APRIL 5, 2019
Jukka-Pekka “JP” Onnela, D.Sc.
Associate Professor of Biostatistics
Director, Master’s Program in Health Data Science
Department of Biostatistics
Harvard T.H. Chan School of Public Health
About the Presentation: Behavior has traditionally been a difficult phenotype to characterize because of its temporal nature and context dependence. Traditionally it has been captured using either self-reported accounts of behavior or clinician-administered instruments or examinations. Both are subjective, qualitative, and typically cross-sectional; the latter is also confined to clinic / office settings. The ubiquity and capability of smartphones to collect social, behavioral, and cognitive data can be used to characterize psychopathology using objective measurement. We have previously defined digital phenotyping as the moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices, in particular smartphones. I will discuss digital phenotyping and will introduce Beiwe, our open source research platform for high-throughput, smartphone-based digital phenotyping. I will show how we have applied Beiwe in the mental health setting and will highlight some recent results. I will also consider some of the statistical and computational challenges that arise in this line of research.