See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/380367827

Optimizing Doctor Availability and Appointment Allocation in Hospitals

through Digital Technology and AI Integration

Article in International Journal of Innovative Science and Research Technology · May 2024
DOI: 10.38124/ijisrt/IJISRT24APR1994

CITATION READS

1 487

5 authors, including:

Pramodd Komarneni Toshan Kumar

Chandigarh University Chandigarh University
2 PUBLICATIONS 1 CITATION 2 PUBLICATIONS 1 CITATION

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Toshan Kumar on 11 September 2024.

The user has requested enhancement of the downloaded file.

 OPTIMIZING DOCTOR AVAILABILITY AND
APPOINTMENT ALLOCATION IN HOSPITALS
THROUGH DIGITAL TECHNOLOGY AND AI
INTEGRATION
Pramodd Komarneni Toshan Kumar Kalakoti Pavan Kumar Narla
Dept. Of Computer Science and Dept. Of Computer Science and Dept. Of Computer Science and
Engineering Engineering Engineering
Chandigarh University, Chandigarh University, Chandigarh University,
Punjab Punjab Punjab

Sai Pujitha Alla Richitha Bomma

Dept. Of Computer Science and Dept. Of Computer Science and
Engineering Engineering
Chandigarh University, Chandigarh University,
Punjab Punjab

