Glaucoma is the second leading cause of irreversible blindness worldwide. About 70 million people have glaucoma, and nearly 4.4 million people are blind from optic nerve damage due to undiagnosed glaucoma. Besides, the current glaucoma growth rate and its economic burdens are unsustainable. As a result, warrant a systematic evaluation for glaucoma risk assessment and early prediction for better glaucoma care management. Effective use of temporal information across electronic health records (EHR) provides data-driven and evidence-based risk factors linked to glaucoma development and supports the early predictive model. In the present study, we used 830,125 unique patient records from the EHR database with time-stamp information from 2001 to 2015. The data was sliced into a yearly breakdown and used as input data. We applied four ML methods and compared the performance of prediction accuracy using the yearly partitioned data. The result shows that predictive model performance improves as observation window length decreases from the time of diagnosis. Overall, the temporal EHR data analysis with ML algorithms demonstrates the prediction of glaucoma onset from one to three years in advance of the development of clinical symptoms of the disease. The study suggests that ML-based prediction models for glaucoma detection using temporal analytics can better understand glaucoma management and timely intervention.
Please contact Robert Sanders (email@example.com) for Zoom information.