Using An Optimized Generative Model To Infer The Progression of Complications In Type 2 Diabetes Patients

Background: People with type 2 diabetes would progress slowly and have few symptoms before diagnosed, if any, and don’t discover their condition until complications develop. Furthermore, with the development of the diabetes, patients often develop comorbidities. However, heterogeneity of progression coupled with deficiencies in electronic health records related to incomplete data, discrete events, and irregular event intervals make identification of pre-diabetes and critical points of diabetes progression challenging. Methods: We utilized longitudinal electronic health records of 9,298 patients with type 2 diabetes or prediabetes from 2005 to 2016 from a large regional healthcare delivery network in China. We optimized a generative Markov-Bayesian-based model to generate 5000 synthetic illness trajectories. The synthetic data were manually reviewed by endocrinologists. Results: We build an optimized generative progression model for type 2 diabetes using anchor information to reduce the number of parameters learning in the third layer of the model from O(N×W) to O(N-C), where N is the number of clinical findings, W is the number of complications, C is the number of anchors. Based on this model, we infer the relationships between progression stages, the onset of complication categories, and the associated diagnoses during the whole progression of type 2 diabetes using electronic health records. Conclusions: The full type 2 diabetes patient trajectories generated by the chronic disease progression model can counter a lack of real-world evidence of desired longitudinal timeframe while facilitating population health management.