JMIR Publications

ABSTRACT

Background:

Wearable technology is used by consumers worldwide for continuous activity monitoring in daily life but more recently also for classifying or predicting mental health parameters like stress or depression levels. Previous studies identified based on traditional approaches that physical activity is a relevant factor in the prevention or management of mental health. However, upcoming artificial intelligence methods have not yet been fully established in the research field of physical activity and mental health.

Objective:

This systematic review aims to provide a comprehensive overview of studies that integrated passive monitoring of physical activity data measured via wearable technology in machine learning algorithms for the detection, prediction, or classification of mental health states and traits.

Methods:

We conducted a review of studies processing wearable data to gain insights into mental health parameters. Eligibility criteria were: (i) the study uses wearables and/or smartphones to acquire physical behaviour and optionally other sensor measurement data; (ii) the study must use machine learning to process the acquired data; (iii) the study had to be published in a peer-reviewed English language journal. Studies were identified via a systematic search in five electronic databases.

Results:

Out of 11,057 unique search results, 49 published articles between 2016 and 2023 were included. Most studies examined the connection between wearable sensor data and stress (30.6% (N=15)) or depression (28.6% (N=14)). 71.4% (N=35) of the studies had less than 100 participants and 46.9% (N=23) had less than 14 days of data recording. More than half of the studies (55.1% (N=27)) used step count as movement measurement, 42.9% used raw accelerometer values. The quality of the studies was assessed scoring between 0 and 18 points in 9 categories (max. 2 points per category). On average studies were rated 6.47 (±3.1) points.

Conclusions:

The use of wearable technology for the detection, prediction, or classification of mental health states and traits is promising and offers a variety of applications across different settings and target groups. However, based on the current state of literature the application of artificial intelligence cannot realise its full potential mostly due to a lack of methodological shortcomings and data availability. Future research endeavours may focus on the following suggestions to improve the quality of new applications in this context. First, by using raw data instead of already pre-processed data. Second, by using only relevant data based on empirical evidence. In particular, crafting optimal feature sets rather than using many individual detached features and consultation with in-field professionals. Third, by validating and replicating the existing approaches (i.e., applying the model to unseen data). Fourth, depending on the research aim (i.e., generalization vs. personalization) maximizing the sample size and/or the duration over which data is collected.