A Study towards Supervised Learning Techniques for a Well-Predictive Modelling Utilising Electronic Health Record Data

International Journal of Emerging Science and Engineering (IJESE) ISSN: 2319–6378 (Online), Volume-13 Issue-11, October 2025 1 Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved. Retrieval Number:100.1/ijese.L262013121125 DOI:10.35940/ijese.L2620.13111025 Journal Website: www.ijese.org A Study towards Supervised Learning Techniques for a Well-Predictive Modelling Utilising Electronic Health Record Data Abhay Bhatia, Rajeev Kumar, Golnoosh Manteghi Abstract: Electronic health records (EHRs) provide a substantial repository of structured and unstructured data, enabling predictive modelling for medical research and clinical decision-making. The gathered EHR data is more useful for machine learning; all the information about a diagnosed patient — such as their lab results, demographics, treatments, etc. — needs to be compiled, cleaned, and converted to a standard format for use. To start supervised learning, split the dataset into two sets: a training set and a test set. Then a model that works well is chosen, such as decision trees, logistic regression, random forests, or neural networks. People use these models to learn about diseases, the risks they pose, and the best treatments. To assess how well something works, model evaluation uses metrics such as precision and accuracy. We can learn more about patient care, achieve better results, and make medical associations more evidence-based by systematically applying supervised learning techniques to EHR data. Keywords: EHR, X-Rays, CT-Scan, MRI, Health, NLP Nomenclature: HER: Electronic Health Records NLP: Natural Language Processing EMRs: Electronic Medical Records PCA: Principal Component Analysis SVMs: Support Vector Machines GBM: Gradient Boosting Machines I. INTRODUCTION Machine learning is transforming how diseases are detected, treated, and avoided in the medical field. Deep learning models are helping doctors and other medical professionals detect diseases such as neurological disorders, cancer, and heart-related conditions by analysing X-rays, MRIs, or CT scans [1], if available. Machine learning algorithms enable early detection of such occurrences by analysing patterns in the EHR data of the unhealthy patient. This helps detect conditions such as diabetes and heart failure. Machine learning [2]. Manuscript received on 30 September 2025 | Revised Manuscript received on 06 October 2025 | Manuscript Accepted on 15 October 2025 | Manuscript published on 30 October 2025. *Correspondence Author(s) Dr. Abhay Bhatia*, Post Doctoral Researcher, Kuala Lumpur University of Science & Technology (KLUST), Malaysia, Jalan Ikram-Uniten (Kajang), Email ID: [email protected], ORCID ID: 0000-0001-7220692X Prof. (Dr.) Rajeev Kumar, Professor, Department of Computer Science & Engineering, Moradabad Institute of Technology, Moradabad, Uttar Pradesh, India. Email ID: [email protected] Dr. Golnoosh Manteghi, Department of Architecture and Built Environment, Kuala Lumpur University of Science & Technology (KLUST), Malaysia, Jalan Ikram-Uniten (Kajang), Email ID: golnoosh.ma[email protected]u.my © The Authors. Published by Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license http://creativecommons.org/licenses/by-nc-nd/4.0/ In personalised medicine, genetic data is used to develop treatments tailored to each person's genetic makeup. Healthcare practitioners can utilise machine learning-based predictive analytics to determine the likelihood that a patient will become ill or need to return to the hospital. These prediction models are used to monitor worsening patient conditions, especially in intensive care units, enabling timely interventions. In the domain of causal inference, automated learning methodologies are employed to replicate results, while randomised controlled trials utilise real-world data. These estimates are more precise and reduce bias. The healthcare sector has experienced significant upheaval due to EHRs, which enable healthcare workers to access patient information and enhance decision-making using clinical notes. This study examines the comparative efficiency of supervised and unsupervised learning algorithms in predicting patient outcomes utilising electronic health record data. The objective is to evaluate the survey [3] on supervised and unsupervised machine learning algorithms within the healthcare domain. This clarifies how effectively they can be operated and how healthcare providers might employ them. II. LITERATURE REVIEW Electronic Health Records (EHR) [4] are computerised systems that collect and store patient health information, including demographics, diagnoses, treatment plans, lab test results, imaging reports, and clinician notes. There are many reasons why EHRs are now an essential aspect of healthcare research. One of those EHRs provides long-term data on how patients' health changes over time, which helps researchers examine how diseases emerge, how treatments work, and how care practices vary. EHR data accurately represent realworld scenarios, incorporating diverse patient demographics and clinical practices [5], thereby increasing the generalisability of healthcare research, unlike controlled clinical trials. The abundance of comprehensive EHR data enables the development of personalised therapeutics by identifying patient-specific trends and customising interventions [6]. There are already many health records, so there is less need to obtain new ones. This makes it faster to gather results. Electronic Health Records (EHRs) are very helpful for identifying disease patterns, monitoring epidemics, and assessing how well public health policies are working. Using EHR data, machine learning can identify problems in care delivery, A Study Towards Supervised Learning Techniques for a Well-Predictive Modelling Utilising Electronic Health Record Data 2 Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved. Retrieval Number:100.1/ijese.L262013121125 DOI:10.35940/ijese.L2620.13111025 Journal Website: www.ijese.org refine treatment plans, and develop rules that help patients get better. A. Comparative Study and Analysis The aim of applying machine learning to electronic health records is to enhance the precision of healthcare choices, including their forecasts. Machine learning [7] programs can easily identify what can go wrong, estimate what can happen next, develop strategies as the best treatment, and monitor how effectively healthcare interventions are functioning. Machine learning can help doctors and nurses receive answers faster and more precisely. Electronic health records are used by machine learning algorithms to analyse heart disease [8] and predict the next stage of a patient's condition, such as whether they will need to return to the hospital or suffer long-term illness. By analysing trends in patient histories, demographics, and clinical data, these models help healthcare providers identify high-risk individuals and take steps to improve outcomes. i. Helps with diagnosis and treatment: An EHR system, along with machine learning, analyses both structured and unstructured data, such as imaging reports, Clinical notes, Case history, diagnostic codes, and more. This helps doctors make more accurate diagnoses, yielding more detailed patient information and enabling them to suggest personalised therapy options [9]. ii. Personalised Medicine: Machine learning uses EHR data, such as clinical information, personal history, etc., to help determine the best treatments for each patient's condition and to plan better care [10]. iii. Clinical Decision Support: By providing real-time inputs to doctors and medical professionals, datadriven, machine-learning-based advice on patient care can be generated. This process creates a clear environment, as before deciding on issues such as drug management, patient diagnosis, and treatment [11]. By analysing EHR data across the desired populations, machine learning can identify the most predictive patterns and highlight differences, thereby identifying risk factors. This information helps formulate targeted public health initiatives and policies to address health issues affecting the entire population effectively. III. MACHINE LEARNING AND ITS METHODS TO VERIFY THE EHR DATASET A. Health Research Dependency Healthcare research depends on EHR databases because they contain vast amounts of unique and essential information that machine learning algorithms need. One of the most widely used datasets is the MIMIC-III database [12], which contains anonymised health information from patients in intensive care. Some others, or standard datasets, come from private