Skip to content
DSML.KZ
Publications

Talk · International Conference on Pervasive Computing and Social Networking · May 14, 2025

Leveraging Machine Learning to Predict Disease Risk Levels from Multiple Eye Condition Indicators

Mudumala Varnika Narayani, Nunnaguppala Rohit, Naga Ruthvika Durupudi, Tejashwini Vadeghar, C. Jyotsna, Aiswariya Milan K

Jyotsna Chandrasekharan
Open via DOI

Abstract

This paper presents a review of machine learning methodologies applied to disease risk evaluation, leveraging ocular condition indices derived from the RFMiD dataset. To enhance the performance of classification, a formal and structured mechanism of statistical analysis and also the method of model prediction was applied. Data mining techniques which include Decision Trees, Random Forest, Naive Bayes, Gradient Boosting, and Stacking Classifiers were evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. For the cases of coarse models applied to healthcare XAI approaches such as SHAP and LIME were used to gain better interpretability. This paper points to the potential of machine learning for disease risk modelling and provides recommendations for generating accurate and easily-interpreted models in order to increase the diagnostic accuracy and, therefore, the quality of care for patients.

Artificial Intelligence in HealthcareRetinal Imaging and AnalysisOphthalmology and Visual Health Researchdisease risk predictioneye diseasesrandom forest

More by Jyotsna Chandrasekharan