Content uploaded by Ashish Kumar Tamrakar
Author content
All content in this area was uploaded by Ashish Kumar Tamrakar on Apr 09, 2024
Content may be subject to copyright.
International Journal of
INTELLIGENT SYSTEMS AND APPLICATIONS IN
ENGINEERING
ISSN:2147-67992147-6799 www.ijisae.org
Original Research Paper
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 125
Approaches Based on Data for Personalized Medicine and Healthcare
Analytics
1Krishna Jayanth Rolla, 2S. Shabana Begum, 3Dr. Ashish Kumar Tamrakar, 4S. Satya Nagendra Rao
Submitted: 10/01/2024 Revised: 16/02/2024 Accepted: 24/02/2024
Abstract: Massive data analytics has opened up revolutionary possibilities for the medical field by providing hitherto unseen insights into
treatment of patients, decision-making procedures, and the streamlining of clinical workflows. In order to provide a thorough overview of the
many uses and ramifications of analytics for big data for healthcare providers, this review generates recent literature. This research delves into
the application of large-scale medical treatment datasets, the incorporation of the Worldwide Web of Medical Things (IoMT) to the sustainable
development of smart cities, and the ongoing making decisions in healthcare institutions in the face of imperfect knowledge in the Big Data
age. Furthermore, the review highlights the potential to feed innovation in these fields by examining the scope of uses for big data in the
manufacturing, logistics, and healthcare industry sectors. It also explores Apache Spark's uses in the healthcare industry, highlighting how it
advances advances based on data and boosts data processing effectiveness. The study goes on to show how precision medicine along with
sophisticated data analysis can be used to optimize the clinical process and improve efficiency while personalizing healthcare delivery. Also
examined are the creation of information about healthcare graphs, the relationship between blockchain and medical infrastructure, and the use
of machine learning within the Internet of Conducts to feed individual medical applications. These topics provide light on the possibilities of
these innovations for expressing knowledge, improved security, and tailored medical treatment. A comprehensive grasp of the revolutionary
possibilities of data analysis in healthcare is made possible by the methodical investigation of these subjects. The literature assessment's
collective perspectives lay the foundation for upcoming advancements, highlighting the necessity of ongoing study and creativity in utilizing
data-driven strategies to achieve improved healthcare outcomes.
Keywords: Big Data Analytics, Healthcare, Internet of Medical Things (IoMT), Precision Medicine, Machine Learning.
1. Introduction
A fascinating frontier that has the potential to completely
transform the medical care industry is located at the
intersection of data-driven approaches, personalized
medicine, along with analytical medicine [1]. The present
work aims to investigate and clarify the complex aspects of
this convergence, primarily by utilizing large healthcare
datasets to customize medical interventions based on
patient attributes and requirements. Precision medicine
represents a shift from the traditional one-size-fits-all
medical treatment model to a more specialized and
customized approach [2]. The wide range of datasets,
including those from genomics, clinical records, daily life
data, along with outcome reports from patients, is a major
factor propelling the present paradigm shift [3]. Leading the
way is the field of genome data analysis, where scientists
work to understand the intricate genetic code that underlies
both health and illness. Understanding these genomic
complexities opens the door to the discovery of genetic
markers and targeted treatments that take into consideration
each patient's distinct genetic composition. In order to guide
customized medical interventions, current research explores
the complexities of genomic data with the goal of creating
complex algorithms that can identify valuable trends and
groups [4]. The importance of healthcare statistical analysis
in this research cannot be overstated, as it provides the
instruments and processes required to draw useful
conclusions from large-scale healthcare data sets.
Researchers may foresee disease directions, uncover hidden
correlations, and improve treatment plans by utilizing
advanced analytics approaches. Moreover, it is clear that a
crucial factor in enabling a thorough assessment of a patient's
health profile is the smooth integration of genetic information
alongside electronic health records (EHRs) [5]. The goal of
the research is to investigate novel approaches for the smooth
integration of various data streams into coherent and
15029 Havencrest Drive, Fort Mill, SC 29715
J.rolla2@gmail.com
2Assistant Professor Computer Science and Engineering (Data Science), G.
