A Smart Multimodal Approach for Personalized Diabetes Risk Prediction

Prabhjot Kaur

Prabhjot Kaur Assistant Professor, Department of Computer Science, Khalsa College Amritsar, Punjab, India

Keywords: Data Preprocessing, Machine Learning, Personalized healthcare, Diabetes Prediction, Logistic Regression, Linear Regression, K- Nearest Neighbors

Abstract

This study presents a machine learning approach for foreseeing diabetes in people utilizing clinical information. A dataset containing highlights like glucose levels, BMI, Insulin, and other medical Indicators is utilized to classify patients into diabetic and non-diabetic categories. We implemented different classification models including Logistic Regression and K- Nearest Neighbors (KNN). As a start, we have initiated with data preprocessing to find out mean imputation, outlier removal via IQR, and Min–Max scaling, models are implemented and evaluated on available held test data. The KNN demonstrate accomplished an accuracy of 96% with a weighted average F1-score of 0.96. We have obtained the ROC-AUC of 0.8613. This approach illustrates the potential for successful diabetes forecast, advertising critical help in restorative diagnostics as an early detection of disease.

References

Tong, L., Shi, W., Isgut, M., Zhong, Y., Lais, P., Gloster, L., Sun, J., Swain, A., Giuste, F. and Wang, M.D., Integrating multi-omics data with EHR for precision medicine using advanced artificial intelligence. IEEE Reviews in Biomedical Engineering. [Google Scholar]

Alam, S., 2021. PMTRS: A Personalized Multimodal Treatment Response System Framework for Personalized Healthcare. International Journal of Applied Health Care Analytics, 8(6), pp.18-28. [Google Scholar]

Li, X., Tao, S., Lhatoo, S.D., Cui, L., Huang, Y., Hampson, J.P. and Zhang, G.Q., 2021. A multimodal clinical data resource for personalized risk assessment of sudden unexpected death in epilepsy. Frontiers in big Data, 5, p.965715. [Google Scholar]

Boehm, K.M., Khosravi, P., Vanguri, R., Gao, J. and Shah, S.P. Harnessing multimodal data integration to advance precision oncology. Nature Reviews Cancer, 22(2), pp.114-126. [Google Scholar]

Johnson, K.B., Wei, W.Q., Weeraratne, D., Frisse, M.E., Misulis, K., Rhee, K., Zhao, J. and Snowdon, J.L., 2021. Precision medicine, AI, and the future of personalized health care. Clinical and translational science, 14(1), pp.86-93. [Google Scholar]