Abstract— Many patients miss their appointments all around the Based on case-specific outcome projections, the suggested
world and many of them don't even cancel at all or don't do so in time approach enables the automated handling of high-risk visits.
due to several reasons. In order to address the widespread issue of
The system was developed in conjunction with a classifier that
medical no-shows, this paper proposes a solution that involves
building a machine learning model utilizing patient datasets that are uses machine learning to identify chronic no-shows. Thus,
already available. This model will identify patterns and links between [1]this research employs a data set of 110,527 arrangement
various patient factors and the patients' propensity to miss records to develop, test, and coordinate an effective classifier.
appointments. As a result, based on their information, it is possible to The arrangement highlights documented in the logs include the
anticipate the chance of a patient appearing. Based on the Support [1]patient's ID, gender, lead time, age, clinic, area, health
Vector Machines classification technique, the machine learning model
benefits, pre-existing medical problem, and a hail indicating
created the solution predictive model. Effective healthcare services
are vital in today's fast-paced environment. This strategy aims to the fact that the quiet was reminded. The framework's
reduce the distance between patients and medical professionals by predictive modeling element learns sufficient from the
offering a workable and friendly solution. For certain medical information to provide precise expectations about non-
institutions, such as clinics and hospitals, this initiative makes it easier attendance. This is frequently achieved by incorporating the
for patients and customers to schedule doctor appointments online. technique's information into the preferred categorization
Using this technology, patients may easily browse a database of
strategy. As a consequence, the framework may use the
doctors' biographies, specializations, and availability. Even the day
and time of their choosing can be chosen for appointments. Each classifier component's anticipated result to overbook
patient's appointment request will be scheduled by this doctor's vacancies that will not be filled. This investigation investigates
appointment system and forwarded to the physician. The system and evaluates several commonly used machine learning
administrator will update the list of doctors, including their specialties, procedures in order to bring together the classifier aspect that
personal information, and system access credentials. Patients will look can create extremely precise and dependable forecasts so that
for a physician who specializes in their requirements by exploring the
the overall framework plan can appropriately manage no-
doctor's appointment system online. Before making their request, the
patient can browse the doctor's weekly schedule to choose a day and shows.
time that works best for them. Following that, the physicians have
access to all of their appointments as well as the patients' appointment The healthcare industry is always changing to meet the ever-
requests, which are prioritized according to their availability. It gives increasing needs of patients and providers in our fast-paced,
medical professionals a strong tool for successfully managing the technologically-driven society. A key component of this
schedules, which reduces administrative strain and ensures a positive
patient experience.
development is the Doctor Appointment System, a cutting-
edge and inventive solution made to make scheduling and
managing doctor visits easier. With so many advantages for
I. INTRODUCTION patients and healthcare providers, this system marks a major
The Appointment Scheduling system is presented in this paper. departure from traditional appointment scheduling techniques.
It allows people to plan appointments quickly and easily, and The Physician Appointment System streamlines the process of
it gives medical professionals in a hospital or clinic accessible scheduling visits with medical specialists by utilizing
and useful schedule monitoring, reporting, and management. technology. It seeks to do rid of issues like lengthy wait times,
overworked administrative staff, and misunderstandings that
are frequently related to appointment scheduling. It gives as the managing patient appointment system is
patients a user-friendly platform to obtain information about utilized to regulate and reduce the amount of time
doctors, their specializations, and the availability of patients must wait in the medical institution. Some
appointments in real time, empowering them to take charge of medical institutions do not have an appointment
their healthcare. system. As a result, it has a longer average patient
wait time than the medical institution that employs
Current availability data Patients can minimize wait times and the patient appointment system.
maximize the utilization of healthcare resources by choosing iv. Online Reservation Platform: [7]An online system
appointment times that work best for their schedules with the is often known as a web-based system. A website is
help of availability information. In addition to streamlining the a computer software that runs a webserver and
scheduling process, the doctor appointment booking system provides access to a collection of connected web
also increases patient satisfaction and boosts the productivity pages. A web is made up of web pages, also known
of medical staff. It improves accessibility, convenience, and as web sites. A system is made up of multiple
efficacy of healthcare as a result. interdependent components that work together to
achieve a single aim.
II. LITERATURE REVIEW v. Online appointment booking for outpatient care:
[8]One of the most pressing issues confronting the
We are currently introducing an interface that allows patients medical sector is the provision of high-quality and
and physicians to communicate. Its exceptional multi-node efficient medical services to patients with changing
administration improves communication between medical health needs.China's online medical services
experts and patients. The hospital's server nodes are freely business is flourishing, growing in part to the
accessible to patients. [1]In this context, patients can discuss country's rapid improvements in information and
