Director of the Master’s Program in Health Data Science
Harvard T.H. Chan School of Public Health, Harvard University.

 

 

Abstract: Recent advances in biomedicine and technology are beginning to change the priority in biomedical research towards phenotyping, which refers to the collection and analysis of various traits of organisms, such as their anatomy, enzyme activity, and behavior. Many investigators have promoted the role of large-scale phenotyping as the natural complement to genome sequencing as a route to advances in biomedical sciences, but behavior continues to present special challenges to phenomics because of its temporal nature and context dependence. We believe that the ubiquity and capability of smartphones to collect social and behavioral data can contribute to the phenotyping challenge via objective measurement, especially in neuropsychiatric conditions. 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 the concept of digital phenotyping, introduce Beiwe, our research platform for high-throughput, smartphone-based digital phenotyping, and will share some results from our ongoing studies with various patient cohorts.