Type 2 Diabetes Mellitus Trajectories and Associated Risks.

摘要: Disease progression models, statistical models that assess a patient's risk of diabetes progression, are popular tools in clinical practice for prevention and management chronic conditions. Most, if not all, currently use based on gold standard trial data. The relatively small sample size available from limits these only considering the state at time assessment ignoring trajectory, sequence events, led up to state. Recent advances adoption electronic health record (EHR) systems large they contain have paved way build disease can take trajectories into account, leading increasingly accurate personalized assessment. To address problems, we present novel method observe directly. We demonstrate effectiveness proposed by studying type 2 mellitus (T2DM) trajectories. Specifically, using EHR data population-based cohort, identified typical trajectory most people follow, which is diseases hyperlipidemia (HLD) hypertension (HTN), impaired fasting glucose (IFG), T2DM. In addition, also show patients who follow different face significantly increased or decreased risk.