Sequential Representation of Sparse Heterogeneous Data for Diabetes Risk Prediction

Rochana Chaturvedi, Mudassir M. Rashid, Brian T. Layden, Andrew D. Boyd, Ali Cinar, Barbara Di Eugenio

Abstract: Type 2 diabetes (T2D) is a major public health problem, and opportunistic screening to detect T2D at an early stage can help initiate interventions that delay or prevent the disease and its complications. In this study, we use electronic health records (EHR) and concepts extracted from clinical notes to predict future T2D risk. Our deep neural network-based model captures the temporal sequence of patient visits. We use explainable AI algorithms to assess the model decisions and observe alignment with the domain knowledge of clinical experts.