Dry Eye Disease in the Digital Age: Causes and Diagnostics Using Machine Learning

Dry Eye Disease (DED) is a widespread condition made worse by modern lifestyle factors such as extended screen time and reduced physical activity. This study focuses on developing a machine learning model, specifically a Random Forest classifier to predict the likelihood of DED based on user data. The dataset included features like screen time, eye discomfort, physical activity, weight, height, blood pressure and other symptoms.The model achieved an accuracy of 71.7\% and a log loss of 0.6501, showing moderatel performance in classifying DED. Feature importance shows that the most important features in prediction were eye strain, redness, irritation, screen time, and physical activity. These results align with clinical expectations and demonstrate that lifestyle-related data can be effectively used to detect DED risk.This research not only supports the idea that behavior affects eye health, but also shows how machine learning can be applied to assist in early detection and personalized recommendations for preventing DED.