their symptoms with physicians. Physicians may keep track of communication technology, as well as increased
and record persons who are scattered regionally, as well as Internet and mobile device usage.
provide appropriate diagnoses. Creating a new system that vi. Current Hospital Scheduling Programs:
would allow doctors to monitor and manage patient visits [9]Exponential entry arrival times were used in one
while customers could schedule them effortlessly online. In application that handled patient appointment
this example, patients book their appointments online based on scheduling. Due to the nature of appointment
the doctor's availability and their time limits. In contrast, the scheduling, this model is limited and assumes that
physicians' working hours may vary depending on the number the exponential arrival times could not be explicitly
of patients arriving during the day. validated by date. Because appointments are
scheduled in the future, the accurate call arrival
i. Waiting period: [2]Waiting time is simply the model will have a limited impact on metrics related
length of time that must pass after a request or to the duration between the call and the appointment
mandate is made for a certain activity to occur. The time. As a result, developing an appointment system
term "patient waiting time" refers to the time that functions well in the context of medical
between when a patient arrives at an outpatient clinic operations is tough. Consequently, the health centre's
and when they take their medicine. [3] It refers to the appointment provider can schedule a patient for a
total period between registration and a doctor's convenient time window on a certain day.
Consultation. There were two waiting periods: one vii. Appointment Postponement: [10]Every day that a
for the doctor's appointment and another for the patient attempts to schedule an appointment, the
medicine to be delivered. likelihood of them cancelling or failing to show up
ii. The Appointment System for Patients: [4]We are increases. Out of 5901 samples, 31% cancelled or did
currently introducing an interface that allows not show up for their planned doctor's visit. Most of
patients and physicians to communicate. Its these appointments are scheduled within a few days
exceptional multi-node administration improves of the request being received. The best course of
communication between medical experts and action in this case would be to encourage them to
patients. [5]Appointment system for patients The come as soon as possible or to book an appointment
patient appointment system or timetable of a at a time that is convenient for them...
healthcare institution was developed long ago. In
prior investigations, patient appointment RESEARCH GAPS
management resulted in simplified queue models and
largely unchanging scheduling situations. Integration with the Healthcare Ecosystem:
iii. Taking Care of the Patient Appointment System: 1. [8]The main barrier to e-healthcare systems attaining
[6]According to Dexter, a computer software known their full potential is the separation between them
 and the wider healthcare ecosystem. It is like physician compensation, the requirement to use
attempting to put together a puzzle with missing EMRs that impacts of various practice models, and
pieces and failing to understand the larger picture or the effect of generational differences.
deliver the best treatment possible. Here is a deeper 4. There is no evidence that they improve treatment in
look at the problem: circumstances where persons recognize the absence
2. Isolated data silos provide incomplete patient of proof but still think the plan of treatment is
records, hindering informed decision-making and acceptable.
leading to errors or missed diagnoses. Lack of cooperation and knowledge on data sharing:
3. Inefficiencies, such as repetitive testing, paperwork, [15] 1. In this broader environment, there is current
and lack of collaboration, can result in costly and lack of frameworks to guide data sharing.
time-consuming activities. 2. A lot of time is taking for ironing out of data
4. Difficult processes and lack of information can sharing.
irritate patients and doctors. 3. Number of things might affect how valuable
Health Equity and Accessibility: people believe an EMR to be, such as difficulties
1. [12]The biggest impediment to achieving health entering and extracting data, data sharing, and
equity and accessibility in e-healthcare systems is uncertainty about how Electronic Health Records
bridging the healthcare ecosystem gaps. The (EMR) will affect patient care.
fragmented environment of this gap has significant III. EXISTING SYSTEMS
impacts for vulnerable populations, including: To organizing and monitoring patient visits, the current doctor
2. The digital gap affects underprivileged populations, appointment system depends on manual procedures and in-
rural inhabitants, and those with disabilities by person contacts. Typically, patients schedule an appointment
limiting access to technology, internet and digital by calling the medical institution. Receptionists or
literacy skills. administrative personnel then manually check for open slots
3. Non-English speakers face language hurdles due to and make the reservation. [16]Patients are regularly sent
a lack of multilingual support. physical appointment cards as reminders, and appointment
4. Design errors can further marginalize those with data are frequently entered into paper books or records.
impairments. According to this approach, people must physically show up
5. Cost and affordability: Subscription fees and data for their appointments, wait in waiting areas, and check in at
costs pose financial challenges. the front desk. The typical appointment system may not scale
6. Historical prejudice may lead to scepticism in data well as medical facilities develop or as the number of patients
security policies. increases. [17] Maintaining paper records might become
New Data Entry and Extraction Procedures Must Be unfeasible as the human processes get more onerous. When it
Developed comes to postponing or cancelling appointments, traditional
1. Participants talked about the conflict between methods sometimes provide little flexibility. Patients who
entering data in the EMR in a standardized manner wish to reschedule their appointments may need to contact
and in free-text format. more than once, and this depends on staff availability.
