New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research

Abstract

BackgroundA longstanding barrier to progress in psychiatry, both in clinical settings and research trials, has been the persistent difficulty of accurately and reliably quantifying disease phenotypes. Mobile phone technology combined with data science has the potential to offer medicine a wealth of additional information on disease phenotypes, but the large majority of existing smartphone apps are not intended for use as biomedical research platforms and, as such, do not generate research-quality data.ObjectiveOur aim is not the creation of yet another app per se but rather the establishment of a platform to collect research-quality smartphone raw sensor and usage pattern data. Our ultimate goal is to develop statistical, mathematical, and computational methodology to enable us and others to extract biomedical and clinical insights from smartphone data.MethodsWe report on the development and early testing of Beiwe, a research platform featuring a study portal, smartphone app, database, and data modeling and analysis tools designed and developed specifically for transparent, customizable, and reproducible biomedical research use, in particular for the study of psychiatric and neurological disorders. We also outline a proposed study using the platform for patients with schizophrenia.ResultsWe demonstrate the passive data capabilities of the Beiwe platform and early results of its analytical capabilities.ConclusionsSmartphone sensors and phone usage patterns, when coupled with appropriate statistical learning tools, are able to capture various social and behavioral manifestations of illnesses, in naturalistic settings, as lived and experienced by patients. The ubiquity of smartphones makes this type of moment-by-moment quantification of disease phenotypes highly scalable and, when integrated within a transparent research platform, presents tremendous opportunities for research, discovery, and patient health.

Using Mobile Phone Sensor Technology for Mental Health Research: Integrated Analysis to Identify Hidden Challenges and Potential Solutions (Preprint)

“…Further, the extent to which the participants' sequence of locations followed a 24-hour, or circadian, rhythm was also associated with depression, with greater circadian movement linked to a lower depression severity. In our study, location data was captured at varied intervals (8,5,4, and 3 minutes) from participants throughout Australia (Fig. 4A).…”

“…Because the collection of sensor data involves large quantities of individualised social and behavioural data, security and privacy have been recognised as a high priority [8,9].…”

“…Identifying data should be hashed and all data should be encrypted [8]. However, these necessary protections are challenging because of the vast amounts of detailed longitudinal data that are routinely collected for each individual [44].…”

“…Patient safety should also be built into the design of data collection apps. Some practitioners have emphasised the importance of including contacts for medical professionals or other services in case of emergency or the need for immediate help [8]. Patients should be made aware of the standard turnaround time for a response to requests for help from system operators [2].…”

“…The Beiwe Research Platform was developed at Harvard University to collect research-quality data from smartphone sensors and use patterns on both Android and iOS platforms. The app collects a range of sensor data including GPS, accelerometer, communication logs, Wi-Fi and Bluetooth (Android only), and battery use [8].…”