JMIR Publications

ABSTRACT

Background:

Previous studies investigating environmental and behavioral drivers of chronic disease often had limited temporal and spatial data coverage. Smartphone-based digital phenotyping mitigates the limitations of these studies by utilizing intensive data collection schemes that take advantage of the widespread use of smartphones while allowing for less burdensome data collection and longer follow-up periods. In addition, smartphone apps can also be programmed to conduct daily or intraday surveys on health behaviors and psychological well-being.

Objective:

The aim of this study was to investigate the feasibility and scalability of embedding smartphone-based digital phenotyping in large epidemiological cohorts by examining participant adherence to a smartphone-based data collection protocol in two ongoing nationwide prospective cohort studies.

Methods:

The participants (N = 2,394) of the Beiwe Sub-study of Nurses’ Health Study 3 (NHS3) and Growing Up Today Study (GUTS) were followed for over a year. During this time, they completed questionnaires every 10 days, delivered via the Beiwe smartphone application, covering topics such as emotions, stress/enjoy, physical activity, green space, pets, diet (vegetables, meats, beverages, nuts and dairy, and fruits), sleep and sitting. These questionnaires aimed to measure participants’ key health behaviors, to combine with objectively assessed high-resolution GPS and accelerometer data provided by participants during the same time period.

Results:

Between July 2021 and June 2023, we had received 11.1 terabytes of GPS and accelerometer data from 2,394 participants and 23,682 survey responses. The average follow-up time for each participant was 214 days (SD=148). During this period, participants provided an average of 14.8 valid hours (SD=5.9) of GPS data and 13.2 valid hours (SD=4.8) of accelerometer data. Using a 10-hour cutoff, we found that 45% and 44% of participants had >50% of data collection days that were valid for GPS and accelerometer data, respectively. In addition, each participant submitted an average of 10 surveys during the same period (SD=11), with a mean response rate of 36% across all surveys (SD=17, median=41). After initial processing of GPS and accelerometer data, we also found that participants spent an average of 14.6 hours per day at home and 1.6 hours per day on trips. We also recorded an average of 1046 steps per day (SD=1029).

Conclusions:

In this study, smartphone-based digital phenotyping technology was used to collect intensive longitudinal data on lifestyle and behavioral factors in two well-established prospective cohorts. Our initial assessment of adherence to smartphone-based data collection protocols over one year suggests that adherence rates in our study were either higher or similar to most previous studies with much shorter follow-up periods and smaller sample sizes. Our efforts have resulted in a large data set on health behaviors that can be linked to spatial datasets to examine environmental and behavioral drivers for chronic disease.