as ChatGPT, in clinical decision
predictive analytics. Dhote et al. (52) demonstrated how cloud support, including their applications in diagnosis and treatment
computing efficiently processes large volumes of medical data planning, and the challenges of integrating these systems into
through Distributed Data Analysis and Organizational Models clinical practice. Demuth et al. (57) studied an AI-based decision
(DDAOM), enabling flexible service provision and minimizing support system called StrokeCopilot aimed at aiding the treatment
errors in mobile healthcare systems. Praveen et al. (53) introduced a of acute ischemic stroke, improving the timeliness and outcomes
novel approach, the DACAR platform, ensuring secure storage and of treatment. Eisenstein (58) discussed Shmulevich’s group’s digital
processing of sensitive medical data in the cloud, enhancing fusion- twin project for acute myeloid leukemia, using clinical data to
based healthcare systems with scalability and precision. Zhang predict drug responses and avoid side effects, with a focus on
et al. (54) explained how the integration of cloud computing with real-world data to enhance personalized treatment AI models.
advanced algorithms, such as the Normal Distribution Method Savage (59) examined how AI uses deep learning algorithms to
and Incremental Higher Order Possibility C-Means Algorithm, integrate diverse data types (imaging, clinical indicators, genetic
enhances the processing of large medical datasets, ensuring testing) to improve diagnostic accuracy. The combination of
efficient data segmentation, processing, and clustering across different data modalities enhances AI’s ability to make precise
multiple hospitals. diagnoses. Mittermaier et al. (60) explored the collaboration
Although cloud computing offers numerous benefits, it between AI systems and physicians to improve clinical decision-
also presents certain limitations. Firstly, reliance on internet making, particularly in routine care settings, highlighting the
connectivity means that service quality can be compromised under challenges and strategies for effective implementation. Luchini
unstable network conditions. Secondly, data privacy and security et al. (61) highlighted how advances in machine learning help
represent major challenges for cloud computing, particularly when oncologists determine the best treatment strategies for cancer
dealing with sensitive medical information. While encryption patients by predicting drug responses and avoiding side effects
and other security measures can mitigate these concerns to a through the analysis of clinical data. Lenharo (62) summarized
degree, completely eliminating risks remains virtually impossible. how AI integrates data from various sources, such as imaging,
Additionally, due to the sensitivity of medical data, compliance clinical indicators, and genetic testing, to improve diagnostic
and regulatory requirements may restrict the application of cloud accuracy and overall diagnostic processes. Real-time data collected
computing in certain regions. by smart sensors and devices facilitates remote monitoring and
immediate medical decision-making, improving patient care and
health management.
2.4 AI and big data analytics Despite the numerous advantages of AI and big data analytics in
healthcare, such as improved diagnostic accuracy and personalized
treatments, these technologies also come with certain limitations.
AI and big data analytics play pivotal roles in medical IoT,
Firstly, the quality and integrity of data are paramount for the
enhancing diagnostic accuracy, personalizing treatment plans, and
effectiveness of AI models; erroneous or incomplete input data
predicting disease trends. In the domain of medical IoT as shown
can lead to incorrect diagnostic outcomes. Secondly, privacy and
in Figure 2, artificial intelligence and big data analytics serve as
ethical concerns continue to pose barriers to the application of
transformative agents, significantly enhancing diagnostic accuracy,
AI technologies in the medical field. Additionally, the lack of
personalizing treatment strategies, and forecasting disease patterns
transparency and explainability in AI systems may hinder the trust
with remarkable precision. The process initiates with the collection
of both medical professionals and patients. Finally, the widespread
of comprehensive training datasets meticulously sourced from
adoption of AI technologies requires ongoing training and support
various repositories, including electronic health records (EHRs),
to ensure that healthcare professionals can properly understand
wearable devices, and patient surveys. These data are then subjected
and utilize the information provided by these technologies.
to an intensive training regimen, wherein sophisticated algorithms
are trained to discern patterns and establish correlations within the
information.
Once the training phase is complete, the AI model 2.5 Privacy and security in electronic
becomes a potent instrument for healthcare professionals. In health records
operational mode, the model receives real-time inputs, processing
them through a structured decision-making framework. This One fundamental challenge in using electronic health records
reconstructed model generates predictive outputs that facilitate (EHRs) in healthcare is protecting patient privacy. Kiania et al.
early disease detection, personalized treatment recommendations, (63) reviewed how blockchain technology enhances integrity,
and forecast future disease trends. The entire process underscores privacy, and security, facilitating rapid action by experts and health
the potential of AI and big data analytics to revolutionize healthcare organizations. Through smart contracts, a secure and effective
delivery and improve patient outcomes. infrastructure can be established, improving healthcare quality and
AI-driven clinical decision support systems (CDSS) analyze individual wellbeing. Wu et al. (64) proposed the use of blockchain
vast amounts of medical data to predict disease trends, personalize technology for securing privacy information in healthcare systems,

Frontiers in Medicine 05 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

FIGURE 2
AI and big data-driven medical IoT for enhanced diagnostics and personalized healthcare.

with storage response times kept below 1,000 ms and maximum The design principles include modularity for scalability, data
information throughput reaching 550 kbit/s, utilizing elliptic curve security and privacy protection, high efficiency with low power
Diffie-Hellman keys to provide effective protection of information. consumption, interoperability and standardization, as well as user-
Zarour et al. (65) designed a hybrid fuzzy-ANP-TOPSIS method friendliness and ease of use (69, 70). These principles ensure the
to evaluate the impact of blockchain technology models on stability, flexibility, and maintainability of the platform, providing
maintaining the security of EHRs. Zhang et al. (66) proposed a support for applications in smart cities, smart manufacturing, and
5G-integrated PTBM scheme capable of tracking patients and close more. The overall architecture of the intelligent nursing platform
contacts while protecting patient information. Zhang et al. (67) based on IoT smart sensing settings is illustrated in Figure 3.
introduced a medical data sharing scheme based on consortium The intelligent Internet of Things (IoT) nursing platform
blockchain, strengthening key management to protect patient adopts a multi-layered architecture design encompassing device
privacy. Alsayegh et al. (68) combined private blockchain with
terminal layers, data layers, cloud platform layers, nursing
smart contracts on a consortium blockchain to encrypt and securely
application layers, and integration with existing medical systems.
store and read medical personal information. Srinivasu et al. (36)
The device terminal layer integrates a variety of IoT sensing
used a knapsack-based system with a knapsack greedy algorithm to
devices and actuators, including wearable health monitoring
encrypt and decrypt medical brain tumor data, achieving shorter
devices, smart home appliances, and medical instruments,
computational times (the proposed blockchain-based knapsack
complemented by edge computing nodes for primary data
method required 68.81 s to encrypt 100 data blocks).
processing and anomaly detection. The data layer relies on
distributed storage systems and big data processing frameworks
to achieve efficient storage and preprocessing of massive datasets,
3 Smart IoT nursing platform applying advanced machine learning algorithms for pattern
framework recognition and predictive analytics. As the core of the platform,
the cloud platform layer not only provides support for device
3.1 Overview of platform architecture management and cross-system communication but also integrates
business intelligence tools to facilitate the visualization of data
The architecture of a smart Internet of Things (IoT) nursing analysis, supporting third-party service integration to enhance
platform comprises four primary layers: the perception layer, platform functionality. The nursing application layer is designed
the network layer, the platform layer, and the application layer. for end-users, offering real-time health monitoring, early warning,

Frontiers in Medicine 06 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

3.2.1 Sensor deployment strategies for real-time

monitoring modules
Strategies for deploying sensors in real-time monitoring
modules are critical across different scenarios. Figure 4 illustrates
various IoT wearable devices placed at different body locations and
serving specific functions for collecting vital signs and other types
of data.
Sundas et al. (74) reviewed hierarchical architectures for IoT
that convert sensor data into clinical inputs, encompassing sensing,
transmission, processing, storage, mining, and learning to enhance
real-time medical monitoring in IoT applications. Liang et al.
(75) proposed two algorithms based on sub-module functional
optimization to maximize surveillance capabilities using mobile
sensors in large pipeline networks. Jiang et al. (76) introduced
an enhanced binary particle swarm optimization (MBPSO)
strategy to determine the minimum number of sensors required
for effective real-time monitoring in grid systems, achieving
FIGURE 3 efficient monitoring of over 89.6% of conductor temperature high
Smart IoT nursing platform framework. events with a root mean square error of less than 0.8◦ C in
reconstructed conductor temperature distributions. Wang et al.
(77) developed a graph flow-based algorithm for intelligent sensor
and nursing management functionalities via an intuitive human- network deployment offset detection to optimize sensor node
machine interaction interface. At the level of integration with updates for efficient monitoring. Rosa et al. (78) presented a
existing medical systems, standardized communication protocols system that uses various sensors, such as electrocardiograms,
such as HL7 and FHIR, along with health information exchange temperature, and motion sensors, for disease analysis and
mechanisms, are implemented to ensure interoperability with continuous monitoring, with data transmission accuracy rates
traditional healthcare information systems, strictly adhering to exceeding 95%. Balakrishnan and Ranganayaki (79) introduced a
regulatory requirements such as HIPAA to safeguard data security wireless health monitoring system that employs sensors for real-
and privacy protection. time patient data collection, transmission, and alerts, enhancing
Successful implementations of smart nursing platforms have healthcare monitoring efficiency and patient safety. Liu et al. (80)
been reported. Zhou et al. (71) described the successful deployment discussed the use of low-cost sensors in healthcare monitoring with
of an intelligent health management system in a nursing home, wireless communication (77%) and algorithms such as SA, SVM,
utilizing IoT, deep learning, and cloud computing to continuously and KNN. Harb et al. (81) proposed a sensor-based data analysis
monitor and intervene early in elderly healthcare. Wen et al. system for real-time patient monitoring in healthcare, focusing on
(72) demonstrated that a Smart Patient Care System (SPCS) emergency detection, sensing frequency adaptation, and patient
had been successfully implemented in medical centers, reducing condition prediction. Shafi et al. (82) proposed an IoT-based patient
nurse response times, decreasing false alarms, and enhancing care health monitoring system that uses sensors for real-time data
efficiency and quality. Boo and Oh (73) surveyed a pilot project in collection, transmission to cloud storage, and remote access by
South Korea that employed AI-enhanced IoT for elderly healthcare, healthcare professionals. These sensor deployment strategies not
finding increased customer satisfaction, improved health behaviors, only enhance patient care but also assist healthcare professionals in
and governmental support as key factors contributing to the making critical decisions based on accurate and timely information.
success of such initiatives. These case studies underscore the
potential benefits of smart nursing platforms in enhancing 3.2.2 Application of AI algorithms in disease
healthcare services, improving patient outcomes, and optimizing management
nursing workflows. In disease management, artificial intelligence (AI) algorithms
are increasingly used in analytics and predictive modules. These
algorithms, such as machine learning models, have shown promise
3.2 Key IoT components and functions in optimizing treatment strategies and improving patient outcomes
in chronic conditions like diabetes.
Key components of IoT systems include sensors and Pandey et al. (83) demonstrated that AI algorithms predicted
actuators (for data acquisition and command execution), network tuberculosis progression with 87.5% accuracy and 88.2% sensitivity,
communication modules (ensuring device connectivity), gateways showcasing the potential of AI to transform disease management
(processing and transmitting data), IoT platforms (managing through personalized treatment plans based on clinical data.
devices and analyzing data), and security components (protecting Grampurohit and Sagarnal (84) utilized AI algorithms such as
data and devices from threats). Functionally, IoT systems random forests, SVM, and Naïve Bayes for disease prediction,
enable real-time monitoring, data analysis, remote control, achieving adjusted random forest accuracy rates of 90%,
and automation across various domains including smart cities, demonstrating the potential of AI in disease management.
industrial IoT, and smart homes. Cho et al. (85) developed an ML-based predictive model to assess

