Wangpitipanit et al.

BMC Nursing (2024) 23:529 BMC Nursing

https://doi.org/10.1186/s12912-024-02170-x

RESEARCH Open Access

Exploring the deep learning of artificial

intelligence in nursing: a concept analysis
with Walker and Avant’s approach
Supichaya Wangpitipanit1 , Jiraporn Lininger2* and Nick Anderson3

Abstract
Background In recent years, increased attention has been given to using deep learning (DL) of artificial intelligence
(AI) in healthcare to address nursing challenges. The adoption of new technologies in nursing needs to be improved,
and AI in nursing is still in its early stages. However, the current literature needs more clarity, which affects clinical
practice, research, and theory development. This study aimed to clarify the meaning of deep learning and identify the
defining attributes of artificial intelligence within nursing.
Methods We conducted a concept analysis of the deep learning of AI in nursing care using Walker and Avant’s 8-step
approach. Our search strategy employed Boolean techniques and MeSH terms across databases, including BMC,
CINAHL, ClinicalKey for Nursing, Embase, Ovid, Scopus, SpringerLink and Spinger Nature, ProQuest, PubMed, and Web
of Science. By focusing on relevant keywords in titles and abstracts from articles published between 2018 and 2024,
we initially found 571 sources.
Results Thirty-seven articles that met the inclusion criteria were analyzed in this study. The attributes of evidence
included four themes: focus and immersion, coding and understanding, arranging layers and algorithms, and
implementing within the process of use cases to modify recommendations. Antecedents, unclear systems and
communication, insufficient data management knowledge and support, and compound challenges can lead to
suffering and risky caregiving tasks. Applying deep learning techniques enables nurses to simulate scenarios, predict
outcomes, and plan care more precisely. Embracing deep learning equipment allows nurses to make better decisions.
It empowers them with enhanced knowledge while ensuring adequate support and resources essential for caregiver
and patient well-being. Access to necessary equipment is vital for high-quality home healthcare.
Conclusion This study provides a clearer understanding of the use of deep learning in nursing and its implications
for nursing practice. Future research should focus on exploring the impact of deep learning on healthcare operations
management through quantitative and qualitative studies. Additionally, developing a framework to guide the
integration of deep learning into nursing practice is recommended to facilitate its adoption and implementation.
Keywords Deep learning, Artificial intelligence, Nursing, Concept analysis, Walker and Avant

*Correspondence: Ramathibodi School of Nursing, Faculty of Medicine Ramathibodi

Jiraporn Lininger Hospital, Mahidol University, Bangkok, Thailand
2
jiraporn.lin@mahidol.edu Division of Community Health Nursing, Ramathibodi School of
1
Visiting Assistant Professor, Division of Health Informatics, Department Nursing, Faculty of Medicine Ramathibodi Hospital, Mahidol University,
of Public Health Sciences, UC Davis School of Medicine, University Bangkok, Thailand
3
of California, Davis, USA, Division of Community Health Nursing, Division of Health Informatics, Department of Public Health Sciences, UC
Davis School of Medicine, University of California, Davis, USA

© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use,
sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and
the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this
article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included
in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will
need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The
Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available
in this article, unless otherwise stated in a credit line to the data.
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 2 of 10

Background with the highest ethical standards and practices in nurs-

Nursing is crucial for supporting patients with chronic ing and healthcare [1, 14–17].
illness or those in need of ongoing care, whether they Numerous studies have explored integrating deep
are healthy or awaiting continuous long-term assistance. learning into healthcare systems, highlighting its poten-
By promoting health, preventing disease, treating ill- tial to enhance nursing practices using advanced artificial
nesses, and facilitating rehabilitation, nurses contribute intelligence tools. Moreover, deep learning algorithms
significantly to the well-being of individuals, families, empower nurses to analyze patient data for more effec-
and communities. This requires delivering services that tive decision-making, outcome prediction, and treatment
prioritize suitability and enhance quality of life, drawing planning. These methods expedite the identification of
upon scientific principles and nursing expertise [1–3]. abnormalities in medical images and streamline docu-
Technology integration is fundamental for advancing the mentation processes. Furthermore, deep learning con-
caregiving process, as it empowers nurses to offer more tributes to safer medication management and facilitates
efficient and streamlined care. By incorporating technol- remote patient monitoring, enabling nurses to inter-
ogy into caregiving and treatment, nurses can provide vene promptly. With its capacity for personalized care,
more effective assistance, ensuring that patients receive deep learning holds promise for revolutionizing nursing
the highest standard of care. Despite technological practices, ultimately resulting in improved patient out-
advancements, compassionate care—often referred to as comes and healthcare delivery [16–21]. DL within arti-
the human touch—remains paramount. Technology can ficial intelligence has garnered considerable attention in
further augment this compassionate care, ensuring that the contemporary era. However, navigating the opera-
patient needs are met efficiently and emotionally [1, 4–6]. tional complexities of ML and ANNs presents a distinct
In recent years, there has been a growing emphasis on challenge, particularly within the nursing profession
integrating AI technology into nursing practices, mark- and healthcare providers. Establishing clear operational
ing a significant milestone in adopting AI in patient care definitions and frameworks is essential for effectively
[2, 6–8]. This movement underscores the importance of integrating deep learning into nursing practice. Given
deploying AI systems effectively within healthcare set- the rapid evolution of AI, insights derived from current
tings. Within this context, machine learning (ML) and analyses may only be intermittently applicable to future
DL are essential components. DL, a specialized branch of practices, influenced by emerging features, requirements,
AI and ML, harnesses artificial neural networks (ANNs) and outcomes. Furthermore, in the realm of health sci-
with multiple layers, commonly known as “deep” net- ence and technology, Morse’s approach, as applied by
works. The pivotal role of DL within the broader AI Zhida Shang, has been pivotal in understanding ‘arti-
landscape is evident, as it introduces advanced tech- ficial intelligence in nursing’ [22]. A significant limita-
niques that enhance the capabilities of intelligent systems tion arises from the need for comprehensive studies that
while adhering to specific parameters and constraints. define, apply, trace origins, delineate characteristics, and
Inspired by the human brain, DL algorithms layer at outline the consequences of AI in nursing. Nonetheless,
understanding intricate patterns in extensive datasets, enhancing clarity and understanding of these concepts
driving breakthroughs in areas such as computer vision, is crucial for advancing knowledge in nursing science.
natural language processing, and speech recognition [1, This research aims to explore the concept of deep learn-
9–12]. As a subset of AI, ML and DL play a crucial role ing within artificial intelligence as it pertains to nursing,
in advancing the development of intelligent systems and utilizing Walker and Avant’s concept analysis method
fostering innovation across various sectors. Examining [23] to ensure a comprehensive and shared understand-
AI functionalities and practical implementation strate- ing. The study seeks to clarify the meaning and identify
gies is vital for enhancing privacy measures and optimiz- the defining attributes of artificial intelligence in the deep
ing resource allocation in healthcare settings. However, learning of artificial intelligence within nursing.
while AI has promising outcomes, its implementation
may pose unforeseen challenges and adverse effects, Methods
impacting medical treatment and healthcare delivery Concept analysis approach
within hospitals [1, 12–15]. Furthermore, a pressing need In the field of nursing science, concept analysis is a cru-
exists to delve more deeply into the potential applica- cial research tool that helps broaden understanding. It
tions of AI in nursing and healthcare to enhance overall includes breaking down essential concepts into their
healthcare provision. It is essential to address pertinent basic parts, providing researchers with valuable insights.
issues such as bias and algorithmic considerations, which Through this approach, nursing experts refine defini-
are integral to evaluating the efficacy and ethical implica- tions, make measurements precise and offer new view-
tions of AI interventions. Ultimately, the prudent use of points on things of interest. Concept analysis reveals
AI technology is essential for achieving outcomes aligned the unique features of concepts that are vital in the
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 3 of 10