2. Participants indicated a strong opinion that include Scheduling flexibility may be restricted, and access to patient
this data should not disrupt the duties of the PHC information is frequently restricted during the procedure.
physicians and medical professionals. Missed appointments, inefficient resource allocation, a hefty
3. We are not yet in a position to leverage the entire administrative burden for medical personnel, and scalability
interaction that free text permits for research and issues are some of the problems that this technique may cause.
evaluation or developing EMR policy. Although appointment management has always been done this
4. by creating additional time demands that interfere way, the introduction of digital technology has brought forth
with physicians' or healthcare practitioners' ability to more effective and patient- centred options that are becoming
provide patient care. increasingly common in contemporary healthcare systems.
Determine the Worth of Electronic
Medical Records(EMR): DISADVANTAGES OF EXISTING SYSTEM:
1. [14]Considering the uncertainty surrounding EMRs' Medical practitioners and consumers may experience various
effects on patient care, evaluating the relevance of drawbacks from the various doctor appointment systems now
EMRs to PHC practice was crucial. in use, regardless of whether they are digital or analog. Some
2. how EMRs affect patient outcomes, safety, typical drawbacks of these systems are as follows:
continuity of care, efficiency, patient and health
system value against usefulness for professionals
3. The effects of Find out the value of electronic
medical records (EMRs), especially with regard to
Restricted Accessibility: [18]Patients who need to make appointments with patients which included group levelling
appointments outside of regular business hours may find it and categorical info encoding. Then, for early testing, best
difficult to use traditional systems as they only permit show assessment, and model selection, this dataset was fed
scheduling during these hours. into a number of classification algorithms..
Rearranging: [19] Patients may find it difficult to reschedule DATASET USED: Medical Appointment No Shows. 110.527
or cancel appointments using traditional methods without medical visits have 14 related variables. The most crucial is
having to call them again or pay a fee. whether the patient shows up or does not show up for the
Taking Up Time: [20]Takes for time for administrative appointment.
personnel to schedule appointments manually, which can The dataset contains:
result in mistakes and inefficiencies. 2.1 Available data:
Resource Allocation: Scheduling appointments might be The collection offers detailed information on medical
difficult since facilities occasionally overbook personnel and appointments, including several attributes for each record. In
supplies for appointments that do not happen. addition to patient identity, appointment IDs, gender,
Communication Breakdown: The main means of scheduling and appointment dates, patient age, and
communication in traditional systems are phone conversations neighborhood data, there are indications for medical diseases
and in-person meetings. This can lead to missed calls, longer including diabetes, hypertension, alcoholism, and disability.
waiting periods, and communication breakdowns. 2.2 Dependent variable definition:
Ineffective Record-Keeping: Paper records, which are prone The term "the patient canceled an appointment close to the
to mistakes, loss, or damage, are frequently used in traditional scheduled time or did not show up according to a scheduled
systems for appointment scheduling appointment" is used to describe no-show behavior in previous
Data privacy: Whether using digital or traditional methods, studies. In the event of an appointment-related cancellation
there may be worries about patient data security and privacy, (such as one made on or before the scheduled appointment
particularly if strong security measures are not in place. day), outpatient appointments cannot be transferred to another
Convenience: Patients may find conventional methods less patient.
convenient since they need to schedule appointments in person 2.3 Independent variables:
or over the phone, which may be time-consuming and less Apart from age and gender, Appointment Day, SMS received,
patient friendly. and other predictive features are the main predictors in this
study.
IV. METHODOLOGY Modules are defined as follows; they are also referred to as
predictor variables.
The main components of the suggested system are a database,
• Booked Day: The day and hour the appointment was
a machine learning component. The database, application
booked.
logic, and user interface layers comprise the three-tier
• Date of Appointment
architecture used to build the system. The layered method
facilitates decoupling, which has several advantages such as • SMS_received: indicates if the patient received an
easier future implementation upgrades and changes, more SMS reminder for the appointment (0 for No, 1 for
understandable code, and enhanced flexibility. Yes).
• Scholarship: Determines if the patient is eligible for
1. USER INTERFACE LAYER:
a scholarship (0 for no, 1 for yes).
There are two client nodes—one for each kind of client—are 2.4 Requirement Analysis:
present in the user interface (patient or hospital administrator). We extensively investigated the existing appointment booking
The online application component is housed in the owner system to discover the essential required materials and features
status, whereas the smartphone app is located in the patient- of doctor appointment system with the help of AI. Medical
owner. A component on every client node allows users to settings rely on systems and processes. We found the most
communicate with the system. To register, schedule popular demands such comfortable appointment scheduling,
appointments, and access other services, patients utilize the on time access to physician’s conflict resolution, resource
smartphone app.The application's mobile server provides web management, and personalized user experiences.
interfaces to give capabilities using the mobile app. The 2.5 Data preprocessing:
hospital administrator uses the web interface to input • Missing Values: Check for null values in each feature
appointment hours, examine schedules, and information. To and determine how to handle them (e.g., imputation,
