Authors: Peter Polack, Shang-Tse Chen, Minsuk Kahng, Moushumi Sharmin, Duen Chang
Abstract: Whereas event-based timelines for healthcare enable users to visualize the chronology of events surrounding events of interest, they are often not designed to aid the discovery, construction, or comparison of associated cohorts. We present TimeStitch, a system that helps health researchers discover and understand events that may cause abstinent smokers to lapse. TimeStitch extracts common sequences of events performed by abstinent smokers from large amounts of mobile health sensor data, and offers a suite of interactive and visualization techniques to enable cohort discovery, construction, and comparison, using extracted sequences as interactive elements. We are extending TimeStitch to support more complex health conditions with high mortality risk, such as reducing hospital readmission in congestive heart failure.