ever-changing world of nursing science. It is essential to approach of Walker and Avant [23]. To thoroughly delve
recognize that concepts in this field change over time. into the depth of the concept, an exhaustive search of
The procedure used in this concept analysis is based on the literature from 2018 to 2024 was meticulously con-
Walker and Avant’s method [23], providing an evalua- ducted across a wide array of diverse databases employ-
tion framework for examining the concept’s definition, ing rigorous Boolean techniques and MeSH terms [25,
characteristics, antecedents, consequences, and scope, 26]. A total of 2,366 articles were screened, eventually
ensuring thorough understanding. Additionally, Morse’s yielding 571 relevant articles across ten databases: 181
analytical foundation approach facilitates the evaluation from PubMed, 159 from ClinicalKey for Nursing, 135
of ideas with clear boundaries, making it appropriate for from SpringerLink and Spinger Nature, 31 from Ovid,
this context [24]. Understanding DL aspect of AI in nurs- 24 from Scopus, 18 from ProQuest, 13 from CINAHL,
ing requires clarifying terms often used interchangeably, five from Embase, three from BMC, and two from the
which is crucial for advancing knowledge and develop- Web of Science show in Table 1. Following the method-
ing theories. The application of DL in nursing converges ology advocated by Walker and Avant [23], the search
multiple disciplines, resulting in a multi-dimensional strategy strategically employed Boolean techniques to
concept. Current literature on AI in nursing needs to be collect pertinent information for concept analysis. Sub-
more specific, with various interchangeable and poorly sequently, the concept analysis method was meticulously
understood definitions, necessitating concept develop- executed, encompassing a series of steps: (1) selection of
ment, explanation, and comparison. The absence of a a concept, (2) determination of the aims or purposes of
comprehensive definition for DL in AI within nursing is analysis, (3) determination of the defining attributes, and
concerning, as future researchers might rely on standard (4) identification of all uses of the concept. (5) Identify
dictionary definitions, leading to broader implications the antecedents and consequences. (6) Identify a model
due to competing definitions. Thus, clarifying and dif- case, (7) identify borderline and related cases, and (8)
ferentiating these definitions using Walker and Avant’s define empirical referents. This systematic and rigorous
method is essential. Therefore, concept analysis is an approach ensures a comprehensive understanding of the
ongoing effort to maintain the evolving understanding of concept’s dimensions and its implications within the field
nursing science. of nursing and its related domains. Finally, 36 articles
were selected for analysis, and the PRISMA diagram is
Data collection shown in Fig. 1 [27].
This study used a systematic analytical approach. The
study aimed to clarify the concept with keywords such
as deep learning, machine learning, artificial intelligence,
and nursing by determining its dimensions using the

Table 1 The search strategies and results summary for each database
Database Search Strategy Filters Eligible Results
PubMed ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 181 2
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
ClinicalKey for ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 159 3
Nursing AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Springerlink ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 135 4
and Spinger AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Nature,
Ovid ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 31 9
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Scopus ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 24 4
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
ProQuest, ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 18 2
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
CINAHL ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 13 2
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Embrace ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 5 5
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
BMC ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 3 3
AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Web of ((“Deep learning” AND (“Machine learning”) AND “Artificial Intelligence”) Publication date: 2018–2024, English 2 3
Science AND (“Nursing”) AND (“Concept Analysis”)) language, Systematic reviews
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 4 of 10