sources, e.g., hospitals and healthcare networks. Researchers use public datasets like MIMIC-III a lot because they are easy to obtain, have complex structures, and provide good documentation. On the other hand, private databases can only offer healthcare organisations information that is helpful to them, making it easier to focus on and enhance localised analysis. It’s mandatory to clean up the raw data before it can be used for EHR datasets. EHR data often contains problems such as missing or inconsistent values, dimension issues, and, worst of all, formatting issues. When discussing missing data, it needs to be handled with care, as it is an essential first step because it can cause bias and make machine learning models less helpful [13]. Some ways to deal with missing data are mean imputation, direct filling, and predictive modelling. Outlier removal and detection techniques are used to maintain data quality. On the other hand, feature extraction is an essential first step that converts the raw EHR data into valuable, organised inputs for machine learning algorithms to process. This process uses natural language processing (NLP) techniques to convert unstructured data, such as clinical notes, into structured properties [14]. A significant time series, with temporal data, including lab results with timestamps or prescriptions for medicine, is assembled or displayed in a time-series format [15]. For machine learning to use categorical data such as diagnosis codes or patient information, one-hot encoding or embeddings are used [16]. Principal component analysis (PCA) and other dimensionality reduction methods can help you retain the most critical data and make it easier to understand [17]. EHR datasets need to be cleaned and organised before they can be used with supervised or unsupervised machine learning algorithms. This is what successful pre-processing does. This helps people studying health data find meaningful patterns and trends. B. State of the Art: Supervised Learning Methods Using EHR Self-supervised learning is when you use labelled data to teach a machine learning model how to make predictions [18]. In electronic medical records (EMRs) [16], patient data (input characteristics) and related clinical outcomes (labels) are used to make models that predict unknown events or help people make decisions. Supervised learning techniques elucidate the relationship between patient data (demographics, vital signs, lifestyle factors, etc.) and disease progression. These models make predictions based on past patterns and correlations. International Journal of Emerging Science and Engineering (IJESE) ISSN: 2319–6378 (Online), Volume-13 Issue-11, October 2025 3 Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved. Retrieval Number:100.1/ijese.L262013121125 DOI:10.35940/ijese.L2620.13111025 Journal Website: www.ijese.org Table 1: Summarises the Method Used in Supervised Learning Using EHR Method Applications Advantages Limitations Logistic Regression [19] Binary classification (e.g., disease risk) Simple, interpretable, efficient Assumes linear relationships Decision Trees [20] Risk stratification, treatment suggestions Interpretable, handles non-linear data Prone to overfitting Random Forests [21] Risk prediction, survival analysis Reduces overfitting, robust to noise Less interpretable, computationally heavy GBM (e.g., XGBoost) [22] Outcome prediction, feature importance High accuracy, handles complexity Requires tuning, prone to overfitting SVM [23] Disease subtype classification Effective in high dimensions Sensitive to noise, slow on extensive data Neural Networks [24] Readmission prediction, complex tasks Captures non-linear patterns, scalable Needs extensive data, less interpretable k-NN Similarity-based predictions Simple, no training needed Slow inference, struggles with high dimensions Naive Bayes [25] Rare disease diagnosis, text classification Fast, effective for small datasets Assumes feature independence Linear Regression Continuous outcomes (e.g., length of stay) Simple, interpretable Limited to linear problems, outlier-sensitive For instance, predicting diabetes based on a patient's risk factors exemplifies the theoretical concept of a correlation between input variables and disease manifestation. On the other hand, to predict death, you need to know how to read patterns of decline in the