Using SHAP Analysis to Detect Areas Contributing to Diabetic Retinopathy Detection

Esmaeil Shakeri, Trafford Crump, Ezekiel Weis, Roberto Souza, Behrouz Homayoun Far

Abstract: Diabetic retinopathy (DR) is known as an important cause of blindness worldwide and serious public health concern in the population aged 20–65. With the burgeoning number of diabetes globally and its effects on patients' vision, the automatic detection of DR has received wide attention from the machine learning field. However, due to the black-box nature of deep learning and machine learning models, the interpretation and reliability of the predictions is still an issue that needs to be addressed for the successful deployment of these predictive models. In this paper, we use the SHapley Additive exPlanations (SHAP) analysis approach to detect areas of an eye image that contribute the most to the prediction of DR using transfer learning. Our predictive model achieves an accuracy of 97% and 81% for binary and multi-class classification of DR. Our SHAP analysis results show that regardless of the performance of the model, this approach can be used as a tool to interpret the prediction results with more context-sensitive information about each sample, and better understand the reasons for the classification results.