Fig. 1 PRISMA diagram outlining the search strategy

Results framework and relevance within the field. This highlights

Selection of a concept the significance of integrating these concepts into nurs-
The review of the literature emphasizes the critical ing practice to enhance patient care using modern tech-
importance of integrating AI into healthcare, particularly nological advancements. Through an analysis of relevant
within nursing. Collaborative efforts between AI and activities and projects in nursing science, this research
nursing teams can potentially enhance healthcare out- aims to elucidate the fundamental principles and defining
comes, as the promotion of AI education among nursing attributes of deep learning in AI.
staff is vital for sustainable development. These studies
offer valuable insights into the role of deep learning in Identifying all uses of the concept that you can discover
healthcare, potentially strengthening our understanding An onomasiological approach was used to define the con-
of deep learning in AI applications. Therefore, the main cept across various contexts. Deep learning involves the
objective of this research is to explore deep learning in theory and development of computer systems capable of
artificial intelligence within the context of nursing sci- tasks like speech recognition, learning, visual perception,
ence through concept analysis. mathematical computations, reasoning, problem-solv-
ing, decision-making, and language translation. Unlike
Determine the aims or purposes of analysis traditional algorithms that focus narrowly, deep learn-
This study explored how deep learning in artificial intel- ing employs supervised or unsupervised machine learn-
ligence can be applied in nursing, aiming to define its ing techniques. These methods create and refine neural
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 5 of 10

network models through multi-layered data representa- to learn hierarchical data representations, progressing
tions and nonlinear transformations. Medical Subject from fundamental concepts to more abstract ones. This
Headings (MeSH) terms vary in specificity in nursing hierarchical learning enables deep models to apprehend
research and literature. There isn’t a single MeSH term intricate patterns by capturing features at varying levels
combining “deep learning” and “artificial intelligence” of abstraction. Training deep learning models neces-
in nursing. However, terms like “Artificial Intelligence,” sitates extensive labeled datasets, commonly called big
“Machine Learning,” and “Neural Networks” collec- data, facilitating robust generalization to new examples
tively cover these concepts. These terms help researchers and enhancing overall performance [9–12]. The ver-
access relevant studies in nursing databases, supporting satility of deep learning is evident in its wide-ranging
advancements in patient care, clinical decision-making, applications across domains such as image and speech
and nursing education [25, 26]. recognition and natural language processing, demon-
Artificial intelligence was first coined by John McCar- strating its ability to perform diverse tasks. Specialized
thy in 1956 at Dartmouth College. Since then, AI has architectures such as ANNs can optimize performance
evolved significantly, emphasizing technological founda- by tailoring the model structures to handle specific data
tions and cognitive resonance with human intelligence. types and tasks effectively. Additionally, deep learning
This evolution led to machine learning paradigms intro- fosters autonomous knowledge acquisition, enabling
ducing models like Artificial Neural Networks (ANNs) machines to learn and apply knowledge from data with-
[1, 10–12]. Deep learning, initially conceptualized by out explicit programming autonomously. Compared with
Dechter in 1986, constructs complex functions through their shallow counterparts, deep networks often exhibit
layered neural networks. These architectures mimic efficiency in approximating functions, achieving com-
hierarchical processing in biological brains with input, parable results with fewer computational resources. As
hidden, and output layers. Techniques like backpropaga- a subset of machine learning and artificial intelligence,
tion refine mathematical operations to discern patterns deep learning aims to emulate human brain networks,
and insights from extensive datasets [28]. This narra- enabling machines to learn and make decisions akin to
tive begins with AI’s inception and traces its evolution human cognition. From a nursing science perspective,
to deep learning [1, 10–12]. A detailed onomasiological numerous studies have demonstrated the potential appli-
analysis shows that “deep learning” involves immersion, cation of deep learning in research [9–12, 30].
focus, and profound understanding, contrasting with When delving into the intricacies of deep learning,
superficial notions. This cognitive engagement parallels specific components emerge. This entails synthesizing
human brain functions, supporting memory and learn- various works and organizing them into a structured
ing pathways. In education and computer science, deep framework harmonized with a formal control system to
learning promotes critical thinking, problem-solving, and enhance nursing care. Focus, immerse, code, understand,
practical knowledge application [29, 30]. Projects and arrange layers and algorithms, and implement within
teamwork encourage deep subject exploration and cre- the use process. This involves (1) focusing and immers-
ative solutions. Computationally, deep learning enhances ing individuals in the central point of interest or atten-
performance through dataset analysis [31, 32]. This mir- tion and thoroughly engaging individuals in an activity
rors hierarchical brain learning with supervised, unsu- and implementing a tactile tool or a system that requires
pervised, or reinforcement methods to absorb knowledge manual manipulation to initiate the process within a use
[9–12, 33–35]. case scenario—a series of actions to achieve a specific
outcome. Focusing or visualizing the original knowledge,
Determine the defining attributes which in this context is deep learning, is crucial. Par-
Deep learning holds promise for transforming nursing ticipants must be sincerely interested and immersed in
practice by enhancing clinical decision-making, improv- the activity, aligning with predefined objectives or goals
ing patient monitoring, and enabling predictive analyt- to foster commitment and engagement. This approach
ics. By leveraging these advanced technologies, nurses forms the cornerstone for success in any endeavor. (2)
can provide more accurate, timely, and personalized care, Coding and understanding are foundational pillars in
ultimately improving patient outcomes and operational the intricate landscape of deep learning, particularly
efficiency in healthcare settings. As the field evolves, in enhancing nursing care. In deep learning, coding
ongoing research and collaboration between data sci- involves meticulously arranging words, letters, or sym-
entists and healthcare professionals will be crucial to bols to encapsulate messages, whether for encryption or
fully realizing the benefits of deep learning in nursing. concise communication. This process, which may utilize
In-depth learning refers to in-depth work that involves numerical, alphabetical, or symbolic systems, encodes
an input process and has functions in both analysis and information conducive to efficient comprehension and
algorithmic processing. It is characterized by its capacity analysis. On the other hand, understanding delves into
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 6 of 10