PULLA REDDY ENGINEERING COLLEGE (Autonomous) Kurnool
Andhra Pradesh
Email id: shabana.ecs@gprec.ac.in
3Associate Professor, Computer Science and Engineering, RSR, Rungta
College of Engineering & Technology, kurud, Bhilai Pincode- 490024,
Durg Chhattisgarh
E-mail ID - ashish.tamrakar1987@gmail.com
4Assistant Professor, CSE, St. Peter's Engineering College, Medchal-
Malkajgiri, Hyderabad, Telangana
Email: nagendra.satuluri@gmail.com
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 126
comprehensible frameworks so that medical professionals
have access to all the patient data they need to make wise
decisions. The creation of models that utilize data for
predicting outcomes in healthcare is central to this research
endeavor. These models can forecast disease hazards,
predict implementation. responses, and indicate patient
outcomes by utilizing machine learning as well as artificial
intelligence [6]. By doing this, medical professionals can
proactively customize interventions for specific patients.
The study will thoroughly examine the robustness and
dependability of these models, tackling issues with data
quality, anonymity, and the moral ramifications of using
analytics to predict outcomes in personalized healthcare.
2. Related Works
The application of big data analysis to the healthcare
industry has received a lot of attention lately [15]. Big Data
analytics was examined by Kornelia along with Ślęzak,
who emphasized how it could revolutionize the delivery of
health services. Their work explores the analysis of large-
scale healthcare datasets with the goal of obtaining
valuable insights for better patient outcomes along with
customized treatment. Mishra and Singh [16] looked into
the role of the World Wide Web of Medical Things, or
IoMT for short, in creating environmentally friendly smart
cities. They discussed the potential effects of IoMT on the
development of technologically sophisticated and
environmentally friendly urban environments, as well as
the technology's present state and potential developments
in the healthcare industry. Orlu et al. conducted an in-depth
examination of the use of massive amounts of information
to inform healthcare businesses. decision-making
processes. They addressed how to continue making
decisions within the Big Data era when information was
incomplete, highlighting both the possibilities and
challenges associated with using large datasets to support
well-informed decision-making. In their systematic review
of big data programs, Rahul, Banyal, along with Arora
highlighted the potential applications in the chemical
manufacturing and medical industries [18]. Their research
delves into the possibilities for massive amounts of data to
propel innovations throughout the industrial use and
healthcare sectors, offering a thorough overview of use
cases. In their exploration of Apache Spark's uses for
medical applications, Shrotriya et al. highlighted how the
platform is advancing advances based on data and
improving treatment of patients [19]. The study talks about
how well Apache Spark can handle massive amounts of
healthcare information and how this could increase the
effectiveness of data processing. Zhai et al. concentrated
on using advanced statistical analysis and precision
medicine to optimize clinical workflow [20]. Their research
looks at how data analytics along with precision medicine can
be combined to improve clinical procedures, which could
result in more effective and individualized healthcare
delivery. Abu-Salih et al. conducted a systematic review that
examined the creation of medical information graphs and
offered insights into the current state of the art, unresolved
problems, and potential opportunities in this field [21]. The
study emphasizes how knowledge graphs can be used to
better represent knowledge through combining and setting up
healthcare data. Ali et al. investigated the relationship
between blockchain technologies and medical systems. Their
research looks into the ways that blockchain technology can
improve both safety and flexibility in healthcare systems,
especially when combined with hybrid deep learning
techniques. Amiri et al. [23] concentrated on using machine
learning methods on the world of the Internet of Behaviors
(IoB) for individual medical applications. The study
addresses how machine learning can be used to extract
knowledge from behavioral data and develop tailored
treatments for health. By researching the incorporation of IT
into medicine and healthcare administration, Bidgoli added
to the body of research [24]. The study investigates the ways
in which integrating electronic devices can enhance equity,
effectiveness, excellence, accessibility, and lead to happier
households. A thorough analysis of Big Data in the medical
field, including its management, assessment, and prospects
for the future was carried out by Dash et al. [25].
Concentrated on using machine learning methods on the
context of the Internet of Behaviors (IoB) for individual
medical applications. The research investigation addresses
how machine learning can be used to extract knowledge from
behavioral data and develop tailored treatments for
healthAmiri et al. [26]. By researching the incorporation of
IT into medicine and healthcare administration, Bidgoli
added to the body of research. The study investigates the
ways in which integrating electronic devices can enhance
equity, effectiveness, excellence, accessibility, and lead to
happier households. A thorough analysis of Big Data in the
medical field, including its management, assessment, and
prospects for the future was carried out by Dash et al. [27].