electronic health record, such as worsening vital signs or lab test results. Another way that machine learning works is through logistic regression, which uses probabilistic modelling to guess binary outcomes. It assumes a linear relationship between the predictors and the logarithm of the probability of the dependent variable. This strategy uses a linear combination of risk factors to estimate the likelihood that a person will become ill. Decision trees and random forests use recursive partitioning to split a dataset into smaller, more similar groups. Ensemble learning with random forests uses many trees, which makes it easier to predict outcomes by how patient data is linked together in a hierarchy. The gradient boosting machine learning method works by ensuring that errors occur in a specific order. The model makes fewer mistakes when predicting complex patterns by repeatedly combining weak learners. This is especially helpful for grouping patients by risk. Artificial neurons that mimic neurons in the human brain form the basis of neural networks. They adjust the weights via backpropagation to learn non-linear relationships between inputs and outputs. This makes them suitable for modelling time-based electronic health record data and predicting patient outcomes. IV. WORKFLOW MODEL OF EHR USING SUPERVISED LEARNING When you use Electronic Health Record (EHR) data for supervised learning in machine learning, you have to follow a set of steps to change raw healthcare data into useful information. As shown in Figure 1, the first step is to collect and combine data. There are many sources of EHR data, including clinical reports, images, lab results, and more. It contains information about the patient, their medical history, diagnosis, treatment plans, medication records, and outcomes. It's essential to put all these records together in a way that makes sense and is easy to understand so that machine learning programs can use them consistently. Data preprocessing and feature engineering are essential steps performed on the raw data. This is when the raw data is cleaned up for analysis. Data cleaning involves handling issues such as missing values, out-of-range values, and values that don't make sense. This could mean adding missing values or removing rows and columns with too many empty cells. One-hot encoding and label encoding are two methods for converting categorical data, such as medications and diagnoses, into numerical values. After that, the numerical data is standardised (normalised) so that all features are on the same scale. This is important for the model to work better. Feature engineering is the process of adding new features to a model to improve its predictive accuracy. For instance, using temporal features, such as the patient's age, or combining data, such as average test results over time, can help you learn more. The dataset is split into two parts: training and testing. This is the model that starts learning. Usually, before it starts, it is divided into the specified ratio, 80-20 or 70-30. We can see that stratified sampling is also often used, ensuring that distributions of essential variables, such as outcomes or early disease diagnoses, are the same across all subgroups. The training set builds the model, and the test set evaluates how well it performs on new data. Choosing the right supervised learning model is a critical decision that depends on the data and the situation. Logistic regression for binary classification, decision trees and random forests for handling complex, non-linear interactions, and support vector machines (SVMs) for high-dimensional datasets are among the most common approaches for interpreting EHR data. Gradient boosting machines (GBM), such as XGBoost, are well-liked because they can make accurate predictions. On the other hand, neural networks are better at analysing large datasets with complex patterns. Knearest neighbours (k-NN) work well for simple applications that are based on similarity. The feedback loop is also vital for verifying the authenticity of the desired data. A Study Towards Supervised Learning Techniques for a Well-Predictive Modelling Utilising Electronic Health Record Data 4 Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved. Retrieval Number:100.1/ijese.L262013121125 DOI:10.35940/ijese.L2620.13111025 Journal Website: www.ijese.org [Fig.1: Schematic Diagram of the Electronic Health Record in the Machine Learning Model] Once you pick a model, you utilise the training data to teach it. For example, neural networks employ backpropagation to learn, whereas tree-based models use boosting. These techniques help improve parameter settings and reduce mistakes. Fig 2 IOT and Blockchain-Based HER [26] [Fig.2: Shows a Three-Step Process for Handling Health Data] A. Data Acquisition and Transformation: Patient RealTime IoT Health Data is collected safely. After that, the data is turned into blocks. This enables the use of blockchain technology for security and integrity. B. Preference-Based Recommendation: The data blocks go into a system that makes recommendations based on preferences. This system combines Expert Preference and Patient Preference to determine the best next step, such as choosing the correct repository. C. Data Storage: The last step is to store the health data in a secure repository, using cloud or decentralised storage to keep records safe and easily accessible over time. The goal of this process is to safely, personally, and efficiently manage patient health data collected by IoT devices. V. CONCLUSION Hence, in the closing note, it can be stated that the electronic health records (EHRs) contain a feature of structured as well as unstructured data, and this data can be used for practical predictive modelling purposes, making them helpful in the field of medical research while figuring out how best to provide for patients. The EHR technology pulls together and cleans the data, making several changes to patient data, likely all the gathered information, including clinical tests, reports, and other required information. The data must undergo a preprocessing step before utilisation begins, which includes filling in missing values, normalising values, and encoding categorical variables. The first step in using supervised learning on EHR data is to split the data into two sets: one for training and the other for testing. After that, a model working on the problem is chosen. There are several ways to tackle the issue, including identifying which diseases exist, estimating risks, and providing therapies. Some of these are logistic regression, decision trees, random forests, and neural networks. After training, the model is tested to evaluate its predictive performance. DECLARATION STATEMENT After aggregating input from all authors, I must verify the accuracy of the following information as the article's author. ▪ Conflicts of Interest/ Competing Interests: Based on my understanding, this article has no conflicts of interest. ▪ Funding Support: This article has not been funded by any organizations or agencies. This independence ensures that the research is conducted with objectivity and without any external influence. ▪ Ethical Approval and Consent to Participate: The content of this article does not necessitate ethical approval or consent to participate with supporting documentation. ▪ Data Access Statement and Material Availability: The adequate resources of this article are publicly accessible. ▪ Author’s Contributions: The authorship of this article is contributed equally to all participating individuals. REFERENCES 1. Rana, M., Bhushan, M. Machine learning and deep learning approach for medical image analysis: diagnosis to detection. Multimed Tools Appl 82, 26731–26769 (2023). DOI: https://doi.org/10.1007/s11042-022-14305-w. 2. Li, Wei, Yuanbo Chai, Fazlullah Khan, Syed Rooh Ullah Jan, Sahil Verma, Varun G. Menon, fnm Kavita, and Xingwang Li. "A comprehensive survey on machine learning-based big data analytics for IoT-enabled smart healthcare systems." Mobile networks and applications 26 (2021): 234-252, DOI: https://doi.org/10.1007/s11036-020-01700-6 3. Yao, Liuyi, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, and Aidong Zhang. "A survey on causal inference." ACM Transactions on Knowledge Discovery from Data (TKDD) 15, no. 5 (2021): 1-46, DOI: https://doi.org/10.48550/arXiv.2002.02770. 4. Si, Yuqi, Jingcheng Du, Zhao Li, Xiaoqian Jiang, Timothy Miller, Fei Wang, W. Jim Zheng, and Kirk Roberts. "Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review." Journal of biomedical informatics 115 (2021): 103671, DOI: https://doi.org/10.1016/j.jbi.2020.103671. 