Frontiers in Medicine 07 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

FIGURE 4
IoT wearable devices for vital sign monitoring and other data collection.

participants’ five-year risk of atherosclerotic cardiovascular disease, 3.2.3 Design and case studies of automated
showing moderate to good discrimination (C-statistic 0.70–0.80). response mechanisms
Glass et al. (86) used Keras for AI modeling and training, where Automated response mechanisms in healthcare are designed
AI algorithms successfully distinguished myocyte injury (1R2 to leverage AI and machine learning technologies to automatically
grade) from non-myocyte injury (1R1A grade) with 94% validation identify emergencies through real-time patient data monitoring
accuracy. ACR and healing injury identification accuracy was and provide timely interventions. These systems integrate sensors,
98–99%, while normal myocardial cell identification accuracy was data analysis tools, and alert systems to ensure rapid response
99%. Yu (87) analyzed multiple indicators using eight different by caregivers, optimizing therapeutic effects (93, 94). Automated
algorithms based on the UCI dataset, achieving the highest response mechanisms also include personalized care plans and
accuracy and reliability in predicting heart disease. Tarumi et al. intelligent reminders, enhancing patient safety and care quality
(88) utilized AI algorithms for predictive analysis, decision support (95). In this way, healthcare can achieve higher efficiency and
system reinforcement, and integration with electronic health accuracy. Ni et al. (96) used automatic search relevance assessment
records to improve patient outcomes in chronic disease care. Isiaka in healthcare environments, highlighting the role of infrared
et al. (89) illustrated the integration of AI into infectious disease technology in improving search engine performance. Jahanshahi
surveillance, enabling early detection, outbreak management, and et al. (97) proposed an intelligent auto-reply to generation system
proactive resource allocation, thereby strengthening public health for medical chat services, achieving 83.28% accuracy through
responses and ensuring community welfare. Farrag et al. (90) historical doctor-patient message analysis and machine learning
detailed AI algorithms in chronic hepatitis C virus management, algorithm training. Bagattini et al. (98) studied the implementation
including the prediction of new therapies, prioritizing patients of an automated system in a central pharmacy at a private hospital
for antiviral drugs, and outperforming traditional diagnostic in Latin America, resulting in reduced dispensing errors down
tools in detecting infections and related diseases. Zhuhadar and to 0.018%, indicating improved pharmacy management. These
Lytras (91) described AutoML technology in diabetes diagnosis, automated systems are critical in major transformations within
utilizing AI algorithms for predictive modeling and identifying global healthcare institutions, optimizing resources and processes.
risk factors such as glucose levels, body mass index, diabetes
pedigree function, and blood pressure, thereby reinforcing
disease management in healthcare. Kargbo (92) detailed AI
algorithms in disease management that analyze biomarker data for 3.3 Security and privacy protection
health predictions, enabling early intervention and personalized strategies
treatment plans.
These cases demonstrate the potential of AI to revolutionize Security and privacy protection strategies in IoT-enabled
clinical decision-making, personalize treatment plans, and healthcare encompass several critical aspects, including the
optimize interventions to improve patient outcomes and adoption of encryption technologies to secure data transmissions
public health results. and ensure secure communications between devices, the

Frontiers in Medicine 08 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

implementation of strict access controls to limit data access professional factors (109). In Western countries, blogs have
rights, regular security assessments and vulnerability patching been integrated into nursing education to enhance learning
to prevent cyberattacks, the utilization of data anonymization outcomes, while Eastern countries are still exploring the potential
techniques to protect patient privacy, and the establishment and of this technology in nursing education (110). De Raeve et al.
adherence to relevant privacy protection laws and standards to (111) found that out of 35 European countries surveyed,
ensure compliance in data handling. 11 have national legislation specifying minimum educational
Recent advances in data security technologies in the healthcare requirements for nurses, with most requiring a master’s degree
sector have witnessed the emergence of innovative methods. for advanced practice nurses. Additionally, Estonia, Iceland,
Odera (99) highlights recent data security technologies including Malta, and Sweden mandate at least two years of practical
digital image encryption, steganography, biometrics, rule-based experience (112). The use of mobile health systems, particularly
policies, prescriptive analytics, blockchain, cloud security, in China, has facilitated the development of Java Web-based
MapReduce, machine learning algorithms, and anonymization intelligent outpatient care service platforms to address evolving
techniques. Madavarapu et al. (100) introduced an Advanced healthcare needs (67, 113). In some advanced regions of China,
Integrated Data Security (AIDS) framework for cloud healthcare 5G networks and artificial intelligence robots have been deployed
systems, combining encryption, access control, anomaly detection, in smart nursing platforms, enhancing personalized medical
and intrusion prevention to enhance data security. Basha services and accelerating digital transformation in healthcare
(101) enhanced the security of healthcare data using quantum (114). In the United States, emphasis is placed on integrating
cryptography, providing robust encryption that surpasses AES in smart nursing platforms into home care delivery processes to
terms of both efficiency and confidentiality (quantum cryptography improve care quality and reduce costs, as evidenced by studies
requires 352,237 milliseconds, compared to 310,285 milliseconds on the integration of Smart Care Platforms (SCPs) into home
for AES), ensuring secure storage and regulatory compliance of care provision (115, 116). Perspectives from Italy, Brazil, and the
patient information. Khan et al. (102) used an adaptive hybrid Philippines highlight the integration of clinical nursing information
encryption and steganography model to strengthen data security systems with electronic health records and the challenges and
in the healthcare industry by encrypting and hiding diagnostic text advancements in nursing informatics across different healthcare
data within medical images, ensuring secure transmission through systems (117).
the Internet of Healthcare Things (IoHT). Abdelaziz and Alia The implementation of Internet of Things (IoT) technologies
(103) proposed an integrated artificial intelligence framework for in healthcare settings in low- and middle-income countries
information security and management, leveraging AI algorithms (LMICs) has been a topic of interest in recent literature. (118)
for secure automated transactions to enhance data security in conducted a multi-country case study focusing on the adoption
healthcare systems. These technologies address vulnerabilities and implementation of a network of university hubs for social
caused by data breaches and unauthorized access, ensuring the innovation in healthcare delivery across Africa, Asia, and Latin
confidentiality, integrity, and privacy of sensitive medical data America. The study aimed to describe the model, components,
stored and processed in cloud environments. and implementation process of these hubs, identifying enablers and
As the digitization of medical information continues to barriers that could be relevant to other LMIC universities interested
increase, legal requirements for data usage and privacy protection in social innovation. In the context of the COVID-19 pandemic,
in healthcare become paramount. Countries such as Russia (119) highlighted the importance of early implementation of
and India are focusing on strengthening their data protection effective measures by governments in controlling the spread of
frameworks to safeguard patient privacy (104, 105). In Europe, the the virus, particularly in LMICs. The study emphasized that
use of patient information is subject to numerous legal and ethical despite wealthier countries having elevated healthcare capacity,
obligations, with the General Data Protection Regulation (GDPR) early and incremental government actions are crucial in LMICs
emphasizing explicit consent for data processing, which contrasts to prevent the rapid spread of the virus. (120) focused on
with common law practices (106, 107). Although informed consent the safe handling of chemotherapy drugs in LMIC healthcare
plays a crucial role in data handling, the obligation to share data facilities, conducting a survey among 53 facilities in different
to improve healthcare may conflict with existing privacy laws and income categories. The study provided an overview of practices
regulations (108). The integrity, availability, and confidentiality of in dealing with chemotherapy drugs, shedding light on the
healthcare information are essential, necessitating a comprehensive challenges faced by healthcare facilities in LMICs. Furthermore,
approach to data protection within the evolving landscape of (121) examined national hospital accreditation programs in
healthcare data processing. the Eastern Mediterranean Region, including case studies from
Egypt, Jordan, and Lebanon. The study addressed design and
implementation issues of these programs, offering insights into
the healthcare quality improvement initiatives in LMICs. In a
4 IoT Implementation case studies in
study by Dkhimi et al. (122), the authors synthesized findings
healthcare from six country case studies examining multiple funding flows
to public healthcare providers in LMICs. The qualitative findings
4.1 Global application of IoT in nursing revealed the potential impact of multiple payment streams on
healthcare provider behavior, highlighting the complexities of
Comparative analyses of smart nursing platforms in developed funding mechanisms in LMIC healthcare systems. Overall, the
countries reveal varying levels of technological integration and literature review indicates a growing interest in exploring the
development, influenced by historical, geographical, political, and implementation of healthcare initiatives, such as social innovation