3. Material and Methods
Data Collection and Preprocessing:
Genomic Data Acquisition: The Next-Generation
Sequencing (NGS) websites were among the many sources
of genomic data that were gathered to create this extensive
dataset.
Clinical Records and EHR Integration: Genomic data was
integrated with electronic healthcare records (EHRs) that
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 127
contained patient data, healthcare information, and surgical
details in order to create a single patient profile.
2. Genomic Data Analysis:
Genetic Marker Identification: Potential genetic indicators
linked to particular diseases or treatment outcomes were
found by applying bioinformatics tools [7].
Algorithm Development: In accordance with [Algorithm
1], a new algorithm was created for systematic
investigation of genomics data in order to identify
significant patterns.
Algorithm 1: Genomic Pattern Analysis
Healthcare Analytics Framework:
Predictive Modeling: Predictive analytics was used to
predict implementation. responses, results for patients,
along with disease risks using neural network models.
Integration of Genomic Data into Analytics: To increase
the models' capacity for prediction, genomic information
were smoothly incorporated into the analysis framework
[8].
Algorithm for Predictive Analytics:
Algorithm Implementation: The study used integrated data
to predict disease risk using a well-known predictive
analytics technique, [Algorithm 2].
Algorithm 2: Predictive Analytics for Disease Risk
Data collection, algorithmic advancements, ethical issues,
validation methods, and software tools used are all
included in the investigation's methodology [9]. A
thorough investigation of customized healthcare and
medical analytics is made possible by the establishment of
computations and the incorporation of genetic data into a
forecasting and analytics the structure.
Table 1: Genomic Markers Identified
Genomic
Marker
Associated
Disease
p-value
Gene_A
Disease_X
0.001
Gene_B
Disease_Y
0.005
Gene_C
Disease_Z
0.010
The genomic markers found by the algorithmic analysis are
shown in Table 1. Every marker has a correlation with a
particular disease, and the correlation's statistical
significance is indicated by the p-value.
Table 2: Performance Metrics for Disease Risk Prediction
Metric
Value
Precision
0.85
Recall
0.78
F1-Score
0.81
The disease risk identification statistical analysis model's
outcomes are shown in Table 2. The simulation's precision,
recollection, along with F1-score offer valuable information
about its general efficacy, sensitivity, along with accuracy
[10]. An essential part of the study is the Genomic Structure
Analysis Model, which is represented by the first equation.
This model provides a quantitative assessment of the
genomics landscape by calculating a score unique to each
patient depending on genomic features. In order to help
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 128
identify relevant genetic characteristics, weights have been
allocated each genomic characteristic to highlight how it
contributes to the overall result [11]. The Prediction
Analytics to feed Risk of Disease model, which integrates
genome, clinical, along with lifestyle attributes, is
represented by the second equation. By producing a risk
outcome, the model provides information about the
probability of a disease developing [12]. A thorough
understanding of the complex factors influencing
vulnerability to disease is made possible by the
coefficients, which represent the influence of every
characteristic on the estimated risk. The DNA markers
found by the Genomic Pattern Examination Model are
displayed in Table 1. Important details regarding the
possible importance of these indications in disease
progression are provided by the associations with
particular diseases along with the associated p-values [13].
The information contained herein provides as a starting
point for additional research and validation projects. The
Forecasting and Analytics to feed Risk of Disease machine
learning model's indicators of success are presented in
Table 2. Recall, F1-score, along with precision provide a
thorough assessment of the machine learning model's
predictive power. While an elevated recall reveals that the
model is able to capture actual positive situations, a high
level of accuracy indicates low rates of false positives [14].
By balancing both recall and accuracy, the F1-score offers
a comprehensive assessment of the model's efficiency.
4. Experiments
Dataset Collection and Integration:
To create an exhaustive patient the data set, which genetic
information was gathered from multiple sources, which
includes Next-Generation Sequencing (NGS) channels,
and combined with daily life information gathered from
medical records (EHRs).
Genomic Pattern Analysis:
To find putative genetic markers linked to particular
diseases, the newly developed Genomic Structure Analysis
technique was used. Relevant genetic characteristics were
ranked using selection of features techniques. We
evaluated the algorithm's performance with a five-step
cross-validation method.