the profound assimilation and interpretation of con- a home visit (home health care [32, 36]) of a 98-year-old
veyed meaning, facilitating informed decision-making. grandfather unable to leave his bed. The nurse assisted
This comprehensive grasp of information is essential with daily tasks using a scale called the Barthel ADL
for nurses as they navigate the complexities of patient Index, where a score of 1 out of 20 is typical. Additionally,
care, encompassing direct clinical interventions and family members, such as grandchildren-in-law, are wait-
the broader implications of illness and healthcare prac- ing to assist, perhaps with tasks such as changing diapers
tices. Through deep understanding, nurses can adeptly twice a day. Imagine a community health nurse prepar-
decipher the intricacies of patient conditions, treatment ing for a home visit to care for a 98-year-old grandfather
plans, and the ever-evolving healthcare landscape, ulti- who is bedridden. Nurses rely on tools such as the Bar-
mately fostering optimal patient outcomes and enhancing thel ADL Index to assess the grandfather’s needs, which
healthcare delivery. (3) Arranging layers and algorithms are typically just 1 out of 20. Family members, such as
involves structuring data akin to distinct material or grandchildren-in-law, are also involved in caregiving,
thin sheet levels and utilizing mathematical instructions aiding with tasks such as changing diapers and schedul-
or rules to guide problem-solving. This process encom- ing visits. However, nurses face the challenge of under-
passes organizing layers based on specific instructions standing grandfathers’ complex health issues to provide
or mathematical principles, allowing computers to com- tailored assistance effectively. To address this, the nurse
prehend and process information effectively. This attri- delves into the patient’s records, utilizing electronic
bute also entails utilizing tools to execute tasks based health records (EHR) systems to access crucial informa-
on predefined instructions and algorithms. For instance, tion for diagnosis and treatment. Mastery of medical
learning algorithms adeptly capture constraints involv- applications and computer programs is also essential for
ing a limited number of variables while arranging layers, medication management and accurate interpretation of
and following prescribed algorithms ensures systematic test results. Additionally, nurses embrace telehealth tools,
processing of information to address the given problem. such as video calls, to facilitate efficient communication
Finally, implementation involves employing tools fol- with healthcare teams, overcoming geographical barri-
lowing predefined instructions to achieve results aligned ers. However, ensuring patient privacy and data security
with the established algorithm. (4) In the implemen- remains paramount when utilizing these technologies.
tation process within the use case, meticulous atten- Organizing care plans and applying algorithms to meet
tion is directed toward practice, employing a systematic the grandfather’s specific needs are crucial in caregiving.
approach reminiscent of principles to yield favorable Understanding these principles allows nurses to provide
outcomes. This approach emphasizes the importance systematic and efficient care while safeguarding patient
of evidence-based practices, drawing upon empirical information from unauthorized access or tampering.
evidence to enhance the quality of care and ultimately In essence, by integrating deep learning concepts into
improve patient outcomes. Implementation strategies caregiving practices, nurses can increase the standard
may involve the utilization of simulations or carefully of home visits for older patients, such as grandfathers.
crafted designs aimed at gaining a comprehensive under- This holistic approach ensures adherence to guidelines
standing of patient needs and intricacies, facilitating the and maximizes efficiency and convenience, leveraging
effective planning and delivery of care. By adhering to the support of family members for an optimal caregiv-
evidence-based practices and leveraging innovative tools ing experience [17]. The deep learning prediction model
such as simulations, healthcare professionals can navi- and the resulting risk stratification score may prove help-
gate the complexities of patient care with precision and ful in clinical decision-making under time-sensitive and
compassion, ensuring optimal outcomes and patient sat- resource-constrained environments [37–44].
isfaction. However, with the advancement of AI technol-
ogy, the intricacies of utilizing deep learning in nursing Identify contrary cases and borderline cases
have become increasingly significant. Investigating the The visiting nurse received an urgent call from a con-
role of AI is crucial, particularly in nurse registration. cerned patient, a 67-year-old individual seeking assis-
This approach involves developing a process to monitor tance from their 85-year-old grandmother who had
advancements, encompassing health trends and nursing recently suffered a debilitating stroke three months prior.
research [9–12, 21, 31]. The grandmother was bedridden, her movements were
restricted, and her ability to sense her surroundings
Identify a model case greatly diminished. Complicating matters, the feeding
The idea of understanding deep learning can be divided tube she relied upon often became dislodged, requiring
into four parts: focusing, understanding code, organizing frequent readjustments and careful monitoring. Upon
layers and algorithms, and applying it in real-life situa- arrival, the nurse encountered a distressing scene. Essen-
tions. Now, picture a community health nurse who plans tial equipment needed to be included or completed,
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 7 of 10

