Sociodemographic Characteristics of Missing Data in Digital Phenotyping

The ubiquity of smartphones, with their increasingly sophisticated array of sensors, presents an unprecedented opportunity for researchers to collect diverse, temporally-dense data about human behavior while minimizing participant burden. Researchers increasingly make use of smartphone applications for "digital phenotyping," the collection of phone sensor and log data to study the lived experiences of subjects in their natural environments. While digital phenotyping has shown promise in fields such as psychiatry and neuroscience, there are fundamental gaps in our knowledge about data collection and non-collection (i.e., missing data) in smartphone-based digital phenotyping. Here, we show that digital phenotyping presents a viable method of data collection, over long time periods, across diverse study participants with a range of sociodemographic characteristics. We examined accelerometer and GPS sensor data of 211 participants, amounting to 29,500 person-days of observation, using Bayesian hierarchical negative binomial regression. We found that iOS users had higher rates of accelerometer non-collection but lower GPS non-collection than Android users. For GPS data, rates of non-collection did not differ by race/ethnicity, education, age, or gender. For accelerometer data, Black participants had higher rates of non-collection while Asian participants had slightly lower non-collection. For both sensors, non-collection increased by 0.5% to 0.9% per week. These results demonstrate the feasibility of using smartphone-based digital phenotyping across diverse populations, for extended periods of time, and within diverse cohorts. As smartphones become increasingly embedded in everyday life, the insights of this study will help guide the design, planning, and analysis of digital phenotyping studies.