All commonly used smartphones contain a similar set of sensors (e.g. Accelerometer, Bluetooth, GPS, Light sensor, Microphone) along with a set of electronic logs (App Use, Web History, Battery, Call Logs, Screen, Keyboard/UI, SMS/Email) which allow a certain insight into the behavioral patterns of the phone’s user. Notably, all this data can be collected passively and does not require any effort on the patient’s side besides installing the application. This results in the continuous collection of objective behavioral data. The collected data can be analyzed in various ways to infer behaviors such as mobility and activity as proxies for a patient’s functioning and well-being.

Digital Phenotyping using passive mobile phone sensors has been shown to be useful for a wide variety of clinical purposes including the monitoring of the day-by-day symptom severity in patients receiving chemotherapy [1], prediction of relapses in schizophrenic patients [2], estimation of depressive symptom severity [3] and monitoring the mobility of patients suffering from spine disease [4].

References:

1. Low CA, Dey AK, Ferreira D, et al. Estimation of Symptom Severity During Chemotherapy From Passively Sensed Data: Exploratory Study. J Med Internet Res. 2017;19(12):e420.

2. Barnett I, Torous J, Staples P, Sandoval L, Keshavan M, Onnela JP. Relapse prediction in schizophrenia through digital phenotyping: a pilot study. Neuropsychopharmacology. 2018;43(8):1660-1666.
 

3. Saeb S, Zhang M, Karr CJ, et al. Mobile Phone Sensor Correlates of Depressive Symptom Severity in Daily-Life Behavior: An Exploratory Study. J Med Internet Res. 2015;17(7):e175.

4. Cote DJ, Barnett I, Onnela JP, Smith TR. Digital Phenotyping in Patients with Spine Disease: A Novel Approach to Quantifying Mobility and Quality of Life. World Neurosurg. 2019.