do these operations, the web application uses web interfaces deletion).
given by the app server. • Encoding Categorical Variables: Using one-hot
2. CLASSIFIER IMPLEMENTATION: encoding, convert categorical information such as
The ASIM system's prediction capability was created by pre- gender and neighbourhood characteristics into
processing there is a availability of datasets of doctor numerical representations.
 • Scale's numerical features: Scale numerical features for a parameter. To achieve comparable performance to that
such as patient age to ensure that they have similar obtained with the entire, balanced dataset, the number of
ranges, which can help some machine learning features in the dataset is also empirically decreased to the bare
algorithms work more effectively. minimum. The two types of feature reduction that are
examined are dimensionality reduction and feature selection,
• Feature engineering is Extract required features,
both of which have SK-learn library implementations. Feature
such as calculating wait periods between scheduling
selection, a feature reduction strategy, uses a parameter also
and appointment dates.
designated "K" to truncate the columns inside a dataset,
Develop additional features based on local characteristics such
keeping the K most significant/informative features.
as population density or socioeconomic status.
2.6 Feature Selection:
On the other side, dimensionality reduction which provide a
• Correlation Analysis: Determine the correlation
limited representation and summary of the data found in the
between each feature and the target variable (no-
original features. SK-Learn's Principal Component Analysis
show) to uncover potentially significant
(PCA) function is used in this research to do dimensionality
characteristics.
reduction. The number of principal components that are
• Feature relevance Ranking: In this we need to use the
desired after postdimensionality reduction is recorded in a
tree type data structures or classification such as
parameter called n_components.
decision tree, random forest.
• Dimensionality Reduction: If the dataset has a high
3. APPLICATION LAYER:
number of features, use techniques like PCA to
• ADMIN MODULE
decrease dimensionality while retaining the most
relevant information. • PATIENT MODULE
2.7 Data balancing: • DOCTOR MODULE
The distribution between ‘No-show’ and ‘Show’ records was
done using percentages showed a significant imbalance, with ADMIN MODULE: The login page allows the administrator
80% labeled as 'Show' and 20% as 'No-show'. A dataset to log in using their email address and password. The website's
logging patient attendance is predicted to show a significant administrator can handle all aspects of the site.
class imbalance, given the majority of medical visits are PATIENT MODULE: Patients may establish profiles,
attended while a minority are not. To address the class schedule appointments, view appointment history, and engage
imbalance in the dataset, we tested several under-sampling and with healthcare professionals.
oversampling strategies. DOCTOR MODULE: The doctor can log in using his or her
2.8 Model Selection: email and password. This module enables doctors to manage
In this stage of developing and testing the model, the subpart profiles, appointments, patient information, and offer medical
of ml algorithms needed to solve patient attendance prediction services.
is classification, which is a type of supervised learning. This is
because the records that were extracted from the Brazilian 3.1 : SOFTWARE USED:
dataset are labeled for the outcomes of show/no-show. In the
context of this work, classification and prediction are identical DJANGO: Built by professional developers, it removes
because the model under development will be used to classify most of the difficulty of web development, allowing you
show/no-show cases. To create supervised learning models to focus on building your app without having to waste a
that carry out categorization. lot of time for no reason. It is completely free
The algorithms outlined below were tested using the SK-Learn and open source.
API. MYSQL: A database is an organized combination of data.
• Decision Tree Classification MySQL is a popular open-source RDBMS for handling
• Linear Support Vector Machines (SVM) structured data. It plays a significant role in developing
dynamic online applications, content management
• Non-Linear Support Vector Machines (SVM)
systems, e-commerce platforms, and other technologies.
• Logistic Regression
MySQL's relational database structure uses Structured
• KNN Classification Query Language (SQL) to efficiently store, retrieve, and
The dataset balanced by the IHT method was employed in this manipulate data.
step of the model's development. In addition, every algorithm HTML: HTML is the standard language for producing
was subjected to a rigorous method of hyper-parameter tuning and organizing web content.HTML offers the
known as grid search, which is incorporated into the SKlearn fundamental structure and semantics of a web page.
library. This method determines the part of parameters given CSS: It is a style sheet language that specifies how a
an algorithm, a parameter grid and a scoring performance markup-generated page should appear and be styled. In
function that serves as a criterion for choosing the best value
 compared to HTML, it provides one additional
functionality. It is frequently used in combination with
HTML to change the look of graphical user interfaces and
internet pages. .
JAVA SCRIPT: For web scripting, JavaScript is the most
widely used language. Single-threaded, cross-platform,
lightweight, interpreted, compiled language with ease of
learning. On both the client and server sides, it is
extensively utilized in web development. It is crucial to
web browsers as a scripting language since it helps to
improve user experience by enabling content alteration of
web pages in real time.. JavaScript syntax is comparable Figure 2.Graph between SMS Received and Count
to other programming languages like Java and C, making
Patients are more likely to attend their appointment if
it quite simple to learn for people who are familiar with
they get an SMS reminder, as seen by the bar graph
programming fundamentals. A program's logic is defined above.
using variables, loops, conditional statements, functions,
and objects.