Frontiers in Medicine 09 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

hubs, COVID-19 control measures, chemotherapy drug handling Qin et al. (131) developed an IoT cloud computing platform
practices, hospital accreditation programs, and funding flows in with an IN model, where wireless temperature monitoring systems
LMICs. These studies provide valuable insights into the challenges (WTMS) and vital sign monitoring systems (VSMS) play a crucial
and opportunities for implementing healthcare interventions in role. Real-time monitoring of patients through radiofrequency
resource-constrained settings. identification of sensors attached under the armpit significantly
improved the efficacy of HGG treatment for pediatric pneumonia
sepsis and reduced adverse reactions. Hu et al. (132) found that
4.2 Specific effects of IoT on enhancing implementing a tertiary enteral nutrition care system under the
nursing levels globally “internet + healthcare” model has been shown to improve nurses’
cognition, behavior, and core competencies in enteral nutrition
Abdulrazak et al. (123) utilized environmental sensors, safety care (P < 0.05), leading to positive clinical outcomes.
enhanced device monitoring, and change-point detection
algorithms to study urinary function in 16 French patients,
focusing on urinary tract infections and irritable bowel syndrome. 4.4 Technological efficacy and
The algorithm analyzed daily bathroom frequency and activity challenges
changes, enabling healthcare providers to track health status
through alerts, thereby improving diagnostic and therapeutic The application of the Internet of Things (IoT) in
outcomes. Yesmin et al. (124) demonstrated that IoT interventions healthcare has expanded considerably, bringing about significant
in healthcare improved hand hygiene compliance rates and staff technological benefits and challenges. Through real-time
experiences, with a direct reduction in patient falls leading to monitoring and data collection from sensors and devices,
improved nursing times. Abril-Jiménez et al. (125) found that IoT enables continuous monitoring of patients’ physiological
digital home hospitalization services based on IoT enhanced indicators, enhancing the precision of diagnostics and treatments.
patient autonomy, reduced hospital stays (from an average Additionally, the proliferation of remote healthcare and
of 11 to 6 days), implemented four disease-specific protocols nursing services provides convenience for patients in remote
with up to 16 different pathways, lowered readmission rates, areas and those with mobility issues, markedly improving
achieved 95% patient satisfaction, and increased professional healthcare efficiency.
trust and workload management. Mudawi (126) proposed an However, the quality and reliability of data pose significant
IoT-based intelligent ICU patient monitoring system capable of challenges to nursing decisions. The accuracy and completeness
real-time measurement of patient parameters, greatly assisting of data directly impact the reliability of medical decisions (133).
doctors and hospitals in continuous patient monitoring and Bernardi et al. (134) argue that well-established and validated
rapid decision-making. Yongjoh et al. (127) implemented the NU workflows for healthcare data quality assurance are beneficial
Medical system using blockchain technology in a Thai hospital for ensuring data quality. Poor dimensions and outcomes of
with 157 healthcare workers, achieving rapid and confidential data quality can be evaluated through various classification
access to medical conditions, enhancing staff efficiency and methods (135). Elucidating the intricate relationships among DQ
patient satisfaction. dimensions and their impacts on clinical, clinician, research,
business process, and organizational outcomes. It identified six
core dimensions of DQ—accessibility, accuracy, completeness,
4.3 Case analysis of IoT enhancing consistency, contextual validity, and currency—that collectively
nursing levels in China form the foundation of data quality. Notably, consistency was
recognized as a pivotal factor influencing all other dimensions,
Ni et al. (128) used telemedicine technology to promote while both consistency and accessibility exert significant influence
a renal anemia management system (the Red China project on all DQ outcomes. To address these DQ issues, we propose a set
aimed to develop a dialysis registration system based on the of solutions: Firstly, there is a need to enhance the management of
WeChat mobile platform) which resulted in a decrease in the data consistency to ensure uniformity across different data sources,
proportion of patients with hemoglobin levels < 8 g/dL from thereby mitigating errors arising from inconsistencies. Secondly,
4.96 to 4.08%. Wang and Liu (129) designed the RASAP-POCT optimizing data accessibility is essential, ensuring authorized
system utilizing IoT to support real-time data collection, on- users can efficiently obtain necessary information, which in turn
site screening, and integration with contact tracing systems, enhances the effectiveness of clinical decision-making. Lastly, it is
providing saliva sample test results within 20–30 min with lower imperative to establish a continuous DQ monitoring mechanism to
reagent complexity (approximately 50% less per reaction) and periodically evaluate the status of each DQ dimension and adjust
cost, while maintaining higher reliability, thus improving public data governance strategies accordingly to maintain high standards
health surveillance and intervention and enhancing SARS-CoV- of data quality. This framework provides healthcare institutions
2 testing in China. Shen et al. (130) described China’s “no with a systematic approach to addressing DQ issues, aiding in the
second visit” program, which leverages internet-based care delivery optimization of resource allocation and the enhancement of service
methods to enhance outpatient services, reducing waiting times quality and efficiency.
(appointment waiting time shortened by 4.05 min; consultation Data interoperability is a significant challenge in modern digital
time shortened by 0.37 min; payment waiting time reduced by environments, involving the ability to share and exchange data
3.09 min), increasing efficiency, and improving patient satisfaction. among multiple systems or platforms. However, in practice, data

Frontiers in Medicine 10 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

interoperability faces numerous issues such as incompatible data patient data while promoting innovation and interoperability
formats, insufficient data standardization, data security concerns, within the healthcare sector.
and lack of common data interfaces and protocols. These problems Moreover, the high initial investment and ongoing
not only limit the value and utilization efficiency of data but maintenance and update costs of IoT devices pose significant
may also have negative impacts on business decision-making and challenges to economic feasibility and sustained development
strategic planning. (141). While the initial investment in IoT devices may be high,
To address these data interoperability issues, a series of effective integrating these technologies into smart city initiatives can
measures should be taken. First, unified data standards and norms facilitate transitions toward greater sustainability (142, 143).
should be established to ensure consistency and interpretability Leveraging IoT and digital economy opportunities can promote
of data. Second, data security and privacy protection measures national development, particularly during crises such as the
should be strengthened by developing corresponding policies COVID-19 pandemic, demonstrating the potential for economic
and regulations to guarantee the safety and legal use of data. growth and resilience through smart education, smart cities, smart
Additionally, common data interfaces and protocols can be homes, and e-health services (140).
developed so that different systems or platforms can communicate Short-term gains include reduced equipment downtime
and interact with each other. Simultaneously, promoting open- through predictive maintenance, optimized inventory management
source technologies and tools can enhance data openness and that minimizes waste, and enhanced staff efficiency via real-time
sharing, improving data utilization and value. Finally, establishing tracking systems. For instance, the University of Washington
cross-domain and cross-industry cooperation mechanisms can Medical Center saw a reduction in equipment failure rates
facilitate data resource integration and sharing, driving innovation and maintenance costs after implementing IoT-based predictive
and development of data (136). maintenance programs.
With the advent of the digital era, issues related to data Long-term financial implications are even more profound.
security and privacy breaches have become increasingly severe. IoT facilitates preventive care and chronic disease management,
Unauthorized access, modification or destruction of data can lead
potentially decreasing hospital readmissions and treatment costs.
to loss, leakage or malicious use of data, which not only poses a
Additionally, IoT opens up new revenue streams through
threat to individual privacy but also may have serious implications
telemedicine and personalized health plans. Teladoc Health, for
for business operations and national security. To address these
example, expanded its telehealth offerings using IoT technology,
problems, it is necessary to establish sound management systems
boosting profitability.
and technical safeguards, enhance employee awareness training,
Case studies illustrate these benefits clearly. The Royal Adelaide
introduce legal and policy regulation, promote privacy protection
Hospital’s use of IoT for asset tracking and environmental
technologies and products, and raise public awareness and
monitoring led to better asset utilization and patient safety. Philips
self-protection capabilities. Only by continuously strengthening
Healthcare’s partnership with hospitals to deploy IoT-enabled
management and technological innovation can effective protection
patient monitoring systems demonstrated the ability to detect
of data security and personal privacy be achieved (136).
issues proactively, reducing complications and associated costs.
User acceptance and adherence represent another critical
The integration of IoT technologies in nursing practice can
challenge, especially for elderly individuals and those unfamiliar
significantly mitigate the impact of workforce shortages. By
with technology. Resistance to and difficulties in using
leveraging smart devices and sensors, IoT enables remote patient
IoT devices affect their adoption and effectiveness (137).
Personalized and intelligent nursing services provided by IoT monitoring, which reduces the need for constant on-site staffing
can increase acceptance among older adults (138). Furthermore, and allows healthcare professionals to manage a larger number
healthcare professionals can improve their acceptance of of patients efficiently. For instance, smart wearables that monitor
IoT-based smart healthcare through cognitive and emotional vital signs can transmit real-time data to nursing stations, enabling
pathways (139). staff to prioritize care and intervene promptly when necessary
However, there is also a need to address ethical dilemmas (144). Additionally, the use of telehealth platforms facilitated by
associated with the implementation of IoT technologies in IoT can extend the reach of healthcare providers, offering virtual
healthcare settings. One such dilemma is the potential deskilling consultations and reducing the physical demands on the nursing
of medical practitioners due to reliance on automated systems. workforce (26).
While these systems aim to enhance diagnostic accuracy and IoT has the potential to revolutionize patient monitoring in
patient monitoring, they could inadvertently reduce the clinical rural areas, where access to healthcare services is often limited.
skills of healthcare workers if over-reliance occurs (140). Another By deploying IoT-enabled sensors and devices, remote health
ethical issue pertains to data ownership and privacy concerns. With monitoring becomes feasible, allowing patients in rural settings to
vast amounts of sensitive health data being collected, ensuring receive continuous care without the need for frequent travel to
secure storage and transparent data sharing practices becomes urban medical centers. This is particularly beneficial for patients
paramount (141). with chronic conditions who require regular health check-ups and
To mitigate these challenges, robust training programs and medication management (145). Furthermore, IoT can facilitate
regulatory frameworks are essential. Training initiatives should the collection of health data from dispersed locations, providing
focus not only on technical proficiency but also on ethical healthcare providers with a comprehensive view of community
considerations, helping both patients and healthcare providers health trends and enabling more informed care decisions (113).
understand the benefits and limitations of IoT applications (142, Thus, while initial IoT investments may be high, the long-
143). Regulatory bodies must establish guidelines that protect term financial viability and operational improvements make IoT

