Omolola I Ogunyemi1, Meghal Gandhi1, Chandler Tayek1,2. 1. Center for Biomedical Informatics, Charles R. Drew University of Medicine and Science, Los Angeles, CA. 2. Dept of Computer Science, University of Massachusetts, Amherst, Amherst, MA.
Abstract
Introduction: Timely diabetic retinopathy detection remains a problem in medically underserved settings in the US; diabetic patients in these locales have limited access to eye specialists. Teleretinal screening programs have been introduced to address this problem. Methods: Using data on ethnicity, gender, age, hemoglobin A1C, insulin dependence, time since last eye examination, subjective diabetes control, and years with diabetes from 27,116 diabetic patients participating in a Los Angeles County teleretinal screening program, we compared different machine learning methods for predicting retinopathy. The dataset exhibited a class imbalance. Results: Six classifiers learned on the data were predictive of retinopathy. The best model had an AUC of 0.754, sensitivity of 58% and specificity of 80%. Discussion: Successfully detecting retinopathy from diabetic patients' routinely collected clinical data could help clinicians in medically underserved areas identify unscreened diabetic patients who are at risk of developing retinopathy. This work is a step towards that goal.
Introduction: Timely diabetic retinopathy detection remains a problem in medically underserved settings in the US; diabeticpatients in these locales have limited access to eye specialists. Teleretinal screening programs have been introduced to address this problem. Methods: Using data on ethnicity, gender, age, hemoglobin A1C, insulin dependence, time since last eye examination, subjective diabetes control, and years with diabetes from 27,116 diabeticpatients participating in a Los Angeles County teleretinal screening program, we compared different machine learning methods for predicting retinopathy. The dataset exhibited a class imbalance. Results: Six classifiers learned on the data were predictive of retinopathy. The best model had an AUC of 0.754, sensitivity of 58% and specificity of 80%. Discussion: Successfully detecting retinopathy from diabeticpatients' routinely collected clinical data could help clinicians in medically underserved areas identify unscreened diabeticpatients who are at risk of developing retinopathy. This work is a step towards that goal.
Authors: Daniella Meeker; Paul Fu; Gary Garcia; Irene E Dyer; Kabir Yadav; Ross Fleishman; Hal F Yee Journal: J Am Med Inform Assoc Date: 2022-03-15 Impact factor: 4.497
Authors: Omolola I Ogunyemi; Meghal Gandhi; Martin Lee; Senait Teklehaimanot; Lauren Patty Daskivich; David Hindman; Kevin Lopez; Ricky K Taira Journal: JAMIA Open Date: 2021-08-19