V. RESULTS AND DISCUSSION

A histogram depicting the ages distribution for the subjects at

the start of the research reveals the population's demographic
mix.The incidence of the ailment in various age groups is then
examined using gender-based analysis, which aids in treatment
planning. Appointment day analysis identifies trends in
attendance to help with schedule optimization. Attendance is
compared to assess the effectiveness of SMS reminders. The
effect of being awarded a scholarship on attendance is
examined. Neighbourhood dispersion has an impact on Figure 3.Graph between Scholarship received and count
resource distribution. Analysing appointment dates (The bar graph above indicates that although fewer persons
contributes to more effective scheduling. Finally, monthly data have gotten scholarships, it is clear that recipients of
for programs that are particularly targeted demonstrates scholarships are more prone than non-recipients to miss
variations in seas appointments.)

Figure 4.Piechart representing the distribution of neighbourhood

(The piechart above indicates that the majority of the
neighborhood has an 80% show rate. This suggests that this
Figure 1.Graph between Age distribution and Count characteristic would not be very useful when developing a
Individuals between the ages of 20 and 60 are probably model to identify the patient segment that is most likely to
interested in making appointments, based on the above attend a visit.Therefore, we are excluding this component
histogram. from our study.)
 appointments, with Tuesdays, Wednesdays, and Thursdays
being the most popular times of day.

Figure 5.Graph between Schedule day and count

The majority of patients are turning up on the day that they Figure 9.Feature Scaling using Lasso regression
are scheduled, according to the graph distribution. (Above graph displays lasso regression which determines
feature scaling)

Figure 6.Graph between Gender biased difference and

frequency
(Above graph indicates that women are more likely than
males to see the doctor.) It is evident from the graph above
that women are nearly twice as likely as males to see the Figure 10.Table represents Prediction model performance
doctor.
However, it works well for a specific age range.)

Figure 11.Displays Home Page of Patient Care Website

Figure 7.Graph between age and different diseases

(above graphs give information about patients)