Frontiers in Medicine 11 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

solutions indispensable for modern healthcare providers seeking The development trend of IoT applications and technologies
sustainable growth and enhanced patient care. in the healthcare field is rapidly evolving with the integration
of advanced technologies such as artificial intelligence (AI), 5G
networks, and blockchain. Ge et al. (160) discuss the potential of 5G
networks in supporting mission-critical IoT services, particularly
5 Discussion and future direction through the implementation of the tactile Internet (TI). This
advancement in wireless communication networks enables real-
5.1 Technological trends time control communications for IoT applications. Additionally,
Wijethilaka et al. (161) highlight the importance of network
The application of Internet of Things (IoT) technology in slicing in realizing IoT applications within 5G networks, thereby
healthcare is rapidly advancing, with innovations primarily focused addressing technical challenges through this innovative technology.
on novel sensors, device technologies, and the integration of Artificial intelligence (AI) plays a pivotal role in the healthcare
artificial intelligence (AI). sector. Vaishya et al. (162) and Almaiah et al. (163) underscore
Wearable and implantable sensors enable real-time monitoring the transformative impact of AI applications, which have been
of patients’ physiological data (146, 147), while smart medical instrumental in addressing challenges such as the COVID-19
devices such as surgical robots and telemedicine equipment pandemic and enhancing security and privacy in digital healthcare
enhance the precision and efficiency of medical procedures (148, using IoT platforms. Furthermore, Taimoor et al. (164) emphasize
149). Supported by 5G technology, the transmission speed and the significance of AI in facilitating personalized healthcare
stability of telemedicine devices have improved significantly, services, illustrating the potential of AI within the modern
enabling physicians to provide more convenient diagnostic and healthcare Internet of Things (HIoT).
treatment services (150). Blockchain technology also plays a vital role in the healthcare
Large models and AI play a critical role in medical data sector. Almaiah et al. (163) and Panagiotidis (165) discuss
analysis, personalized medicine, and intelligent diagnostic systems the integration of blockchain in healthcare applications, which
(151, 152). AI can process large volumes of medical data, ensures data security, privacy, and authentication. Specifically,
identify patterns of diseases, predict disease progression, and Panagiotidis (165) examines the educational applications of
offer personalized treatment plans (153, 154). Furthermore, the blockchain, highlighting its features, advantages, and potential
integration of IoT platforms allows for unified management of challenges within the educational sector.
data from various devices and sensors, further enhancing the Overall, the development trend of IoT applications and
operational efficiency and service quality of healthcare institutions technologies in the healthcare field is driven by the convergence
(155). In the future, the application of IoT in healthcare will evolve of AI, 5G, and blockchain technologies. These advancements are
toward greater intelligence, precision, and personalization, driven transforming the healthcare industry by enabling personalized
by the convergence of novel sensors, advanced device technologies, healthcare services, enhancing data security and privacy, and
and AI, to comprehensively elevate the level and efficiency of supporting real-time control communications for mission-critical
medical services. IoT services. The utilization of these advanced technologies is
essential for the paradigm shift toward a distributed, patient-centric
approach in healthcare, as emphasized by Abir et al. (166).
The integration of Internet of Things (IoT) technology into
5.2 Policy recommendations and nursing practice is gaining increasing significance within the
collaborative models healthcare sector. As elucidated by Al-Rawashdeh et al. (167),
key drivers for the adoption of IoT applications in nursing
The application of IoT technology in healthcare has become care encompass delivering deep insights and strategic guidance
a global focal point, making international cooperation and to leaders and system developers in the healthcare industry.
resource sharing particularly important. Through cross-border This highlights the imperative for collaboration between nursing
collaboration, countries can share medical technologies, devices, professionals and IoT technology developers to ensure the seamless
and data, leveraging each other’s strengths. For example, the and effective implementation of these technologies.
United States and the European Union have a lead in medical To catalyze this collaboration, healthcare organizations should
device and sensor technologies (156), while Asian countries offer nurses training in artificial intelligence (AI) and opportunities
excel in big data analytics and AI applications (157). Cross- for professional development, as advocated by Yelne et al.
border cooperation facilitates the development of advanced IoT (168). Such initiatives are vital for maintaining the currency of
healthcare solutions and promotes the standardization of global nurses’ knowledge and skills, thereby enhancing their capability
medical data, enhancing interoperability and availability of medical to collaborate effectively with IoT technology developers. Deep
information (17). Additionally, resource sharing optimizes global collaboration between nursing professionals and IoT technology
allocation of healthcare resources, allowing remote regions to developers is essential for the proficient adoption and utilization
consult with experts in major cities through telemedicine platforms, of IoT applications in nursing care. By fostering a collaborative
reducing misdiagnosis and treatment costs (158). This was environment, nurses and developers can ensure that technology is
particularly evident during the COVID-19 pandemic in 2019, when integrated in a manner that not only optimizes patient care but also
governments and health experts implemented various preventive enhances the overall quality of healthcare outcomes.
measures and collaborated on resource sharing to curb the spread In the field of IoT healthcare, regulatory frameworks and
of the virus (159). standardization policies are crucial for ensuring data security,

Frontiers in Medicine 12 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

privacy, and interoperability. Various policy issues influence the addressed the application of IoT technologies in healthcare,
integration of big data technologies in healthcare, including data technical challenges, international cooperation, and policy
sharing, security, standards, stakeholder engagement, and legal recommendations. Exclusion criteria explicitly ruled out non-
considerations (169). The European legal framework includes the peer-reviewed conference abstracts, review articles, editorials, news
General Data Protection Regulation (GDPR) and the Medical reports, blog posts, and other documents that were either off-topic
Device Regulation (MDR), addressing data breaches and security or did not contribute substantively to the research subject.
measures applicable to IoT medical devices (170). Rathee et al. During the screening process, two independent researchers first
(171) emphasize the importance of IoMT device standardization reviewed the titles and abstracts of all search results to identify
for increasing trust and transparency, while Rathee et al. (171) potentially eligible studies. Following this, a thorough full-text
discuss the significance of blockchain technology in securing examination was conducted to further verify compliance with the
medical multimedia data. Sadhu et al. (172) highlight the need final inclusion criteria. Throughout the process, any discrepancies
for standardized regulations and security systems in IoMT due were resolved through discussion, ensuring consistency and
to the risk of exploitation by hackers. Ghosh et al. (173) propose fairness in the selection of literature.
a framework for continuous delivery of IoT services to address From the finally included studies, key information including
latency issues, ensuring service delivery even in areas with poor the first author, publication year, study design, main findings,
internet coverage. These insights collectively underscore the critical and conclusions were extracted. A narrative synthesis approach
role of regulations, frameworks, and standards in shaping the future was utilized to systematically summarize the research findings
of IoT healthcare. and discuss their significance in the context of current IoT
The collaboration between the European Union (EU) and the applications in healthcare.
United States in the realm of medical device safety standards
exemplifies the significant outcomes achieved through concerted
efforts to promote consistency between the Medical Device
Regulation (MDR) and the US Food and Drug Administration
Author contributions
(FDA). This cooperation has not only simplified compliance
BW: Writing – review and editing, Writing – original
requirements for businesses but also enhanced global medical
device safety standards (174). draft, Methodology. XS: Writing – original draft. XH: Project
In the Asia-Pacific region, the cooperation among APEC administration, review and editing. GX: Supervision, Writing –
member economies, particularly through its Privacy Framework, review and editing.
provides guidelines for cross-border data transfers. This is
especially important for IoT healthcare services that rely on real-
time data exchange (175). Funding
Initiatives such as the Global Health Data Exchange Initiative
aim to establish a global network for sharing health data, fostering The authors declare that financial support was received
knowledge exchange and technical collaboration among countries for the research, authorship, and/or publication of this article.
in health data management. This collaborative effort contributes to This research was funded by the National Key Research and
the development of unified data protection standards and promotes Development Program of China (No. 2022YFC2009606) and the
interoperability in health information systems (176). Medical Scientific Research Foundation of Guangdong Province of
China (grant number A2023159).

6 Materials and methods

Conflict of interest
To enhance the scientific rigor and credibility of our
review paper, we have meticulously detailed the systematic
The authors declare that the research was conducted in the
processes employed for literature retrieval and screening in the
absence of any commercial or financial relationships that could be
methodology section. Initially, we formulated an exhaustive search
construed as a potential conflict of interest.
strategy targeting major databases such as PubMed, Web of
Science, Scopus, and Google Scholar. Keyword combinations
included terms like “Internet of Things,” “smart nursing,”
“technical challenges,” “international cooperation,” and “policy Publisher’s note
recommendations,” ensuring the breadth and specificity of the
search results. The time span for literature retrieval was set from All claims expressed in this article are solely those of the
2015 to 2024, aiming to capture the latest developments in the authors and do not necessarily represent those of their affiliated
application of IoT technologies in healthcare over the past decade. organizations, or those of the publisher, the editors and the
Subsequently, we established rigorous inclusion and exclusion reviewers. Any product that may be evaluated in this article, or
criteria. Inclusion criteria were strictly defined as English- claim that may be made by its manufacturer, is not guaranteed or
language articles published in peer-reviewed journals that directly endorsed by the publisher.