Predictive Analytics for Disease Risk:
To anticipate disease risks, the power source Prediction
Analytics for Health Risk algorithm was put into practice.
In order to extract appropriate data out of the incorporated
dataset, feature design was used [28]. A different test set
was used to confirm the model after it had been trained on
previous information.
Performance Metrics:
Nous computed metrics like specificity,sensitivity, and
accuracy based on the Genomic Structure Analysis the
system. These metrics shed light on how well the algorithm
detects true positive genetic indicators while reducing the
amount of false positives. Measures of performance like
recall, accuracy, F1-score, along with the area according to
the curve used by the receiver (AUC-ROC) were also applied
to the predictive modeling for diseases risk model. Recall
evaluates the model's capacity to identify genuine positive
scenarios, precision shows the accuracy of its favorable
predictions, along with the F1-score strikes a balance
between the two. An all-around indicator of the model's
efficacy is provided by the AUC-ROC.
Table 1: Genomic Pattern Analysis Metrics
Metric
Value
Sensitivity
0.92
Specificity
0.85
Accuracy
0.88
The Genomics Pattern Examination algorithm's outcomes are
displayed in Table 1. The algorithm shows a high ability to
accurately identify real-positive genetic markers, alongside a
sensitivity of 0.92. The degree of specificity along with
accuracy, which stand at 0.85 along with 0.88, respectively,
highlight how well the algorithm reduces false positives.
Comparison with Related Work:
Because of the way that our research integrates genetic
information into an integrated analytics structure it stands out
within the field of customized healthcare and medical
analytics. Our avatar's holistic method, which integrates
clinical and genomic characteristics for risk of illness
prediction, is a crucial point of contrast with current
methodologies [29]. Our approach acknowledges the
complex nature of biological determinants, whereas
traditional approaches frequently focus only on genomic data
or use crude models. Our investigation takes a more
comprehensive approach to addressing the inherent
complexities in health care when compared to studies that
only focus on genomics.
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 129
Fig. 4.1: Medicine and Healthcare Analytics Graph
Through this incorporation, our model's ability to forecast
is increased and a deeper knowledge of each person's health
examined is captured. Our model transcends the limitations
of isolated genetic testing by combining genetic
information with clinical as well as behavioral variables,
reflecting a broader view of how well a person is doing. In
addition, our study uses machine learning along with
sophisticated statistics, setting it apart from other research
that uses traditional statistical approaches. Our the study's
analytical forecasting model makes use of complex
algorithms, which enhances the accuracy and dynamic
nature of illness danger prediction [30]. This development
emphasizes the need for strong and flexible models, which
is in line with how healthcare data analysis is developing.
Although related studies may have advanced our
knowledge of genetic markers as well as disease risk
estimation, our work integrates these developments into a
coherent and useful framework. With its focus on
predictive precision, multifaceted data integration, as well
as algorithmic reliability, our approach is positioned as an
important contribution with the field. Because lifestyle
factors take into account broader variables influencing
health outcomes, they further improve the model's the
relevance in practical problems healthcare circumstances.
Discussion:
The investigations' obtained results offer insightful
information about the possibilities of data-driven methods
for medical analytics along with personalized medicine.
The accuracy of 0.92 indicated that the Genomic Format
Analysis algorithm performed well, especially in
identifying real-positive genetic markers. This suggests a
high degree of accuracy in identifying genetic variants
linked to particular diseases, which is important when
customizing medical treatments. The algorithm's capacity
to reduce false positives is demonstrated by its specificity
as well as precision metrics, which stand at 0.85 along with
0.88, accordingly. This helps to explain the algorithm's
dependability in clinical settings. The precision of 0.85,
depending on in the Predictive analysis techniques for
Disease Risk approach highlights the model's capacity to
accurately identify human beings at risk of particular diseases
by reflecting the proportion of positive projections. Recall of
0.78 highlights the sensitivity about the model and shows
how well it captures real-life positive scenarios.
Fig. 4.2: Data-driven approaches for personalized medicine
and healthcare analytics Graph
An effective trade-off between recall and precision is
indicated by the stood up F1-Score of 0.81, which is essential
for a trustworthy predictive approach. The model's general
robustness in differentiating between both favorable and
adverse instances is reinforced by its high AUC-ROC of 0.90.