forcing the nurse to improvise with makeshift solutions. DL technology within their practice, intertwining it with
This hindered the efficiency of care and posed risks to various related arts such as simulating complex sce-
the grandmother’s well-being. Adding to the situation’s narios, crafting intricate decision trees, and predicting
complexity was the psychological and economic stress outcomes through advanced algorithms like deep belief
experienced by the family caregivers. Individuals con- networks and multilayer perceptron’s. This integration
stantly tending to meet the needs of elderly loved ones addresses existing challenges and advances the profes-
with serious health issues exacted a heavy toll, both emo- sion by enhancing the accuracy and efficiency of patient
tionally and financially. The demands of continuous care care, ultimately leading to better patient outcomes and a
left caregivers exhausted and overwhelmed, exacerbating more efficient healthcare system [17, 18].
the challenges faced by nurses upon arrival. Furthermore,
the need for premade equipment added another layer Define the empirical referents
of complications. Procuring these items often involved Directly connected to the theory behind DL, we see that
lengthy delays, further impeding the provision of timely whatever can be measured is retained. This is evident
and effective care—the strain of navigating these logisti- when we try receiving and interpreting signals. In nurs-
cal hurdles not only exacerbated the already tense atmo- ing, careful attention is given to science. We collected
sphere. During these challenges, it became evident that various data for analysis, aiming for meaningful results.
the standard of care fell short of what was necessary Understanding these principles empowers nurses to pro-
for the grandmother’s well-being. Despite the caregiv- vide well-organized, impactful data-based care. It has
ers’ best efforts, the lack of adequate preparation and been noted that what can be measured there is kept. This
support left the grandmother vulnerable and in need of is noticeable in the trial of the reception of the receipt
more comprehensive care. This scenario underscores the signal. Care in the scientific direction of nursing may be
critical importance of recognizing and addressing the all forms of data recorded to be analyzed and interpreted
psychological and economic stress experienced by fam- appropriately, and possible results may be obtained.
ily caregivers. Providing patients with adequate support Understanding these principles helps nurses provide sys-
and resources is essential for ensuring the well-being of tematic, effective care based on data.
both the caregiver and the care recipient. Additionally,
ensuring that healthcare professionals access the neces- Discussion
sary equipment and resources is vital for delivering high- This approach offers a systematic approach to refining
quality care in home healthcare settings. one’s understanding of complex concepts, such as DL, by
exploring various qualities and elements. DL, a subset of
Identify the antecedents and consequences ML and AI, employs artificial neural networks to process
When exploring the antecedents of DL in nursing, it vast datasets, revolutionizing industries such as health-
becomes evident that nurses across various care settings care and finance. Its multilayered architecture enables
face overwhelming challenges and demands that directly precise simulation and outcome prediction and promis-
impact patient care. These antecedents include the repet- ing enrichment of nursing and patient care across vari-
itive nature of caregiving tasks, inadequate knowledge ous domains. Utilizing Walker and Avant’s conceptual
of data management, and insufficient support. Nurses in framework [23], critics of the DL concept typically fol-
both care facilities and community settings juggle mul- low eight steps; a contemporary concept widely applied
tiple roles amidst ambiguity in systems and communica- today entails a thorough analysis to enhance functional-
tion, leading to risky and repetitive caregiving tasks that ity. Understanding its application in healthcare is crucial
contribute to heightened stress and fatigue. The lack of for nurses, given DL’s proficiency in learning hierarchical
knowledge in data management significantly hinders the data representations through extensive labeled datasets,
effective utilization of the nursing process, while insuffi- thus achieving robust performance across various tasks.
cient support and resources exacerbate these challenges, DL leverages specialized architectures such as ANNs and
impeding effective communication and continuous learn- transformers to optimize performance for specific tasks,
ing. This intensifies feelings of isolation and frustration promote automated knowledge acquisition and facilitate
among caregivers, underscoring the complexities inher- learning from explicit programming of data sans. Deep
ent in caregiving and highlighting the need for enhanced networks efficiently estimate functions, delivering com-
support and training in data management and communi- parable results with fewer computational resources [17,
cation [17, 18]. Consequently, integrating DL in nursing 18]. DL analysis entails meticulous data collection and
can lead to several beneficial outcomes. Enhanced sup- investigation to delve into layer-by-layer data representa-
port and training foster trust and precision in evaluating tions, necessitating large datasets. DL models showcase
and planning nursing care, resulting in a more explicit, versatility in recognizing images, controlling specialized
outcome-oriented process. Nurses can seamlessly apply natural language features, and promoting autonomous
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 8 of 10