Frontiers in Medicine 13 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

References
1. Miyashita J, Shimizu S, Shiraishi R, Mori M, Okawa K, Aita K, et al. Culturally 24. Nguyen P, Soenksen L, Donghia N, Angenent-Mari N, de Puig H, Huang A,
adapted consensus definition and action guideline: Japan’s advance care planning. J et al. Wearable materials with embedded synthetic biology sensors for biomolecule
Pain Symptom Manage. (2022) 64:602–13. doi: 10.1016/j.jpainsymman.2022.09.005 detection. Nat Biotechnol. (2021) 39:1366–74. doi: 10.1038/s41587-021-00950-3
2. Zou Z, Cini K, Dong B, Ma Y, Ma J, Burgner D, et al. Time trends in cardiovascular 25. Yasin A, Delaney J, Cheng C, Pang T. The design and implementation of an IoT
disease mortality across the BRICS: an age-period-cohort analysis of key nations with sensor-based indoor air quality monitoring system using off-the-shelf devices. Appl Sci.
emerging economies using the Global Burden of Disease Study 2017. Circulation. (2022) 12:9450. doi: 10.3390/app12199450
(2020) 141:790–9. doi: 10.1161/CIRCULATIONAHA.119.042864
26. Rajagopal S., Lyngdoh DC Songra R, Vasan N. IoT-enabled solutions
3. Xie M, Liu X, Cao X, Guo M, Li X. Trends in prevalence and incidence of chronic for environmental monitoring in hospitals. Open Biomed Eng. J. (2023)
respiratory diseases from 1990 to 2017. Respir Res. (2020) 21:49. doi: 10.1186/s12931- 17:e187412072301020. doi: 10.2174/18741207-v17-e230110-2022-HT28-4371-4
020-1291-8
27. Abubeker K, Baskar S. Wireless sensor and wireless body area network assisted
4. World Health Organization. Global Health Workforce Statistics Database. biosensor network for effective monitoring and prevention of non-ventilator hospital-
(n.d.). Available online at: https://www.who.int/data/gho/data/themes/topics/health- acquired pneumonia. Front Sustain Cities. (2022) 4:1063067. doi: 10.3389/frsc.2022.
workforce (accessed July 13, 2024). 1063067
5. Blumenthal D. Wiring the health system–origins and provisions of a new federal 28. Wilson N, Calabria C, Warren A, Finlay A, O’Donovan A, Passerello G, et al.
program. N Engl J Med. (2011) 365:2323–9. doi: 10.1056/NEJMsr1110507 Quantifying hospital environmental ventilation using carbon dioxide monitoring - a
Multicentre study. Anaesthesia. (2024) 79:147–55. doi: 10.1111/anae.16124
6. Liu J, Liu S, Zheng T, Fang J. Development of nursing informatics in Mainland
China: a Bibliometric analysis. Stud Health Technol Inform. (2021) 284:56–8. doi: 29. Alabere I, Luckyn BJ, Anyanwu FC. Implementation of HCSR04 ultrasonic
10.3233/SHTI210664 sensor based internet of things hospital drip bag monitoring and alert system. J Innov
Data Sci Big Data Manage. (2024) 3:36–50.
7. Exley J, Glover R, Mccarey M, Reed S, Ahmed A, Vrijhoef H, et al. Governing
integrated health and social care: an analysis of experiences in three European 30. Liu X, Hu J, Zhang H, Di B, Bian K, Song L. Meta-material sensor-based internet
countries. Int J Integr Care. (2024) 24:9. doi: 10.5334/ijic.7610 of things for environmental monitoring by deep learning: design, deployment, and
implementation. Trans Wireless Comm. (2023) 22:2462–76. doi: 10.1109/TWC.2022.
8. Umer M, Aljrees T, Karamti H, Ishaq A, Alsubai S, Omar M, et al. Heart
3211610
failure patients monitoring using IoT-based remote monitoring system. Sci Rep. (2023)
13:19213. doi: 10.1038/s41598-023-46322-6 31. Alasmary H. Scalable Digital Health (SDH): an IoT-based scalable framework for
remote patient monitoring. Sensors. (2024) 24:1346. doi: 10.3390/s24041346
9. Alshammari H. The internet of things healthcare monitoring system based on
MQTT protocol. Alexandria Eng J. (2023) 69:275–87. doi: 10.1016/j.aej.2023.01.065 32. Raparla K, Pandey N, Modh S. Indigenous and disruptive remote patient
monitoring devices - a Case Study on AI in healthcare. SDMIMD J Manag. (2023)
10. Astell A, Dosanjh S, D’Elia T, Kokorelias K, Stewart S, Grigorovich A, et al.
14:27–34. doi: 10.18311/sdmimd/2023/32513
Personalized tablets for residents in long-term care to support recreation and mitigate
isolation. J Am Med Dir Assoc. (2024) 25:105022. doi: 10.1016/j.jamda.2024.105022 33. Ren S, McDonald C, Corwin D, Wiebe D, Master C, Arbogast K. Response
rate patterns in adolescents with concussion using mobile health and remote patient
11. Ni Ki C, Hosseinian-Far A, Daneshkhah A, Salari N. Topic modelling in
monitoring: observational study. JMIR Pediatr Parent. (2024) 7:e53186. doi: 10.2196/
precision medicine with its applications in personalized diabetes management. Exp.
53186
Syst. (2022) 39:e12774. doi: 10.1111/exsy.12774
34. Kedwan F. Remote patient monitoring system implementation. J Clin Case Stud
12. Bzai J, Alam F, Dhafer A, Bojoviæ M, Altowaijri S, Niazi I, et al. Machine
Rev Rep. (2022):1–4. doi: 10.47363/JCCSR/2022(4)232
learning-enabled Internet of Things (IoT): data, applications, and industry perspective.
Electronics. (2022) 11:2676. doi: 10.3390/electronics11172676 35. Vaghasiya J, Mayorga-Martinez C, Pumera M. Telemedicine platform for health
assessment remotely by an integrated nanoarchitectonics FePS3/rGO and Ti3C2-based
13. HealthIT.Gov,. Medical practice efficiencies and cost savings. (n.d.). Available
wearable device. NPJ Flex Electron. (2022) 6:73. doi: 10.1038/s41528-022-00208-1
online at: https://www.healthit.gov/topic/health-it-and-health-information-
exchange-basics/medical-practice-efficiencies-cost-savings (accessed November 36. Srinivasu P, Ijaz M, Shafi J, Woźniak M, Sujatha R. 6G Driven fast computational
20, 2024). networking framework for healthcare applications. IEEE Access. (2022) 10:94235–48.
doi: 10.1109/ACCESS.2022.3203061
14. Kulshreshtha A, Kvedar J, Goyal A, Halpern E, Watson A. Use of remote
monitoring to improve outcomes in patients with heart failure: a pilot trial. Int J 37. Donghua J, Zeric N, Nkapkop J, Nestor T, Wang X, Awrejcewicz J. A new
Telemed Appl. (2010) 2010:870959. doi: 10.1155/2010/870959 cross ring neural network: dynamic investigations and application to WBAN. IEEE
Int Things J. (2023) 10:7143–52. doi: 10.1109/JIOT.2022.3228748
15. Mullins A, O’Donnell R, Mousa M, Rankin D, Ben-Meir M, Boyd-Skinner C,
et al. Health outcomes and healthcare efficiencies associated with the use of electronic 38. Sodhro A, Malokani A, Sodhro G, Muzammal M, Zongwei L. RETRACTED
health records in hospital emergency departments: a systematic review. J Med Syst. ARTICLE: an adaptive QoS computation for medical data processing in intelligent
(2020) 44:200. doi: 10.1007/s10916-020-01660-0 healthcare applications. Neural Comput Appl. (2020) 32:723–34. doi: 10.1007/s00521-
018-3931-1
16. Paul L, Ahmed S, Rani T, Haque M, Roy T, Hossain M, et al. A smart medicine
reminder kit with mobile phone calls and some health monitoring features for senior 39. Rehman A, Haseeb K, Fati S, Lloret J, Peñalver L. Reliable bidirectional data
citizens. Heliyon. (2024) 10:e26308. doi: 10.1016/j.heliyon.2024.e26308 transfer approach for the internet of secured medical things using ZigBee wireless
network. Appl Sci. (2021) 11:9947. doi: 10.3390/app11219947
17. El-Saleh A, Manan Sheikh A, Albreem M, Honnurvali M. The Internet of
Medical Things (IoMT): opportunities and challenges. Wireless Netw. (2024) 1–18. 40. Rehman U, Park S, Lee S. Secure health fog: a novel framework for personalized
doi: 10.1007/s11276-024-03764-8 recommendations based on adaptive model tuning. IEEE Access. (2021) 9:108373–91.
doi: 10.1109/ACCESS.2021.3101308
18. Huang C, Wang J, Wang S, Zhang Y. Internet of medical things: a systematic
review. Neurocomputing. (2023) 557:126719. doi: 10.1016/j.neucom.2023.126719 41. Padma B, Babu E. Efficient secure communication in Zigbee network using the
DNA sequence encryption technique. Life. (2023) 13:1147. doi: 10.3390/life13051147
19. Pan Y, Fu M, Cheng B, Tao X, Guo J. Enhanced deep learning assisted
convolutional neural network for heart disease prediction on the internet of medical 42. Yu C, Ku M, Wang L. Joint topology construction and hybrid routing strategy on
things platform. IEEE Access. (2020) 8:189503–12. doi: 10.1109/ACCESS.2020.302 load balancing for Bluetooth low energy networks. IEEE Int Things J. (2021) 8:7101–2.
6214 doi: 10.1109/JIOT.2021.3051561
20. Parvathy V, Pothiraj S, Sampson J. Automated Internet of Medical Things 43. Wang W, He D, Jia W, Chen X, Gu T, Liu H, et al. PRComm: Anti-interference
(IoMT) based healthcare monitoring system. In: Hassanien AE, Khamparia A, Gupta cross-technology communication based on pseudo-random sequence. In: Proceedings
D Shankar K, Slowik A, editors. Cognitive Internet of Medical Things for Smart of the 20th International Conference on Information Processing in Sensor Networks.
Healthcare: Services and Applications. Cham: Springer. (2021). p. 117–28. New York, NY: ACM. (2021). p. 163–75.
21. Li S, Li H, Lu Y, Zhou M, Jiang S, Du X, et al. Advanced textile-based 44. Sriram S. Determination of maximum allowable data transfer rate by Bluetooth
wearable biosensors for healthcare monitoring. Biosensors. (2023) 13:909. doi: 10.3390/ LET energy method in WSN. In: Proceedings of the 2023 World Conference on
bios13100909 Communication & Computing (WCONF). 1–6. Raipur: IEEE (2023).
22. Wang Q, Sun X, Liu C, Wang C, Zhao W, Zhu Z, et al. Current development 45. Kozhubaev Y, Ovchinnikova E, Krotova S, Ivanov V, Ruide Y. Energy efficient
of stretchable self-powered technology based on nanomaterials toward wearable indoor wireless communication techniques based on BLE technology. E3S Web of
biosensors in biomedical applications. Front Bioeng Biotechnol. (2023) 11:1164805. Conf. (2023) 389:7011. doi: 10.1051/e3sconf/202338907011
doi: 10.3389/fbioe.2023.1164805
46. Verma P, Fatima S. Smart healthcare applications and real-time analytics through
23. Tricase A, Imbriano A, Valentino M, Ditaranto N, Macchia M, Franco C, et al. edge computing. In: Raj P, Moy J, Abhishek C, editors. Internet of Things Use Cases for
Water-based conductive ink formulations for enzyme-based wearable biosensors. Adv the Healthcare Industry. Cham: Springer International Publishing (2020). p. 241–70.
Sensor Res. (2024) 3:2300036. doi: 10.1002/adsr.202300036 doi: 10.1007/978-3-030-37526-3_11

