BACKGROUND
A popular trend in depression forecasting research is the development of machine learning (ML) models trained with various types of smartphone sensor data and periodic self-ratings to derive early indications of changes in depression severity. While most works focus on model performance, there is little concern about the universal usability and reliable operation of such systems across smartphone platforms. This review is a part of the MENTBEST subproject MENTINA trial exploring smartphone-based health self-management for depression. The usability and reliability of mobile applications for depression is commonly perceived through the lens of the approaches and interventions offered rather than the reliability of the built-in mobile phone functions to support effortless and exact delivery of intended interventions.
OBJECTIVE
This work aimed to provide an overview of cross-platform-available smartphone data streams for the strong design and operation of digital depression indication systems that rely on objective data patterns related to depression severity changes.
METHODS
To identify the already used hard- and software sensors and their purposes in mental health monitoring, an umbrella literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Three electronic databases including PubMed, Web of Science Core Collection, and Scopus were searched using smartphone, sensor data, and depression keyword combination to retrieve relevant literature reviews published within the past five years (2019-2024). Once the initial search was completed, the extracted hardware sensors were checked for availability on Android and iOS smartphones by analyzing device specifications in the PhoneDB over the past ten years.
RESULTS
The resulting data streams observed across studies include sixteen hardware and three software data streams. Hardware data streams include accelerometer, barometer, battery level, Bluetooth, camera, cell, GPS, gyroscope, humidity, light, magnetometer, proximity, sound, step count, temperature, and Wi-Fi. Software data streams include app usage, call and message logs, and screen status. Hardware component availability on Android and iOS systems shows the changes in component trends from 2014 to 2024 as of September 2024 with the accelerometer, battery, camera, and GPS being consistent on Android and iOS while components such as gyroscope, step counter, and barometer where gradually increasing over the years, particularly on Android.
CONCLUSIONS
Multiple data streams observed across literature reviews have been consistently growing in availability across time, allowing better utilization of such outputs for depression forecasting and training machine learning models with a variety of smartphone data including smartphone sensor data. For more precise and reliable data to be utilized in the mental health field, particularly in critical areas such as tracking and predicting changes in depression severity further research is required to streamline smartphone data across varying mobile hardware and software configurations to provide reliable output for digital mental health purposes.