Figure 1 2 . Displays Patient Module of Patient Care

Website
Figure 8.Graph between Appointment Day and count
As can be seen from the graph distribution above, days in a
week are when most appointments are made rather than
weekends. Mondays and Fridays are the least common days
for
 VI. CONCLUSION Journal of Advanced Trends in Computer Science and
Engineering, 2(4)
The System for Appointment Booking and Intuitive [6] Akinode, J. L., & Oloruntoba, S. A. (2017). Design
Management (ASIM) system utilized a classifier using and implementation of a patient appointment and
machine learning to detect patient no-shows. This study scheduling system. Department of Computer Science,
achieved an accuracy and F1-score of 80%, indicating Federal Polytechnic Ilaro Nigeria.
strong prediction ability. The study discusses how several [7] Song, J., Bai, Y., & Wen, J. (2018). Optimal
techniques were used to create and evaluate the presented appointment rule design in an outpatient department.
models. Models were evaluated on a dataset and compared IEEE Transactions on Automation Science and
using measures. To achieve the best outcomes from each Engineering, 16(1), 100-114
method, several grid search runs were used to evaluate [8] Edwards, T., & Sankaranarayanan, S. (2009,
various settings. The presence of the lead time feature in the November). Intelligent agent based hospital search &
dataset is crucial for correct results. Without it, classifier appointment system. In Proceedings of the 2nd
performance reduces by up to 30 %. Current methods rely International Conference on Interaction Sciences:
on telephone conversations and manual record-keeping, Information Technology, Culture and Human (pp.
resulting in time-consuming and error- prone operations. 561-567).
Digital appointment systems provide patients online
[9] Usharani, S., Prithivi, S., Sharmila, S., Bala, P. M.,
booking, real-time availability, and automatic reminders.
Kumar, T. A., & Rajmohan, R. (2021, July). Mobile
Real-time availability information enables patients to
Application for Doctor Appointment Scheduling. In
choose appointment times that best fit their schedules,
2021 International Conference on System,
reducing wait times and maximizing healthcare resources.
Computation, Automation and Networking (ICSCAN)
It not only cuts administrative expenses, but also enhances
(pp. 1-6). IEEE.
the patient experience through user-friendly interfaces, self-
service capabilities, and proactive care. [10] Sankarananrayanan, S., & Wani, S. M. A. (2014,
May). NFC enabled intelligent hospital appointment
The Medical Appointment Booking System streamlines
and medication scheduling. In 2014 2nd International
appointment scheduling, improves patient experience,
Conference on Information and Communication
increases healthcare professional efficiency, and optimizes
Technology (ICoICT) (pp. 24- 29). IEEE.
services. As a result, it improves healthcare accessibility,
convenience, and effectiveness. [11] Zhang, L., Xu, J., Vijayakumar, P., Sharma, P. K., &
Ghosh, U. (2022). Homomorphic encryption- based
VII .FUTURE SCOPE privacy-preserving federated learning in iot- enabled
healthcare system. IEEE Transactions on Network
Science and Engineering
The integration in alerts via email capabilities will improve
patient engagement and reduce missed appointments. AI will [12] Kaur, M., Singh, D., Kumar, V., Gupta, B. B., & Abd
also play a crucial role in enhancing the system. AI-powered El-Latif, A. A. (2021). Secure and energy efficient-
scheduling offers tailored reliable appointment based E-health care framework for green internet of
recommendations based on patient preferences and prior things. IEEE Transactions on Green Communications
appointment trends. and Networking, 5(3), 1223-1231.
[13] F. A.-T. Louisa Aiyeyika, “Appoinment System using
I. REFERENCES Artifical Intelligence Techniques,” International
Research Center for AI and IOT.
[1] F. A.-T. Louisa Aiyeyika, “Appoinment System
[14] Jin, Y., Wang, H., Chugh, T., Guo, D., & Miettinen,
using Artifical Intelligence Techniques,”
K. (2018). Data-driven evolutionary optimization: An
International Research Center for AI and IOT .
overview and case studies. IEEE Transactions
[2] Tsui, K. M., & Chan, S. C. (2012). Demand on Evolutionary Computation, 23(3), 442-458.
response optimization for smart home scheduling
[15] Humayun, M., Safdarian, A., Degefa, M. Z., &
under real-time pricing. IEEE Transactions on Smart
Lehtonen, M. (2014). Demand response for
Grid, 3(4), 1812-1821.
operational life extension and efficient capacity
[3] Jin, Y., Wang, H., Chugh, T., Guo, D., & Miettinen, utilization of power transformers during
K. (2018). Data-driven evolutionary optimization: contingencies. IEEE Transactions on Power Systems,
An overview and case studies. IEEE Transactions 30(4), 2160-2169.
on
[16] Akinode, J. L., & Oloruntoba, S. A. (2017). Design
Evolutionary Computation, 23(3), 442-458.
and implementation of a patient appointment and
[4] Humayun, M., Safdarian, A., Degefa, M. Z., & scheduling system. Department of Computer Science,
Lehtonen, M. (2014). Demand response for Federal Polytechnic Ilaro Nigeria.
operational life extension and efficient capacity
[17] Edwards, T., & Sankaranarayanan, S. (2009,
utilization of power transformers during
November). Intelligent agent based hospital search &
contingencies. IEEE Transactions on Power
appointment system. In Proceedings of the 2nd
Systems, 30(4), 2160-2169.
International Conference on Interaction Sciences:
[5] Symey, Y., Sankaranarayanan, S., & binti Sait, S. Information Technology, Culture and Human (pp.
N. (2013). Application of smart technologies for 561-567).
mobile patient appointment system. International
[18] Usharani, S., Prithivi, S., Sharmila, S., Bala, P. M.,
 Kumar, T. A., & Rajmohan, R. (2021, July). Mobile
Application for Doctor Appointment Scheduling. In
2021 International Conference on System,
Computation, Automation and Networking
(ICSCAN) (pp. 1-6). IEEE
[19] D. Y.Huang, “Patient No-Show Predictive Model
Development usinf Multiple Data Sources for an
Effective Overbbooking Approach,” Applied
Clinical Informatics, vol. 5, no. 3, pp. 836-860,
2014.
[20] Zhang, L., Xu, J., Vijayakumar, P., Sharma, P. K.,
& Ghosh, U. (2022). Homomorphic encryption-
based privacy-preserving federated learning in iot-
enabled healthcare system. IEEE Transactions on
Network Science and Engineering.
[21] N. G. X. Xingwei Pan, “Appoinment scheduling
and real-time sequencing strategies for patient
unpunctuality,” Operational Research, vol. 295, no.
1, pp. 246-260, 2021.
[22] Y. S. M. Suresh Cloud & Ubiquitous, pp. 98-103,
2013.
[23] D. D. ,. J. Ying Zhou, Material Science and
Engineering, vol. 439, no. 3, 2018.

View publication stats