knowledge acquisition. Moreover, DL fosters research intricately layered in nursing applications to encompass
efficiency by illuminating fundamental principles and understanding healthcare contexts, collecting and pre-
structures in various applications, particularly in health- processing diverse data, developing specialized algo-
care settings, with profound impact. The aim of deep rithms, and integrating models into clinical workflows.
learning concept analysis is to refine its functional scope Implementation strategies involve collaborative efforts
and clarify and differentiate concepts to pave the way to align AI with nursing standards, integrate it into exist-
for future understanding and measurement. Systematic ing infrastructure, provide adequate training, and ensure
reviews help delineate the definition and scope of deep ethical usage. These initiatives promise to enhance
learning, enhancing the precision and comprehensive- patient care, streamline workflows, and address ethical,
ness of its application [9–12]. legal, and societal concerns, significantly advancing nurs-
This literature review explores DL within the AI, high- ing practice [37–45].
lighting its significance and unique characteristics. DL
stands at the forefront of transformative technologies, Limitations
continually enhancing machines’ data processing and The study’s limitation is its dependence on theoretical
comprehension capabilities. By leveraging advancements analysis without empirical validation, which diminishes
in computational resources and methodologies, DL has its applicability to real-world nursing education and
the potential to revolutionize various industries. As a highlights a significant research gap. Empirical validation
subset of AI and machine learning, DL replicates human- could have improved the understanding of deep learning
like abilities in pattern recognition and decision-making, in nursing, offered practical insights into its educational
utilizing artificial neural networks inspired by the human implications, identified implementation challenges, and
brain’s structure. Its intricate, multilayered architecture confirmed theoretical constructs. The introduction high-
facilitates sophisticated data analysis, offering advan- lights the limited number of studies in AI and notes that
tages over traditional machine-learning techniques [17, the field is continually evolving with new deep learn-
18]. Despite these efficiency gains, DL methods require ing approaches. This scarcity and the rapidly changing
substantial computational power and time due to their nature of AI make in-depth exploration difficult, empha-
complex neural networks and the handling of large data- sizing the need for empirical studies to bridge this gap
sets. The discussion section should prioritize core con- and ensure theoretical models are relevant in practical
cepts such as integrating DL into nursing care and its contexts.
technical foundations rather than solely focusing on its
technological and mechanical applications. While the Conclusion
current overview provides a broad perspective on DL This study enhances the understanding of the applica-
and its implications for nursing practice, a more pro- tion of deep learning in nursing care and underscores its
found exploration of specific challenges, opportunities, potential implications for nursing practice. Moving for-
and future directions would enhance its depth and rel- ward, future research needs to further explore the impact
evance. This deeper analysis can elucidate how DL can of deep learning on healthcare operations management
effectively enhance patient care and nursing outcomes through quantitative and qualitative studies. Research-
while addressing the ethical and practical considerations ers can provide valuable insights into the transforma-
accompanying its implementation in healthcare settings. tive potential of deep learning technology by examining
Furthermore, a detailed examination of DL’s implications how deep learning technologies can optimize various
in nursing could illuminate innovative methodologies aspects of healthcare delivery, such as resource allocation
and approaches that leverage its capabilities to improve and patient monitoring. Moreover, developing a com-
diagnostic accuracy, treatment planning, and patient prehensive framework is crucial for effectively integrat-
monitoring. Such an expanded discussion would under- ing deep learning into nursing practice. This framework
score DL’s transformative potential in healthcare and should not only address technical considerations but also
contribute a clearer understanding of the strategic initia- encompass ethical, legal, and regulatory aspects to ensure
tives necessary for responsible and effective integration the responsibility and ethical use of AI in healthcare set-
into nursing practice. These insights can inform poli- tings. Additionally, future research should acknowledge
cies and practices that support the ethical deployment and address the limitations of this study, such as poten-
of DL, ensuring alignment with patient-centered care tial biases in article selection or analysis methodolo-
and advancing nursing excellence in the future. Integrat- gies, to foster a more robust and nuanced understanding
ing AI in nursing requires enhancing nurses’ qualifica- of the role of deep learning in nursing care. Nurses can
tions and education to comprehend AI’s capabilities and augment their decision-making capabilities by embrac-
limitations, complemented by informational campaigns ing deep learning technologies, enhancing patient care
to equip nurses with essential skills. DL technology is outcomes, and streamlining clinical workflows. As we
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 9 of 10

Author contributions
continue to explore and harness the potential of AI in SW: Conceptualization, methodology, investigation, interpretation of data,
healthcare, collaboration between researchers, clinicians, writing‐original draft, validation, review & editing JL: Methodology, writing‐
policymakers, and industry stakeholders will be essential original draft, investigation, validation, review & editing NA: Methodology,
investigation, validation, review & editing. All the authors reviewed the
to drive innovation and facilitate the widespread adop- manuscript and agreed on the final version.
tion of deep learning in nursing practice.
Funding
There was no financial support from any organization.
Recommendations Open access funding provided by Mahidol University
The exploration of deep learning as a subset of artifi-
cial intelligence and machine learning underscores its Data availability
DeclarationsUnder ‘Declarations,’ this study involved a retrospective review
potential to revolutionize nursing practices. While the of records and did not include any direct interaction with patients by the
literature review reveals the limited presence of deep research team. The data and materials used or produced throughout this
learning applications in nursing research, particularly study have been included in this manuscript”.

in medical domains and interdisciplinary fields, the

identified gap highlights an opportunity for integration. Declarations
Under ‘Declarations,’ this study involved a retrospective review of records and
Inspired by the human brain’s neural networks, deep did not include any direct interaction with patients by the research team.
learning offers advantages in recognizing patterns and The data and materials used or produced throughout this study have been
making decisions, showcasing its versatility in handling included in this manuscript”.

