Modeling Disease Progression Trajectories from Longitudinal Observational Data

Analyzing disease progression patterns can provide useful insights into the disease processes of many chronic con-ditions. These analyses may help inform recruitment for prevention trials or the development and personalization oftreatments for those affected. We learn disease progression patterns using Hidden Markov Models (HMM) and distillthem into distinct trajectories using visualization methods. We apply it to the domain of Type 1 Diabetes (T1D) usinglarge longitudinal observational data from the T1DI study group. Our method discovers distinct disease progres-sion trajectories that corroborate with recently published findings. In this paper, we describe the iterative process ofdeveloping the model. These methods may also be applied to other chronic conditions that evolve over time.