Frontiers in Medicine 14 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

47. Ghadi Y, Shah A, Mazhar T, Shahzad T, Ouahada K, Hamam H. Enhancing 72. Wen M, Bai D, Lin S, Chu C, Hsu Y. Implementation and experience of an
patient healthcare with mobile edge computing and 5G: challenges and solutions for innovative smart patient care system: a cross-sectional study. BMC Health Serv Res.
secure online health tools. J Cloud Comput. (2024) 13:93. doi: 10.1186/s13677-024- (2022) 22:126. doi: 10.1186/s12913-022-07511-7
00654-4
73. Boo S, Oh H. Perceptions of registered nurses on facilitators and barriers of
48. Hemmati A, Raoufi P, Rahmani A. Edge artificial intelligence for big data: a implementing the AI-IoT-based healthcare pilot project for older adults during the
systematic review. Neural Comput Appl. (2024) 36:11461–94. doi: 10.1007/s00521-024- COVID-19 pandemic in South Korea. Front Public Health. (2023) 11:1234626. doi:
09723-w 10.3389/fpubh.2023.1234626
49. Urblik L, Kajati E, Papcun P, Zolotova I. A modular framework for data 74. Sundas A, Badotra S, Singh G. Sensor data transforming into real-time healthcare
processing at the edge: design and implementation. Sensors. (2023) 23:7662. doi: 10. evaluation: a review of internet of things healthcare monitoring applications. In
3390/s23177662 Proceedings of the 2023 International Conference on Intelligent and Innovative
Technologies in Computing, Electrical and Electronics (IITCEE), 559–67. Bengaluru:
50. Lakhani Z. The role of cloud integration in healthcare sector: a comprehensive
IEEE. (2023).
review. Int J Res Appl Sci Eng Technol. (2024) 12:4280–5. doi: 10.22214/ijraset.2024.
60919 75. Liang J, Tu J, Leung V. Mobile sensor deployment optimization algorithm for
maximizing monitoring capacity of large-scale acyclic directed pipeline networks in
51. Himanshu Y, Punhani A. A perspective to cloud computing in healthcare sector.
smart cities. IEEE Internet things J. (2020) 8:16083–95.
In: Proceedings of the 2024 2nd International Conference on Disruptive Technologies
(ICDT). Greater Noida: IEEE (2024). p. 811–7. 76. Jiang J, Wang J, Wu H, Lee C, Chou C, Wu C, et al. A novel sensor placement
strategy for an IoT-based power grid monitoring system. IEEE Int. Things J. (2020)
52. Dhote S, Baskar S, Mohamed Shakeel P, Dhote T. Cloud Computing Assisted
7:7773–82. doi: 10.1109/JIOT.2020.2991610
Mobile Healthcare Systems using Distributed Data Analytic Model. Piscataway, NJ:
IEEE (2023). 77. Wang W, Zhu Q, Gao H. Drift detection of intelligent sensor networks
deployment based on graph stream. IEEE Trans Netw Sci Eng. (2023) 10:1096–106.
53. Praveen S, Thati B, Anuradha C, Sindhura S, Altaee M, Jalil M. A novel approach
doi: 10.1109/TNSE.2022.3227909
for enhance fusion based healthcare system in cloud computing. J Intell Syst Int Things.
(2023) 12:88–100. doi: 10.54216/JISIoT.090106 78. Rosa S, Kadir E, Abbasi Q, Almansour A, Othman A, Siswanto A. Patient
monitoring and disease analysis based on IoT wearable sensors and cloud computing.
54. Zhang H, Zhao Y, Pang C, He J. Splitting large medical data sets based on normal
In Proceedings of the 2022 International Conference on Electrical, Computer,
distribution in cloud environment. IEEE Trans Cloud Comput. (2020) 8:518–31. doi:
Communications and Mechatronics Engineering (ICECCME). Maldives: IEEE (2022).
10.1109/TCC.2015.2462361
79. Balakrishnan R, Ranganayaki V. Sensor based health monitoring system using
55. Prajapati J, Prajapati B. Clinical decision support system braced with artificial
embedded technology. In Proceedings of the 2022 8th International Conference on
intelligence: a review. In: Chen J, João Manuel R, Tavares S, editors. Third International
Advanced Computing and Communication Systems (ICACCS). Coimbatore: IEEE
Conference on Image Processing and Capsule Networks. Cham: Springer (2022). p. 531–
(2022). p. 1263–7.
40. doi: 10.1007/978-3-031-12413-6_42
80. Liu Z, Cascioli V, McCarthy P. Healthcare monitoring using low-cost sensors
56. Ferdush J, Begum M, Hossain S. ChatGPT and clinical decision support: scope,
to supplement and replace human sensation: does it have potential to increase
application, and limitations. Ann Biomed Eng. (2024) 52:1119–24. doi: 10.1007/
independent living and prevent disease? Sensors. (2023) 23:2139. doi: 10.3390/
s10439-023-03329-4
s23042139
57. Demuth S, Müller J, Quenardelle V, Lauer V, Gheoca R, Trzeciak M, et al.
81. Harb H, Mansour A, Nasser A, Cruz C, Torre Díez I. A sensor-based data
Strokecopilot: a literature-based clinical decision support system for acute ischemic
analytics for patient monitoring in connected healthcare applications. IEEE Sensors
stroke treatment. J Neurol. (2023) 270:6113–23. doi: 10.1007/s00415-023-11979-6
J. (2021) 21:974–84. doi: 10.1109/JSEN.2020.2977352
58. Eisenstein M. AI assistance for planning cancer treatment. Nature. (2024)
82. Shafi I, Din S, Farooq S, Díez I, Breñosa J, Espinosa J, et al. Design and
629:S14–6. doi: 10.1038/d41586-024-01431-8
development of patient health tracking, monitoring and big data storage using Internet
59. Savage N.. AI’s keen diagnostic eye. Nature. (2024) doi: 10.1038/d41586-024- of Things and real time cloud computing. PLoS One. (2024) 19:e0298582. doi: 10.1371/
01132-2 Online ahead of print journal.pone.0298582
60. Mittermaier M, Raza M, Kvedar J. Collaborative strategies for deploying AI- 83. Pandey S, Singh K, Dingankar R, Jadhav K, Gupta K, Yadav R. Prediction of
based physician decision support systems: challenges and deployment approaches. NPJ tuberculosis disease progression with AI analysis of clinical data. In: Proceedings of the
Digit Med. (2023) 6:137. doi: 10.1038/s41746-023-00889-6 2023 International Conference on Artificial Intelligence for Innovations in Healthcare
Industries (ICAIIHI). Raipur: IEEE (2023). p. 1–6.
61. Luchini C, Pea A, Scarpa A. Artificial intelligence in oncology: current
applications and future perspectives. Br J Cancer. (2022) 126:4–9. doi: 10.1038/s41416- 84. Grampurohit S, Sagarnal C. Disease prediction using machine learning
021-01633-1 algorithms. In: Proceedings of the 2020 International Conference for Emerging
Technology (INCET). Belgaum: IEEE (2020).
62. Lenharo M. An AI revolution is brewing in medicine. What will it look like?
Nature. (2023) 622:686–8. doi: 10.1038/d41586-023-03302-0 85. Cho S, Kim S, Kang S, Lee K, Choi D, Kang S, et al. Pre-existing and machine
learning-based models for cardiovascular risk prediction. Sci Rep. (2021) 11:8886.
63. Kiania K, Jameii S, Rahmani A. Blockchain-based privacy and security
doi: 10.1038/s41598-021-88257-w
preserving in electronic health: a systematic review. Multimed Tools Appl. (2023).
doi: 10.1007/s11042-023-14488-w Online ahead of print. 86. Glass C, Davis R, Xiong B, Dov D, Glass M. The use of Artificial Intelligence
(AI) machine learning to determine myocyte damage in cardiac transplant acute
64. Wu H, Dwivedi A, Srivastava G. Security and privacy of patient information
cellular rejection. J Heart Lung Transpl. (2020) 39:S59. doi: 10.1016/j.healun.2020.01.
in medical systems based on blockchain technology. ACM Trans Multimedia Comput
1250
Commun Appl. (2021) 17:1–17. doi: 10.1145/3408321
87. Yu, H. Analysis and prediction of heart disease based on machine learning
65. Zarour M, Ansari M, Alenezi M, Sarkar A, Faizan M, Agrawal A. Evaluating the
algorithms. In Proceedings of the 2023 8th International Conference on Intelligent
impact of blockchain models for secure and trustworthy electronic healthcare records.
Computing and Signal Processing (ICSP). IEEE (2023). Xi’an, p. 1418–23.
IEEE Access. (2020) 8:157959–73. doi: 10.1109/ACCESS.2020.3019829
88. Tarumi S, Takeuchi W, Chalkidis G, Rodriguez-Loya S, Kuwata J, Flynn
66. Zhang C, Xu C, Sharif K, Zhu L. Privacy-preserving contact tracing in 5G-
M, et al. Leveraging artificial intelligence to improve chronic disease care:
integrated and blockchain-based medical applications. Comput Stand Interfaces.
methods and application to pharmacotherapy decision support for type-2 diabetes
(2021) 77:103520. doi: 10.1016/j.csi.2021.103520
mellitus. Methods Inf Med. (2021) 60(S 01):e32–43. doi: 10.1055/s-0041-172
67. Zhang D, Wang S, Zhang Y, Zhang Q, Zhang Y. A secure and privacy-preserving 8757
medical data sharing via consortium blockchain. Security Commun Netw. (2022)
89. Isiaka A, Anakwenze V, Ilodinso C, Anaukwu C, Mary-
2022:1–15. doi: 10.1155/2022/2759787
Vin Ezeokoli C, Noi S. Harnessing artificial intelligence for early
68. Alsayegh M, Moulahi T, Alabdulatif A, Lorenz P. Towards secure searchable detection and management of infectious disease outbreaks. Int J
electronic health records using consortium blockchain. Network. (2022) 2:239–56. Innov Res Dev. (2024) 13:52–65. doi: 10.24940/ijird/2024/v13/i2/
doi: 10.3390/network2020016 FEB2406
69. Ayele E, Gavriel S, Gonzalez J, Teeuw W, Philimis P, Gillani G. Emerging 90. Farrag A, Kamel A, El-Baraky I. Opportunities and challenges for the application
industrial internet of things open-source platforms and applications in diverse sectors. of artificial intelligence paradigms into the management of endemic viral infections:
Telecom. (2024) 5:369–99. doi: 10.3390/telecom5020019 the example of chronic hepatitis C virus. Rev Med Virol. (2024) 34:e2514. doi: 10.1002/
rmv.2514
70. Rubio J, Prieto S. Implementation of a cross-platform development board for
embedded internet-of-things systems. J Telecommun Digital Econ. (2024) 12:463–85. 91. Zhuhadar, L, Lytras M. The application of AutoML techniques in diabetes
doi: 10.3316/informit.T2024040300010991472617594 diagnosis: current approaches, performance, and future directions. Sustainability.
(2023) 15:13484. doi: 10.3390/su151813484
71. Zhou F, Wan X, Du X, Lu Z, Wu J. Design and implementation of an intelligent
health management system for nursing homes. In Proceedings of the 2022 IEEE 92. Kargbo R. Advancements in predictive medicine: NLRP3 inflammasome
7th International Conference on Smart Cloud (SmartCloud). Shanghai: IEEE (2022). inhibitors and AI-driven predictive health analytics. ACS Med Chem Lett. (2024)
p. 145–50. 15:331–3. doi: 10.1021/acsmedchemlett.4c00056