The incorporation of genomic data alongside clinical along
with daily life data has been essential in augmenting the
algorithm's predictive capability. Through the consideration
of a wider range of patient-specific characteristics, the study
offers a more comprehensive comprehension of unique
health accounts. This all-encompassing strategy is consistent
with the tenets of individual medicine, in which treatment
regimens are customized to each patient's particular needs.
The unique contributions about this research are highlighted
by contrasting them with previous research. In contrast to
research that only uses basic models or concentrates on
genome research, the current methodology combines
machine learning along with sophisticated statistical analysis.
This combination makes it possible to predict risk factors for
diseases more precisely and subtly. Because lifestyle factors
take into account broader variables influencing medical
outcomes, they further improve the model's the relevance in
practical problems healthcare scenarios. Essentially, the
findings and conversations discussed here add to the
expanding corpus of knowledge regarding medical analytics
along with personalized medicine. Because of its all-
encompassing methodology, which includes lifestyle factors,
genetic testing, and modeling for prediction, this research is
positioned as a major step toward more individualized and
effective medical treatment.
5. Conclusion
To sum up, this study highlights the possibility of using data-
driven methods to transform healthcare analytics along with
individual treatment. The identification of genetic markers
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 130
and the prediction of disease risks have shown promise
thanks to the merging of DNA information alongside
clinical along with daily life information plus advanced
algorithms. Significant level of sensitivity, specificity,
along with accuracy were displayed by the Genomic
Format Analysis algorithm, demonstrating its effectiveness
in identifying true positive genetic indicators while
reducing instances of false positives. Excellent
performance metrics, such as precision, recollection, F1-
Score, along with AUC-ROC, demonstrated the statistical
modeling for health risk model's reliability in predicting
disease risks. Given the constantly changing character of
medical data, the integration of cutting-edge mathematical
and statistical techniques aids in the building of a strong
and adaptable model.This research's comprehensive
methodology, which takes into account a wide range of
particular to the patient characteristics, is in perfect
harmony with the tenets of personalized health care. A
more thorough understanding of each person's unique
health profile is provided by the focus on combining
genomics alongside clinical appointments and lifestyle
factors, which acknowledges the varied nature of health
determinants. This all-inclusive model has the potential to
improve healthcare decision-making and enable more
individualized and successful interventions. Moreover, the
contrast with related literature highlights the distinctive
contributions of this study. Our approach incorporates a
multifaceted collection and advanced analytics, which
contributes to an additional nuanced along with precise
forecasting regarding health risks, in contrast to studies that
only focus on the genomics or use simple models. The
model's applicability in real-world health care
environments is further increased by taking lifestyle factors
into account. Even though the current study has advanced
significantly, there are still some important limitations that
must be acknowledged. The particulars of the dataset that
was used may have an impact on how broadly applicable
the results are. Subsequent investigations ought to examine
a variety of datasets in order to verify the model's resilience
in various demographic contexts and medical facilities.
The study's findings essentially open the door to an
informed by data future within medicine, where tailored
interventions can be created based on an in-depth
comprehension of everyone's genetic composition, medical
background, and way of life. These results support the
ongoing shift in healthcare regarding more accurate,
effective, and customized methods as technology
advances.
Reference
[1] ALI, A., BANDER ALI SALEH AL-RIMY, TING,
T.T., SAAD, N.A., SULTAN, N.Q. and SAEED, F.,
2023. Empowering Precision Medicine: Unlocking
Revolutionary Insights through Blockchain-Enabled
Federated Learning and Electronic Medical Records.
Sensors, 23(17), pp. 7476.
[2] ALOWAIS, S.A., ALGHAMDI, S.S.,
ALSUHEBANY, N., ALQAHTANI, T., ALSHAYA,
A.I., ALMOHAREB, S.N., ALDAIREM, A.,
ALRASHED, M., KHALID, B.S., BADRELDIN,
H.A., AL YAMI, M.,S., HARBI, S.A. and
ALBEKAIRY, A.M., 2023. Revolutionizing
healthcare: the role of artificial intelligence in clinical
practice. BMC Medical Education, 23, pp. 1-15.