diverse datasets. The study’s findings emphasize the Ethics approval and consent to participate
need for nurses to embrace deep learning, empowering Not applicable.
them with enhanced knowledge and decision-making
Consent for publication
capabilities. By integrating deep learning into nursing Not applicable.
practices, nurses could be equipped with tools to make
more informed decisions, especially in diagnostic nurs- Competing interests
The authors declare no competing interests.
ing, thereby improving healthcare operation assessments
and reducing the risk of medical disputes. Moving for- Received: 14 May 2024 / Accepted: 11 July 2024
ward, future research proposals and the development of
a framework are recommended to explore the impact of
deep learning on healthcare operations management.
Such initiatives aim to promote safety and enhance the References
overall quality of life for patients and communities glob- 1. Robert N. How artificial intelligence is changing nursing. Nurs Manag.
2019;50(9):30–9. https://doi.org/10.1097/01.NUMA.0000578988.56622.21
ally, reflecting the transformative potential of deep learn- 2. Johnson EA, Dudding KM, Carrington JM. When to err is inhuman: an exami-
ing as technology continues to advance. Preparing nurses nation of the influence of artificial intelligence-driven nursing care on patient
for AI deep learning in healthcare integration requires safety. Nurs Inq. 2024;31:e12583. https://doi.org/10.1111/nin.12583
3. O’Connor S, Yan Y, Thilo FJS, Felzmann H, Dowding D, Lee JJ. Artificial
updating their qualifications, educating them about AI intelligence in nursing and midwifery: a systematic review. J Clin Nurs.
capabilities and limitations, and conducting nursing care- 2023;32:2951–296. https://doi.org/10.1111/jocn.16478
specific research. The involvement of researchers, policy- 4. Seibert K, Domhoff D, Fürstenau D, Biessmann F, Schulte-Althoff M, Wolf‐
Ostermann K. Exploring needs and challenges for AI in nursing care – results
makers, and guideline developers ensures alignment with of an explorative sequential mixed methods study. BMC Digit Health.
standards, while discussions on ethical, legal, and societal 2023;1:1–13. https://doi.org/10.1186/s44247-023-00015-2
implications are crucial for stakeholder participation and 5. Sommer D, Schmidbauer L, Wahl F. Nurses’ perceptions, experience and
knowledge regarding artificial intelligence: results from a cross-sectional
advancement. online survey in Germany. BMC Nurs. 2024;23:205. https://doi.org/10.1186/
s12912-024-01884-2
Abbreviations 6. Seibert K, Domhoff D, Bruch D, Schulte-Althoff M, Fürstenau D, Biess-
AI Artificial Intelligence mann F, et al. Application scenarios for Artificial intelligence in nursing
ANNs Artificial Neural Networks care: Rapid Review. J Med Internet Res. 2021;23(11):e26522. https://doi.
CDS Clinical Decision Support org/10.2196/26522
CINAHL Cumulative Index to Nursing & Allied Health Literature 7. Ross J. Visioning a future: virtual nursing care. J Perianesth Nurs. 2024;39:322–
DL Deep Learning 3. https://doi.org/10.1016/j.jopan.2024.01.016
ML Machine Learning 8. Uymaz AO, Uymaz P, Akgül Y. Assessing acceptance of AI nurses for outpa-
MeSH Medical Subject Headings tients with chronic diseases: from nurses’ perspective. Environ Soc Psychol.
PRISMA Preferred Reporting Items for Systematic Reviews and Meta 2024;9(5):2309. https://doi.org/10.54517/esp.v9i5.2309
Analyses 9. Indolia S, Goswami AK, Asopa P. Conceptual understanding of convolu-
tional neural Network- A Deep Learning Approach. Procedia Comput Sci.
Acknowledgements 2018;132:679–88.
The author thanks the Ramathibodi School of Nursing and the Faculty of 10. McGrow K. Artificial intelligence: essentials for nursing. Nursing.
Medicine, Ramathibodi Hospital, Mahidol University, for their support, which 2019;49(9):46–9. https://doi.org/10.1097/01.NURSE.0000577716.57052.8d
was instrumental in completing this work. 11. Sittichanbuncha Y. Artificial Intelligence (AI) and its use in Healthcare and
Emergency Medicine. J Emerg Med Serv Thail. 2021;1(1):91–104.
Wangpitipanit et al. BMC Nursing (2024) 23:529 Page 10 of 10