5. Rashidi, Hooman H., Nam Tran, Samer Albahra, and Luke T. Dang. "Machine learning in health care and laboratory medicine: General overview of supervised learning and Auto‐ML." International Journal of Laboratory Haematology 43 (2021): 15-22, DOI: https://doi.org/10.1111/ijlh.13537. 6. Tayefi, Maryam, Phuong Ngo, Taridzo Chomutare, Hercules Dalianis, Elisa Salvi, Andrius Budrionis, and Fred Godtliebsen. "Challenges and opportunities beyond structured data in analysis of electronic health records." Wiley Interdisciplinary Reviews: Computational Statistics 13, no. 6 (2021): e1549, International Journal of Emerging Science and Engineering (IJESE) ISSN: 2319–6378 (Online), Volume-13 Issue-11, October 2025 5 Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved. Retrieval Number:100.1/ijese.L262013121125 DOI:10.35940/ijese.L2620.13111025 Journal Website: www.ijese.org DOI: https://doi.org/10.1002/wics.1549. 7. Javaid, Mohd, Abid Haleem, Ravi Pratap Singh, Rajiv Suman, and Shanay Rab. "Significance of machine learning in healthcare: Features, pillars and applications." International Journal of Intelligent Networks 3 (2022): 58-73, DOI: https://doi.org/10.1016/j.ijin.2022.05.002. 8. Ramesh, T. R., Umesh Kumar Lilhore, M. Poongodi, Sarita Simaiya, Amandeep Kaur, and Mounir Hamdi. "Predictive analysis of heart diseases with machine learning approaches." Malaysian Journal of Computer Science (2022): 132-148, DOI: https://doi.org/10.22452/mjcs.sp2022no1.10. 9. Kute, Shruti Suhas, A. V. Shreyas Madhav, Shabnam Kumari, and S. U. Aswathy. "Machine learning–based disease diagnosis and prediction for E‐healthcare system." Advanced analytics and deep learning models (2022): 127-147, DOI: https://doi.org/10.1002/9781119792437 10. Tong, Li, Wenqi Shi, Monica Isgut, Yishan Zhong, Peter Lais, Logan Gloster, Jimin Sun, Aniketh Swain, Felipe Giuste, and May D. Wang. "Integrating multi-omics data with EHR for precision medicine using advanced artificial intelligence." IEEE Reviews in Biomedical Engineering (2023), DOI: https://doi.org/10.1109/rbme.2023.3324264. 11. Berge, Geir Thore, Ole-Christoffer Granmo, Tor Oddbjørn Tveit, Bjørn Erik Munkvold, Anna Linda Ruthjersen, and Jivitesh Sharma. "Machine learning-driven clinical decision support system for concept-based searching: a field trial in a Norwegian hospital." BMC Medical Informatics and Decision Making 23, no. 1 (2023): 5, https://hdl.handle.net/11250/3126844. 12. Johnson, Alistair EW, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J. Pollard et al. "MIMIC-IV, a freely accessible electronic health record dataset." Scientific data 10, no. 1 (2023): 1, DOI: https://doi.org/10.1038/s41597-022-01899-x. 13. Hasan, Md Kamrul, Md Ashraful Alam, Shidhartho Roy, Aishwariya Dutta, Md Tasnim Jawad, and Sunanda Das. "Missing value imputation affects the performance of machine learning: A review and analysis of the literature (2010–2021)." Informatics in Medicine Unlocked 27 (2021): 100799, DOI: https://doi.org/10.1016/j.imu.2021.100799. 14. Davuluri, Manaswini. "An Overview of Natural Language Processing in Analyzing Clinical Text Data for Patient Health Insights." Researchgate journal 10, no. 10 (2024), https://researchgate.in/index.php/Rgj/article/view/53. 15. Jin, Ming, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang et al. "Large models for time series and spatiotemporal data: A survey and outlook." DOI: https://doi.org/10.48550/arXiv.2310.10196. 16. Tayefi, Maryam, Phuong Ngo, Taridzo Chomutare, Hercules Dalianis, Elisa Salvi, Andrius Budrionis, and Fred Godtliebsen. "Challenges and opportunities beyond structured data in analysis of electronic health records." Wiley Interdisciplinary Reviews: Computational Statistics 13, no. 6 (2021): e1549, DOI: https://doi.org/10.1002/wics.1549. 17. Hasan, Basna Mohammed Salih, and Adnan Mohsin Abdulazeez. "A review of principal component analysis algorithm for dimensionality reduction." Journal of Soft Computing and Data Mining 2, no. 1 (2021): 20-30, DOI: https://doi.org/10.30880/jscdm.2021.02.01.003. 18. Krishnan, Rayan, Pranav Rajpurkar, and Eric J. Topol. "Self-supervised learning in medicine and healthcare." Nature Biomedical Engineering 6, no. 12 (2022): 1346-1352, DOI: https://doi.org/10.1038/s41551-022-00914-1. 19. Zabor, Emily C., Chandana A. Reddy, Rahul D. Tendulkar, and Sujata Patil. "Logistic regression in clinical studies." International Journal of Radiation Oncology* Biology* Physics 112, no. 2 (2022): 271-277, DOI: https://doi.org/10.1016/j.ijrobp.2021.08.007. 