International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Predictive Analytics in Diabetes Diagnosis and Risk Assessment with Data Science Modeling |
|---|---|
| ABSTRACT | One of the most significant chronic health issues in the world today is diabetes mellitus, which calls for early detection and ongoing risk assessment to minimize consequences. Conventional diagnostic techniques frequently rely significantly on manual interpretation and clinical evaluation, which can result in inconsistent results, delays, and low prediction accuracy. Predictive analytics Analytics has become a powerful instrument. for assisting clinical decision-making due to the growing accessibility of medical information and developments in machine learning. This study, "Predictive Analytics in Diagnosis and Risk Evaluation of Diabetes with Data Science Modelling," describes a machine-learning-based system that uses methods such as Naive Bayes and K-Nearest Neighbour (KNN) to categorize patients as either diabetic or not. To determine the best predictive method, the system preprocesses the dataset, extracts pertinent characteristics, trains several models, and assesses each model's performance. By providing data-driven insights, enhancing diagnostic precision, and facilitating early action, The objective is to support healthcare professionals. The suggested method demonstrates The possibility of lightweight machine-learning models in practical healthcare applications and produces dependable classification results through supervised learning. The project enhances risk assessment, improves patient outcomes, and makes health monitoring more intelligent by combining predictive analytics with medical datasets. |
| AUTHOR | SUPRITHA M, DR. PUJA SHASHI PG Student, Dept. of MCA, City Engineering College, Bengaluru, India Professor & HOD, Dept. of MCA, City Engineering College, Bengaluru, India |
| VOLUME | 177 |
| DOI | 10.15680/IJIRCCE.2025.1312072 |
| pdf/72_Predictive Analytics in Diabetes Diagnosis and Risk Assessment with Data Science Modeling.pdf | |
| KEYWORDS | |
| References | 1. Ahmed, I. E., El Seddawy, A. I., & Ali, M. (2022). Addressing class imbalance in predictive analysis of diabetes risk Using algorithms for machine learning. The Journal of Biomedical Informatics, 124, 103936. 2. Al Zu’bi, S., & Akhras, M. (2023). Diabetes monitoring system in smart health cities using big data intelligence. IEEE Access, 11, 5678-5689. 3. Adua, E., Alhassan, A., & Mohammed, A. (2021). Predictive modeling and feature importance in early detection of type II diabetes mellitus. Journal of Healthcare Engineering, 2021, 6629032. 4. Burri, V., Reddy, M., & Srinivasan, P. (2024). AI-powered Early disease prediction models detection: Electronic health record insights and medical imaging. Artificial Intelligence in Medicine, 132, 102025. 5. Butt, U. M., Khan, M., & Babar, M. A. (2021). Machine learning-based diabetes classification and prediction for healthcare applications. Journal of Biomedical Science and Engineering, 14, 167-178. 6. Deore, M., & Gupta, R. (2023). Machine learning-based diabetic retinopathy detection techniques. Medical Image https://doi.org/10.1016/j.media.2023.102643 Analysis, 85, 102643. 7. El Seddawy, A. I., Ahmed, I. E., & Ali, M. (2022). Handling class imbalance in diabetes risk prediction. A comparative study regarding machine learning techniques. Biology and Medicine using Computers 146, 105621. 8. Iyer, K. B. P., & Sharma, S. (2018). Diabetes predictive analytics employing the oneR classification algorithm. Procedia Computer https://doi.org/10.1016/j.procs.2018.05.187 IEEE Science, 132, 308-315. 9. Mbithe, N., & Omondi, L. (2024). Hybrid AI framework for sensor-based personal health monitoring. Transactions on Biomedical Engineering, 71(1), 91-102. 10. Muharram, A. P., & Akbar, M. (2023). Supervised learning models to identify early signs of albuminuria risk in type-2 diabetes mellitus patients. Computational Biology and Chemistry, 92, 107572. 11. Nzomo, M., & Muriuki, B. (2024). Hybrid AI framework for sensor-based health monitoring: Applications in the treatment of diabetes. The Journal of Health Informatics, 29(2), 145-158. 12. Oh, R., & Parker, K. (2022). An interactive online app for diabetes prediction based on environment-polluting chemical exposure data. Journal of Medical Systems, 46(12), 10243. 13. Priyanka Shetty, S. R., & Nayak, R. (2016). Diabetes prediction and monitoring employing data mining methods. International Computer Journal Applications, 142(11), 10-17. |