Frontiers in Medicine 15 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

93. Alshamrani M. IoT and artificial intelligence implementations for remote 117. D’Agostino F, Almeida M, Nomura A, Tayaben J. Nursing informatics within
healthcare monitoring systems: a survey. J King Saud Univer Comput Inf Sci. (2022) health systems: global comparison. Milton Park: Taylor and Francis (2022).
34:4687–701. doi: 10.1016/j.jksuci.2021.06.005
118. van Niekerk L, Mathanga D, Juban N, Castro-Arroyave D, Balabanova D.
94. Wang C, He T, Zhou H, Zhang Z, Lee C. Artificial intelligence enhanced sensors Universities as catalysts of social innovation in health systems in low-and middle-
- enabling technologies to next-generation healthcare and biomedical platform. income countries: a multi-country case study. Infect Dis Poverty. (2020) 9:90. doi:
Bioelectron Med. (2023) 9:17. doi: 10.1186/s42234-023-00118-1 10.1186/s40249-020-00684-5
95. Martinez-Ortigosa A, Martinez-Granados A, Gil-Hernández E, Rodriguez- 119. Allel K, Tapia-Muñoz T, Morris W. Country-level factors associated with the
Arrastia M, Ropero-Padilla C, Roman P. Applications of Artificial intelligence in early spread of COVID-19 cases at 5, 10 and 15 days since the onset. Glob Public Health.
nursing care: a systematic review. J Nurs Manag. (2023):3219127. doi: 10.1155/2023/ (2020) 15:1589–602. doi: 10.1080/17441692.2020.1814835
3219127
120. von Grünigen S, Geissbühler A, Bonnabry P. The safe handling of
96. Ni Y, Jacob F, Achuthan P, Wu H, Javed F. Leveraging automated search relevance chemotherapy drugs in low- and middle-income countries: an overview of practices. J
evaluation to improve system deployment: a case study in healthcare. In: Proceedings Oncol Pharm Pract. (2021) 28:410–20.
of the 31st ACM International Conference on Information & Knowledge Management,
121. Mansour W, Boyd A, Walshe K. National accreditation programmes for
Atlanta, GA: ACM (2022).
hospitals in the Eastern Mediterranean region: case studies from Egypt, Jordan,
97. Jahanshahi H, Kazmi S, Cevik M. Auto response generation in online medical and Lebanon. Int J Health Plann Manag. (2021) 36:1500–20. doi: 10.1002/hpm.
chat services. J Healthc Inform Res. (2022) 6:344–74. doi: 10.1007/s41666-022-00118-x 3178
98. Bagattini Â, Borges J, Riera R, de Carvalho D. Automation of a tertiary hospital 122. Dkhimi F, Honda A, Hanson K, Mbau R, Onwujekwe O, Phuong T, et al.
pharmacy drug dispensing system in a lower-middle-income country: a case study and Examining multiple funding flows to public healthcare providers in low- and middle-
preliminary results. Explor Res Clin Soc Pharm. (2022) 6:100151. doi: 10.1016/j.rcsop. income countries - results from case studies in Burkina Faso, Kenya, Morocco, Nigeria,
2022.100151 Tunisia And Vietnam. Health Policy Plan. (2022) 38:1139–53. doi: 10.1093/heapol/
czad072
99. Odera D. A survey on techniques, methods and security approaches in big data
healthcare. Glob J Eng. (2023) 14:093–106. doi: 10.30574/gjeta.2023.14.2.0035 123. Abdulrazak B, Mostafa Ahmed H, Aloulou H, Mokhtari M, Blanchet F. IoT
in medical diagnosis: detecting excretory functional disorders for older adults via
100. Madavarapu J, Yalamanchili R, Mandhala V. An ensemble data security on
bathroom activity change using unobtrusive IoT technology. Front Public Health.
cloud healthcare systems. In: Proceedings of the 2023 4th International Conference on
(2023) 11:1161943. doi: 10.3389/fpubh.2023.1161943
Smart Electronics assnd Communication (ICOSEC). Trichy: IEEE (2023). p. 680–6.
124. Yesmin T, Carter M, Gladman A. Internet of things in healthcare for patient
101. Basha B. Enhancing healthcare data security using quantum cryptography for
safety: an empirical study. BMC Health Serv Res. (2022) 22:278. doi: 10.1186/s12913-
efficient and robust encryption. J Electrical Syst. (2024) 20:1993–2000. doi: 10.52783/
022-07620-3
jes.2535
125. Abril-Jiménez P, Merino-Barbancho B, Fico G, Martín Guirado J, Vera-Muñoz
102. Khan M, Khan J, Sehito N, Mahmood K, Ali H, Bari I, et al. An adaptive
C, Mallo I, et al. Evaluating IoT-based services to support patient empowerment in
enhanced technique for locked target detection and data transmission over internet
digital home hospitalization services. Sensors. (2023) 23:1744. doi: 10.3390/s23031744
of healthcare things. Electronics. (2022) 11:2726. doi: 10.3390/electronics11172726
126. Mudawi N. Integration of IoT and fog computing in healthcare based the smart
103. Abdelaziz A, Alia M. Data security in healthcare systems: integration of
intensive units. IEEE Access. (2022) 10:59906–18. doi: 10.1109/ACCESS.2022.3179704
information security and information management. J Cybersecur Inf Manag. (2023)
11:17–26. doi: 10.54216/JCIM.110202 127. Yongjoh S, So-In C, Kompunt P, Muneesawang P, Morien R. Development of
an internet-of-healthcare system using blockchain. IEEE Access. (2021) 9:113017–31.
104. Naithani P. COMMENTARY: protecting healthcare privacy: analysis of data
doi: 10.1109/ACCESS.2021.3103443
protection developments in India. Indian J Med Ethics. (2023) 9:149–53. doi: 10.20529/
IJME.2023.078 128. Ni Z, Jin H, Jiang G, Wang N, Peng A, Guo Z, et al. A telemedicine-based
registration system for the management of renal anemia in patients on maintenance
105. Polubinskaya S. Big Data in Healthcare: Cybersecsurity and Legal Protection of
hemodialysis: multicenter study. J Med Internet Res. (2019) 21:e13168. doi: 10.2196/
Personal Data. Moscow: Russian Academy of Sciences (2023).
13168
106. McClelland R, Harper C. Information privacy in healthcare - The vital role
129. Wang Z, Liu S. Internet of things (IoT) imbedded point-of-care SARS-CoV-
of informed consent. Eur J Health Law. (2022) 30:469–80. doi: 10.1163/15718093-
2 testing in the pandemic and post-pandemic era. Biosaf Health. (2022) 4:365–8.
bja10097
doi: 10.1016/j.bsheal.2022.09.005
107. Scheibner J, Ienca M, Vayena E. Health data privacy through homomorphic
130. Shen J, Zhang J, He Q, Pan H, Wu Z, Nie L, et al. Without the need for a second
encryption and distributed ledger computing: an ethical-legal qualitative expert
visit&quot; initiative improves patient satisfaction with updated services of outpatient
assessment study. BMC Med Ethics. (2022) 23:121. doi: 10.1186/s12910-022-00852-2
clinics in China. BMC Health Serv Res. (2021) 21:267. doi: 10.1186/s12913-021-06260-
108. Vedder A, Spajiæ D. Moral autonomy of patients and legal barriers to a possible 3
duty of health related data sharing. Ethics Inf Technol. (2023) 25: 23. doi: 10.1007/
131. Qin A, Liu Y, Shao C, Dong H. Application of intelligent nursing based on
s10676-023-09697-8.
cloud computing of internet of things in children with pneumonia and sepsis treated
109. Beil-Hildebrand M, Smith H. Comparative analysis of advanced practice with human gamma globulin. Eur J Inflamm. (2023) 21:1721727X231194144. doi:
nursing: contextual and historical influences in North American and German- 10.1177/1721727X231194144
speaking European countries. Policy Polit Nurs Pract. (2022) 23:162–74. doi: 10.1177/
132. Hu M, Ling Y, Xiong F, Xu J. Construction of a three-level enteral nutrition
15271544221105032
nursing system under the &quot;Internet + medical&quot; mode and an evaluation of
110. Wang M, Tang J, Liu Y, Chuang C, Shih C. Innovative digital technology its effect in clinical application. Front Public Health. (2022) 10:976276. doi: 10.3389/
adapted in nursing education between Eastern and Western countries: a mini-review. fpubh.2022.976276
Front Public Health. (2023) 11:1167752. doi: 10.3389/fpubh.2023.1167752
133. Jawad MH, Bin Hussein Z, Zaidan BB, Mohamad Jawad FH, Mohamad Jawad
111. De Raeve P, Davidson P, Bergs J, Patch M, Jack S, Castro-Ayala A, et al. DH, Alredany WHD, et al. A systematic literature review of enabling IoT in healthcare:
Advanced practice nursing in Europe-Results from a pan-European survey of 35 motivations, challenges, and recommendations. Electronics. (2022) 11:3223. doi: 10.
countries. J Adv Nurs. (2024) 80:377–86. doi: 10.1111/jan.15775 3390/electronics11193223
112. Efn E. Advanced Practice Nursing (Apn). (2023).Available online at: https://efn. 134. Bernardi F, Alves D, Crepaldi N, Yamada D, Lima V, Rijo R. Data quality in
eu/?page_id=15936 (accessed July 18, 2024). health research: integrative literature review. J Med Internet Res. (2023) 25:e41446.
doi: 10.2196/41446
113. Zhang, W, Ming Y, Li G. Research on application of computer big data
and mobile communication technology in intelligent nursing service platform. In 135. Syed R, Eden R, Makasi T, Chukwudi I, Mamudu A, Kamalpousr M, et al.
Proceedings of the 2022 IEEE International Conference on Electrical Engineering, Big Digital health data quality issues: systematic review. J Med Internet Res. (2023)
Data and Algorithms (EEBDA). Piscataway, NJ: IEEE (2022). p. 1–5. doi: 10.1109/ 25:e42615. doi: 10.2196/42615
EEBDA53927.2022.9744729
136. Canali S, Schiaffonati V, Aliverti A. Challenges and recommendations for
114. Guo C, Li H. Application of 5G network combined with AI robots in wearable devices in digital health: data quality, interoperability, health equity, fairness.
personalized nursing in China: a literature review. Front Public Health. (2022) PLoS Digit Health. (2022) 1:e0000104. doi: 10.1371/journal.pdig.0000104
10:948303. doi: 10.3389/fpubh.2022.948303
137. Mukherjee S, Baral M, Chittipaka V, Srivastava S. Analysis of internet of things
115. Selvaganesan P, Russell A, Milo T, Mahajan A. A seamless healthcare platform acceptance dimensions in hospitals. In: Mahmood M, Raja R, Kaur H editors. Ambient
for total connectivity throughout the patients medical journey. Int J Biomed Eng Intelligence and Internet of Things. Hoboken NJ: John Wiley & Sons, Ltd (2022).
Technol. (2023) 41:186. doi: 10.1504/IJBET.2023.129196 p. 189–213. doi: 10.1002/9781119821847.ch6
116. Vannieuwenborg F, Van der Auwermeulen T, Van Ooteghem J, Jacobs A, 138. Madrigal C, Mogle J, Abbott K, Mills W, Fick D, Scanlon D, et al. The
Verbrugge S, Colle D. Evaluating the economic impact of smart care platforms: association between preference satisfaction and satisfaction with overall care for
qualitative and quantitative results of a case study. JMIR Med Inform. (2016) 4:e33. nursing home residents. J Aging Soc Policy. (2022) 34:707–22. doi: 10.1080/08959420.
doi: 10.2196/medinform.5012 2022.2029265