20. Aeppli, Stefanie, M. Schmaus, Timothy Eisen, Bernard Escudier, Viktor Grünwald, James Larkin, David McDermott et al. "First-line treatment of metastatic clear cell renal cell carcinoma: a decision-making analysis among experts." ESMO open 6, no. 1 (2021): 100030, DOI: https://doi.org/10.1016/j.esmoop.2020.100030. 21. Pickett, Kaci L., Krithika Suresh, Kristen R. Campbell, Scott Davis, and Elizabeth Juarez-Colunga. "Random survival forests for dynamic predictions of a time-to-event outcome using a longitudinal biomarker." BMC medical research methodology 21 (2021): 1-14, DOI: https://doi.org/10.1186/s12874-021-01375-x. 22. Adler, Afek Ilay, and Amichai Painsky. "Feature importance in gradient boosting trees with cross-validation feature selection." Entropy 24, no. 5 (2022): 687, DOI: https://doi.org/10.3390/e24050687. 23. Kushwaha, Pradeep Kumar, and M. Kumaresan. "Machine learning algorithm in healthcare system: A Review." In 2021 International Conference on Technological Advancements and Innovations (ICTAI), pp. 478-481. IEEE, 2021, DOI: https://doi.org/10.1109/ICTAI53825.2021.9673220. 24. Kumar, Ashish, Ketan Rathor, Snehit Vaddi, Devanshi Patel, Preethi Vanjarapu, and Manichandra Maddi. "ECG-Based Early Heart Attack Prediction Using Neural Networks." In 2022, the 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 1080-1083. IEEE, 2022, DOI: https://doi.org/10.1109/ICESC54411.2022.9885448. 25. Anubhav kumar, Virat Sharma, Praveen Verma, Abhay Bhatia, Manish Kumar, “Use of Artificial Intelligence and Machine Learning in Medicines with Implementation of Bayesian Techniques” is published in IJCRT, https://ijcrt.org/papers/IJCRT2208526.pdf. 26. Front. Public Health, 21 January 2022 Sec. Digital Public Health Volume 9 - 2021 | DOI: https://doi.org/10.3389/fpubh.2021.831404 AUTHOR’S PROFILE Dr. Abhay Bhatia is an accomplished academician and researcher and is associated as Post Doctoral Researcher at Kuala Lumpur University of Science and Technology (KLUST), Malaysia. He is also serving as Associate Professor in the Department of Computer Science and Engineering at Roorkee Institute of Technology, Uttarakhand and with over 13 years of teaching and research experience, he holds a B.Tech and M.Tech in Computer Science and a Ph.D. in Wireless Sensor Networks. An active IEEE member, he has published over 34 papers, authored 11 book chapters, and filed seven patents. His authored books include Fundamentals of IoT and Practical Approach to Machine Learning with TensorFlow. His research interests include Artificial Intelligence, Machine Learning, and Wireless Sensor Networks. Prof. (Dr.) Rajeev Kumar is a distinguished academician and researcher with over 15 years of experience in higher education. He serves as Professor in the Department of Computer Science and Engineering at Moradabad Institute of Technology, Uttar Pradesh. Holding a Ph.D., D.Sc., and Postdoctoral Fellowship from Malaysia, he specializes in Artificial Intelligence, Cloud Computing, and Data Science. A senior IEEE member, he has published over 120 papers, filed 15 patents, and guided multiple Ph.D. scholars. His global academic engagements, leadership roles, and innovative teaching approaches reflect his dedication to advancing education, research, and technological innovation. Dr. Golnoosh Manteghi is a distinguished academic at the Faculty of Architecture and Built Environment, Kuala Lumpur University of Science and Technology (KLUST), Malaysia. With expertise in computer algorithms, data analysis, and network management, she has contributed significantly to academia and industry. Formerly a Senior Lecturer at IUKL and a Research Officer at PETRONAS Electromagnetics Research Cluster, she has advanced research in wireless sensor networks and hydrocarbon detection. Her innovative work has earned multiple gold and silver medals, and she actively serves in editorial and leadership roles, promoting excellence in smart infrastructure, digital communication, and technological innovation. Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of the Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP)/ journal and/or the editor(s). The Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions, or products referred to in the content.