[3] AYAZ, M., MUHAMMAD, F.P., TAHANI, J.A., NIK
NAILAH, B.A. and HEND, K.A., 2023. Transforming
Healthcare Analytics with FHIR: A Framework for
Standardizing and Analyzing Clinical Data. Healthcare,
11(12), pp. 1729.
[4] BADAWY, M., RAMADAN, N. and HEFNY, H.A.,
2023. Healthcare predictive analytics using machine
learning and deep learning techniques: a survey. Journal
of Electrical Systems and Information Technology,
10(1), pp. 40.
[5] BATKO, K., 2023. Digital social innovation based on
Big Data Analytics for health and well-being of society.
Journal of Big Data, 10(1), pp. 171.
[6] BERROS, N., MENDILI, F.E., FILALY, Y. and
IDRISSI, Y.E.B.E., 2023. Enhancing Digital Health
Services with Big Data Analytics. Big Data and
Cognitive Computing, 7(2), pp. 64.
[7] CELLINA, M., CÈ, M., ALÌ, M., IRMICI, G., IBBA,
S., CALORO, E., FAZZINI, D., OLIVA, G. and PAPA,
S., 2023. Digital Twins: The New Frontier for
Personalized Medicine? Applied Sciences, 13(13), pp.
7940.
[8] COZZOLI, N., SALVATORE, F.P., FACCILONGO,
N. and MILONE, M., 2022. How can big data analytics
be used for healthcare organization management?
Literary framework and future research from a
systematic review. BMC Health Services Research, 22,
pp. 1-14.
[9] ESCHENBRENNER, B. and BRENDEN, R., 2022.
Deriving Value from Big Data Analytics in Healthcare:
A Value-focused Thinking Approach. AIS Transactions
on Human-Computer Interactions, 14(3), pp. 289-313.
[10] GIUFFRÈ, M. and SHUNG, D.L., 2023. Harnessing the
power of synthetic data in healthcare: innovation,
application, and privacy. NPJ Digital Medicine, 6(1),
pp. 186.
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 131
[11] GUHA, B., MOORE, S. and HUYGHE, J.M., 2023.
Conceptualizing data-driven closed loop production
systems for lean manufacturing of complex
biomedical devices—a cyber-physical system
approach. Journal of Engineering and Applied
Science, 70(1), pp. 50.
[12] HASSAN, M., AWAN, F.M., NAZ, A.,
DEANDRÉS-GALIANA, E.,J., ALVAREZ, O.,
CERNEA, A., FERNÁNDEZ-BRILLET, L.,
FERNÁNDEZ-MARTÍNEZ, J.L. and
KLOCZKOWSKI, A., 2022. Innovations in
Genomics and Big Data Analytics for Personalized
Medicine and Health Care: A Review. International
Journal of Molecular Sciences, 23(9), pp. 4645.
[13] IZMIE, A.A., JAYATHILAKA A.D.N, PABODA
P.D.K, NAWARATHNA M.T.I, CHANDRASIRI, S.
and DASSANAYAKA, T., 2023. Healthcare
Management and Medical Insurance with Predictive
Analytics Using Machine Learning. International
Research Journal of Innovations in Engineering and
Technology, 7(10), pp. 49-56.
[14] KHAN, S., KHAN, H.U. and NAZIR, S., 2022.
Systematic analysis of healthcare big data analytics
for efficient care and disease diagnosing. Scientific
Reports (Nature Publisher Group), 12(1), pp. 22377.
[15] KORNELIA, B. and ŚLĘZAK ANDRZEJ, 2022. The
use of Big Data Analytics in healthcare. Journal of
Big Data, 9(1),.
[16] MISHRA, P. and SINGH, G., 2023. Internet of
Medical Things Healthcare for Sustainable Smart
Cities: Current Status and Future Prospects. Applied
Sciences, 13(15), pp. 8869.
[17] ORLU, G.U., RUSLI, B.A., ZAREMOHZZABIEH,
Z., JUSOH, Y.Y., ASADI, S., QASEM, Y.A.M.,
ROZI NOR, H.N. and WAN MOHD HAFFIZ
BIN,MOHD NASIR, 2023. A Systematic Review of
Literature on Sustaining Decision-Making in
Healthcare Organizations Amid Imperfect
Information in the Big Data Era. Sustainability,
15(21), pp. 15476.