Frontiers in Medicine 16 frontiersin.org

Wang et al. 10.3389/fmed.2024.1471527

139. Huo W, Yuan X, Li X, Luo W, Xie J, Shi B. Increasing acceptance of medical 157. Schüller M. Artificial intelligence: new challenges and opportunities for Asian
AI: the role of medical staff participation in AI development. Int J Med Inform. (2023) countries. In: Wang L, Zhao J, editors. Exchanges and Mutual Learning among Asian
175:105073. doi: 10.1016/j.ijmedinf.2023.105073 Civilizations. Singapore: Springer Nature. (2023). p. 277–85. doi: 10.1007/978-981-19-
7165-5_42
140. Abdulkarim Adamu I, Umar M, Umaru J, Dokoro H. Utilizing ICT in
sustaining national development using digital economy and IOT. Int J Wireless 158. Wan S, Chen Y, Xiao Y, Zhao Q, Li L, Wu S. Spatial analysis and evaluation of
Commun Mobile Comput. (2020) 8:18. doi: 10.11648/j.wcmc.20200802.11 medical resource allocation in China based on geographic big data. BMC Health Serv
Res. (2021) 21:1084. doi: 10.1186/s12913-021-07119-3
141. Mathkor D, Mathkor N, Bassfar Z, Bantun F, Slama P, Ahmad F, et al. Multirole
of the internet of medical things (IoMT) in biomedical systems for managing smart 159. Nurse, J. The Potential Role of China in Advancing the COVID-19 Policy
healthcare systems: an overview of current and future innovative trends. J Infect Public Framework, Beijng. (2020).
Health. (2024) 17:559–72. doi: 10.1016/j.jiph.2024.01.013
160. Ge X, Zhou R, Li Q. 5G NFV-based tactile internet for mission-critical IoT
142. Endres H, Indulska M, Ghosh A. Unlocking the potential of industrial Internet services. IEEE Internet Things J. (2020) 7:6150–63. doi: 10.1109/JIOT.2019.2958063
of Things (IIOT) in the age of the industrial metaverse: business models and challenges.
161. Wijethilaka S, Liyanage M, Survey on network slicing for internet of things
Industr Mark Manag. (2024) 119:90–107. doi: 10.1016/j.indmarman.2024.03.006
realization in 5G networks. IEEE Commun Surv Tutor. (2021) 23:957–994. doi: 10.
143. Guan H. Construction of urban low-carbon development and sustainable 1109/COMST.2021.3067807
evaluation system based on the internet of things. Heliyon. (2024) 10:e30533. doi:
162. Vaishya R, Javaid M, Khan IH, Haleem A. Artificial intelligence (AI)
10.1016/j.heliyon.2024.e30533
applications for COVID-19 pandemic. Diab Metab Syndr Clin Res Rev. (2020) 14:337–
144. Mohammadzadeh N, Gholamzadeh M, Saeedi S, Rezayi S. The application 9. doi: 10.1016/j.dsx.2020.04.012
of wearable smart sensors for monitoring the vital signs of patients in epidemics:
163. Almaiah MA, Hajjej F, Ali A, Pasha MF, Almomani O. A novel hybrid
a systematic literature review. J Ambient Intell Human Comp. (2023) 14:6027–41.
trustworthy decentralized authentication and data preservation model for digital
doi: 10.1007/s12652-020-02656-x
healthcare IoT based CPS. Sensors (2022) 22:1448. doi: 10.3390/s22041448
145. Alshamrani M. IoT and artificial intelligence implementations for remote
164. Taimoor N, Rehman S. Reliable and resilient AI and IoT-based personalised
healthcare monitoring systems: a survey. J King Saud Univ Comp Inform Sci. (2022)
healthcare services: a survey. IEEE Access. (2022) 10:535–63. doi: 10.1109/ACCESS.
34:4687–701.
2021.3137364
146. Hu Y, Pan Z, De Bock M, Tan T, Wang Y, Shi Y, et al. A wearable microneedle
165. Panagiotidis P. Blockchain in education-the case of language learning. Eur J
patch incorporating reversible FRET-based hydrogel sensors for continuous
Educ. (2022) 5:66–82. doi: 10.26417/443gjm83
glucose monitoring. Biosens Bioelectron. (2024) 262:116542. doi: 10.1016/j.bios.2024.
116542 166. Simpson K, Nham W, Thariath J, Schafer H, Greenwood-Eriksen M, Fetters
MD, et al. How health systems facilitate patient-centered care and care coordination:
147. Mishra S, Saha B. Graphene- polymer nanocomposite-based wearable strain
a case series analysis to identify best practices. BMC Health Serv Res. (2022) 22:1448.
sensors for physiological signal monitoring: recent progress and challenges. Curr
doi: 10.1186/s12913-022-08623-w
Opin Solid State Materials Sci. (2024) 31:101174. doi: 10.1016/j.cossms.2024.10
1174 167. Al-Rawashdeh M, Keikhosrokiani P, Belaton B, Alawida M, Zwiri A. Effective
factors for the adoption of IoT applications in nursing care: a theoretical framework
148. Siao C, Chang R, Huang H. Robotic arms for telemedicine system using smart
for smart healthcare. J Build Eng. (2024) 89:109012. doi: 10.1016/j.jobe.2024.109012
sensors and ultrasound robots. Int Things. (2024) 27:101243. doi: 10.1016/j.iot.2024.
101243 168. Yelne S, Chaudhary M, Dod K, Sayyad A, Sharma R. Harnessing the power
of AI: a comprehensive review of its impact and challenges in nursing science and
149. Sikander S, Biswas P, Kulkarni P. Recent advancements in telemedicine:
healthcare. Cureus. (2023) 15:e49252. doi: 10.7759/cureus.49252
surgical, diagnostic and consultation devices. Biomed Eng Adv. (2023) 6:100096. doi:
10.1016/j.bea.2023.100096 169. Maina, A, Singh U. Exploring the Scope of Policy Issues Influencing IoT Health
and Big Data: A Structured Review. Florida: Apple Academic Press (2022).
150. Lu J, Ling K, Zhong W, He H, Ruan Z, Han W. Construction of a 5G-based,
three-dimensional, and efficiently connected emergency medical management system. 170. Casarosa F. Cyber security of Internet of Things in the health sector:
Heliyon. (2023) 9:e13826. doi: 10.1016/j.heliyon.2023.e13826 understanding the applicable legal framework. Comput Law Sec Rev. (2024) 53:105982.
doi: 10.1016/j.clsr.2024.105982
151. Yeasmin M, Al Amin M, Joti T, Aung Z, Azim M. Advances of AI in image-
based computer-aided diagnosis: a review. Array. (2024) 23:100357. doi: 10.1016/j. 171. Rathee G, Sharma A, Saini H, Kumar R, Iqbal R. A hybrid framework for
array.2024.100357 multimedia data processing in IoT-healthcare using blockchain technology. Mult Tools
Appl. (2020) 79:9711–33. doi: 10.1007/s11042-019-07835-3
152. Zhang J, Wu J, Qiu Y, Song A, Li W, Li X, et al. Intelligent speech technologies
for transcription, disease diagnosis, and medical equipment interactive control in 172. Sadhu P, Yanambaka V, Abdelgawad A, Yelamarthi K. Prospect of internet
smart hospitals: a review. Comput Biol Med. (2023) 153:106517. doi: 10.1016/j. of medical things: a review on security requirements and solutions. Sensors. (2022)
compbiomed.2022.106517 22:5517. doi: 10.3390/s22155517
153. Muse E, Topol E. Transforming the cardiometabolic disease landscape: 173. Ghosh A, Saha R, Misra S. Persistent service provisioning framework for
multimodal AI-powered approaches in prevention and management. Cell Metab. IoMT based emergency mobile healthcare units. IEEE J Biomed Health Inform. (2022)
(2024) 36:670–83. doi: 10.1016/j.cmet.2024.02.002 26:5851–8. doi: 10.1109/JBHI.2022.3172624
154. Tang Z, Tang Z Liu Y, Tang Z, Liao Y. Smart healthcare systems: a new IoT- 174. Fink M, Akra B. Comparison of the international regulations for medical
Fog based disease diagnosis framework for smart healthcare projects. Ain Shams Eng J. devices-USA versus Europe. Injury. (2023) 54:110908. doi: 10.1016/j.injury.2023.
(2024) 15:102941. doi: 10.1016/j.asej.2024.102941 110908
155. Li C, Wang J, Wang Sı, Zhang Y. A review of IoT applications in healthcare. 175. Raul AC (ed.). The Privacy, Data Protection and Cybersecurity Law Review. Law
Neurocomputing. (2024) 565:127017. doi: 10.1016/j.neucom.2023.127017 Business Research Limited (2021).
156. Fink M, Akra B. Comparison of the international regulations for medical 176. Szarfman A, Levine JG, Tonning JM, Weichold F, Bloom JC, Soreth JM, et al.
devices-USA versus Europe. Injury. (2023) 54:110908. doi: 10.1016/j.injury.2023. Recommendations for achieving interoperable and shareable medical data in the USA.
110908 Commun Med. (2022) 2:86. doi: 10.1038/s43856-022-00148-x

Frontiers in Medicine 17 frontiersin.org