12. Prince SJD. Understanding Deep Learning. The MIT press; 2023. https://udl- 31. Hote PK, Venkatesan L, Garg R, Gopichandran L. Artificial intelligence for
book.github.io/udlbook/. Updated April 16, 2024. smart patient care: transforming future of nursing practice. Int J Res Med Sci.
13. Esmaeilzadeh P. Use of AI-based tools for healthcare purposes: a survey study 2023;11(10):3931–6. https://doi.org/10.18203/2320-6012.ijrms20233066
from consumers’perspectives. BMC Med Inf Decis Mak. 2020;20:170. https:// 32. Sockolow PS, Bowles KH, Topaz M, Koru G, Hellesø R, O’Connor M, et al. The
doi.org/10.1186/s12911-020-01191-1 Time is now: Informatics Research Opportunities in Home Health Care. Appl
14. Cheng AS, Guan Q, Su Y, Zhou P, Zeng Y. Integration of machine learning Clin Inf. 2021;12(1):100–6. https://doi.org/10.1055/s-0040-1722222
and Blockchain Technology in the Healthcare Field: A literature review and 33. Cambridge Dictionary. Deep Learning. Cambridge University Press; 2024.
implications for Cancer Care. Asia Pac J Oncol Nurs. 2021;8(6):720–4. https://dictionary.cambridge.org/dictionary/english/deep-learning. Updated
15. Lambert B, Forbes F, Doyle S, Dehaene H, Dojat M. Trustworthy clinical AI April 10, 2024.
solutions: a unified review of uncertainty quantification in Deep Learning 34. Cambridge Dictionary. Artificial intelligence, Cambridge University Press.
models for medical image analysis. Artif Intell Med. 2024;150:102830. https:// 2024. https://dictionary.cambridge.org/dictionary/english/ai?q=AI. Updated
doi.org/10.1016/j.artmed.2024.102830 April 10, 2024.
16. Aprianto AD. The impact and issues of Artificial intelligence in Nursing 35. Cambridge Dictionary. Machine Learning. Cambridge University Press. 2024.
Science and Healthcare settings. SAGE Open Nurs. 2023;9:1–4. https://doi. https://dictionary.cambridge.org/dictionary/english/machine-learning.
org/10.1177/23779608231196847 Updated April 11, 2024.
17. Zhu JS, Ge P, Jiang C, Zhang Y, Li X, Zhao Z, et al. Deep-learning artificial intel- 36. Jeong GH. Artificial intelligence, machine learning, and deep learning in
ligence analysis of clinical variables predicts mortality in COVID-19 patients. women’s health nursing. Korean J Women Health Nurs. 2020;26(1):5–9.
JACEP Open. 2020;1:1364–73. https://doi.org/10.1002/emp2.12205 https://doi.org/10.4069/kjwhn.2020.03.11
18. Wataya T, Nakanishi K, Suzuki Y, Kido S, Tomiyama N. Introduction to deep 37. Ren Y, Yang Y, Chen J, Zhou Y, Li J, Xia R et al. A scoping review of deep
learning: minimum essence required the launch of research. JPN J RADIOL. learning in cancer nursing combined with augmented reality: the era of intel-
2020;38:907–21. https://doi.org/10.1007/s11604-020-00998-2 ligent nursing is coming. Asia Pac J Oncol Nurs. 2022;9:100135. https://doi.
19. Zhu T, Li K, Herrero P, Georgiou P. Deep learning for diabetes: a systematic org/10.1016/j.apjon.2022.100135
review. J Biomed Inf. 2021;25(7):2744–57. 38. Wang J, Liang Y, Cao S, Cai P, Fan Y. Application of Artificial Intelligence in Geri-
20. Siebert JN, Hartley MA, Courvoisier DS, Salamin M, Robotham L, Barazzone- atric Care: bibliometric analysis. J Med Internet Res. 2023;25:e46014. https://
Argiroffo C, Gervaix A, et al. Deep learning diagnostic and severity stratifica- doi.org/10.2196/46014
tion for interstitial lung diseases and chronic obstructive pulmonary disease 39. Adus S, Macklin J, Pinto A. Exploring patient perspectives on how they can
in digital lung auscultations and ultrasonography: clinical observational and should be engaged in the development of artificial intelligence (AI)
protocol case–control study. BMC Pulm Med. 2023;23:191. https://doi. applications in health care. BMC Health Serv Res. 2023;23:1163. https://doi.
org/10.1186/s12890-022-02255-w org/10.1186/s12913-023-10098-2
21. Zhang K, Fan Y, Long K, Lan Y, Gao P. Research hotspots and trends of Deep 40. Chhetri L, Shrestha OK. Use of Artificial Intelligence in Nursing. Thesis Social
Learning in critical Care Medicine: a bibliometric and visualized study. J Multi- and Health Care Services. University of Applied Sciences. 2023. https://
discip Healthc. 2023;16(2155–2166). https://doi.org/10.2147/JMDH.S420709 www.theseus.fi/bitstream/handle/10024/814764/Chhetri_Shrestha.
22. Shang Z. A Concept Analysis on the Use of Artificial Intelligence in nursing. pdf?sequence=2&isAllowed=y Updated April 15, 2024.
Cureus. 2021;13(5):e14857. https://doi.org/10.7759/cureus.14857 41. Albers M, Gobbens RJJ, Reitsma M, Timmermans OAAMJ, Nies HLGR. Learning
23. Walker LO, Avant KC. Strategies for theory construction in nursing. 6th ed. and innovation network in nursing: a concept analysis. Nurse Educ Today.
New York (US): Pearson; 2019. 2021;104:104988. https://doi.org/10.1016/j.nedt.2021.104988
24. Morse JM. Exploring the theoretical basis of nursing using advanced tech- 42. Benzinger L, Ursin F, Balke WT, Kacprowski T, Salloch S. Should Artificial Intel-
niques of concept analysis. ANS Adv Nurs Sci. 1995;17(3):31–46. https://doi. ligence be used to support clinical ethical decision-making? A systematic
org/10.1097/00012272-199503000-00005 review of reasons. BMC Med Ethics. 2023;24:48. https://doi.org/10.1186/
25. National Library of Medicine. (2024). Medical Subject Headings. Deep s12910-023-00929-6
Learning [MeSH term]. Retrieved from https://www.ncbi.nlm.nih.gov/ 43. Laacke S, Mueller R, Schomerus G, Salloch S. Artificial Intelligence, Social
mesh/?term=deep+learning Media and Depression. A New Concept of Health-Related Digital Autonomy.
26. National Library of Medicine. (2024). Medical Subject Headings. Artificial Intel- AM J Bioeth. 2021;21(7):4–20. https://doi.org/10.1080/15265161.2020.186351
ligence [MeSH term]. Retrieved from https://www.ncbi.nlm.nih.gov/mesh/ 5
D001185 44. Hwang YJ, Kim GH, Kim MJ, Nam KW. Deep learning-based monitoring
27. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. technique for real‐time intravenous medication bag status. Biomed Eng Lett.
The PRISMA 2020 statement: an updated guideline for reporting systematic 2023;13:705–14. https://doi.org/10.1007/s13534-023-00292-w
reviews. BMJ. 2021;372:n71. https://doi.org/10.1136/bmj.n71 45. Nashwan AJ, Abujaber A, Ahmed SK. Charting the Future: The Role of AI in
28. Dechter R. Learning while searching in constraint-satisfaction-problems. AAAI Transforming Nursing Documentation. Cureus. 2024;16(3):e57304. https://
Conference on Artificial Intelligence. 1986: 178––183. doi.org/10.7759/cureus.57304
29. Wang Y, Sohn S, Liu S, Shen F, Wang L, Atkinson EJ, et al. A clinical text clas-
sification paradigm using weak supervision and deep representation. BMC
Med Inf Decis Mak. 2019;19:1–13. https://doi.org/10.1186/s12911-018-0723-6
30. He Z, Tian S, Singh A, Chakraborty S, Zhange S, Lustria MLA, et al. A Publisher’s Note
machine-learning based Approach for Predicting older adults’ adherence to Springer Nature remains neutral with regard to jurisdictional claims in
technology-based cognitive training. Inf Process Manage. 2022;59:103034. published maps and institutional affiliations.
https://doi.org/10.1016/j.ipm.2022.103034