Predictive Analytics for Glaucoma Using Data From the All of Us Research Program

center dot PURPOSE: To (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research. center dot DESIGN: Development and evaluation of machine learning models. center dot METHODS: Electronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open -angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glau-coma surgery using multivariable logistic regression, ar-tificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was & nbsp; evaluated based on area under the receiver operating char-acteristic curve (AUC), accuracy, precision, and recall. center dot RESULTS: The mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort ( P = .04 and P < .001, re-spectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in supe-rior performance: AUCs ranged from 0.80 (logistic re-gression) to 0.99 (random forests). center dot CONCLUSIONS: Models trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it of-fers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research.& nbsp;