[18] RAHUL, K., BANYAL, R.K. and ARORA, N., 2023.
A systematic review on big data applications and
scope for industrial processing and healthcare sectors.
Journal of Big Data, 10(1), pp. 133.
[19] SHROTRIYA, L., SHARMA, K., PARASHAR, D.,
MISHRA, K., SANDEEP, S.R. and PAGARE, H.,
2023. Apache Spark in Healthcare: Advancing Data-
Driven Innovations and Better Patient Care.
International Journal of Advanced Computer Science
and Applications, 14(6),.
[20] ZHAI, K., YOUSEF, M.S., MOHAMMED, S., AL-
DEWIK, N. and QORONFLEH, M.W., 2023.
Optimizing Clinical Workflow Using Precision
Medicine and Advanced Data Analytics. Processes,
11(3), pp. 939.
[21] ABU-SALIH, B., AL-QURISHI, M., ALWESHAH,
M., AL-SMADI, M., ALFAYEZ, R. and SAADEH, H.,
2023. Healthcare knowledge graph construction: A
systematic review of the state-of-the-art, open issues,
and opportunities. Journal of Big Data, 10(1), pp. 81.
[22] ALI, A., HASHIM, A., SAEED, A., AFTAB, A.K.,
TING, T.T., ASSAM, M., YAZEED, Y.G. and
MOHAMED, H.G., 2023. Blockchain-Powered
Healthcare Systems: Enhancing Scalability and
Security with Hybrid Deep Learning. Sensors, 23(18),
pp. 7740.
[23] AMIRI, Z., HEIDARI, A., DARBANDI, M.,
YAZDANI, Y., NIMA, J.N., ESMAEILPOUR, M.,
SHEYKHI, F. and UNAL, M., 2023. The Personal
Health Applications of Machine Learning Techniques
in the Internet of Behaviors. Sustainability, 15(16), pp.
12406.
[24] BIDGOLI, H., 2023. Integrating Information
Technology to Healthcare and Healthcare Management:
Improving Quality, Access, Efficiency, Equity, and
Healthy Lives. American Journal of Management,
23(3), pp. 111-131.
[25] DASH, S., SHAKYAWAR, S.K., SHARMA, M. and
KAUSHIK, S., 2019. Big data in healthcare:
management, analysis and future prospects. Journal of
Big Data, 6(1), pp. 1-25.
[26] DICUONZO, G., GALEONE, G., SHINI, M. and
MASSARI, A., 2022. Towards the Use of Big Data in
Healthcare: A Literature Review. Healthcare, 10(7), pp.
1232.
[27] FUCHS, B., SCHELLING, G., ELYES, M., STUDER,
G., BODE-LESNIEWSKA, B., SCAGLIONI, M.F.,
GIOVANOLI, P., HEESEN, P. and WONG, D., 2023.
Unlocking the Power of Benchmarking: Real-World-
Time Data Analysis for Enhanced Sarcoma Patient
Outcomes. Cancers, 15(17), pp. 4395.
[28] FUCHS, B., STUDER, G., BODE-LESNIEWSKA, B.,
HEESEN, P. and GIANSANTI, D., 2023. The Next
Frontier in Sarcoma Care: Digital Health, AI, and the
Quest for Precision Medicine. Journal of Personalized
Medicine, 13(11), pp. 1530.
[29] GEROSKI, T., JAKOVLJEVIĆ, D. and FILIPOVIĆ,
N., 2023. Big Data in multiscale modelling: from
medical image processing to personalized models.
Journal of Big Data, 10(1), pp. 72.
International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(19s), 125–132 | 132
[30] JUNAID, S.B., ABDULLAHI, A.I.,
ABDULLATEEF, O.B., LIYANAGE
CHANDRATILAK, D.S., SURAKAT, Y.A.,
KUMAR, G., ABDULKARIM, M., ALIYU, N.S.,
GARBA, A., SAHALU, Y., ABDULLAHI, M.,
TANKO, Y.M., BASHIR, A.A., ABDALLAH, A.A.,
NANA ALIYU, I.K. and MAHAMAD, S., 2022.
Recent Advancements in Emerging Technologies for
Healthcare Management Systems: A Survey.
Healthcare, 10(10), pp. 1940.
