High-Throughput Digital Phenotyping

Social, behavioral, and cognitive phenotypes are difficult to study due to their temporal and contextual dependence. The standard approach to learning about something as complex as human behavior is to use surveys, which are cross-sectional, subjective, and often burdensome.

The ubiquity and capability of smartphones—when coupled with appropriate data analytic techniques—can be part of the solution. We coined the term Digital Phenotyping to refer to the “moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices, in particular smartphones.” We developed Beiwe and Forest specifically for use in smartphone-based digital phenotyping research.

Most commercially available smartphone applications use software development kits (SDKs) made by Apple and Google that generate unvalidated behavioral summary measures using closed proprietary algorithms. These apps don’t meet the high standards of reproducible science, and often require researchers to modify their scientific questions based on what data happens to be available. Beiwe collects raw sensor and phone use data for analysis by Forest. That means that data collection and data analysis can be customized to address specific scientific questions of interest.