Related Experiment Video
Updated: Jan 10, 2026
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
3.2K
An exploratory study on predicting depressive symptoms in autistic individuals using wearable devices and machine
Shih-Ying Ni1, Chen-Chun Lu2, Chia-Tung Wu2
1Department of Psychiatry, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan.
Journal of the Formosan Medical Association = Taiwan Yi Zhi
|November 20, 2025
Summary
Wearable devices can monitor depressive symptoms in autistic adults using machine learning. Lower activity, sleep, and heart rate predict depression, aiding early detection and self-care.
Area of Science:
- Neuroscience
- Digital Health
- Machine Learning
Background:
- Autistic adults face challenges in communicating and expressing emotions, complicating depression monitoring.
- Early detection of depressive symptoms in autism is crucial for timely intervention.
Purpose of the Study:
- To leverage digital biomarkers from wearable devices for monitoring depressive symptoms in autistic adults.
- To develop machine learning models for early detection of depression in this population.
Main Methods:
- Prospective observational study with 17 autistic adults.
- Continuous collection of physiological data (activity, heart rate, sleep) via smartwatches.
- Application of machine learning (XGBoost) to longitudinal data and self-rated depressive symptoms (Beck Depression Inventory).
Main Results:
- The XGBoost model achieved 84% accuracy and an AUROC of 0.91 in identifying depressive states.
- Key digital biomarkers predicting depression included lower activity levels, decreased sleep duration, and reduced average heart rate.
- Feature importance analysis identified these physiological changes as significant indicators.
Conclusions:
- Digital phenotypes from wearable devices show promise for detecting depressive symptoms in autistic adults.
- This approach can potentially enhance clinical assessments and support emotion self-care strategies.
- Wearable technology offers a novel avenue for objective monitoring of mental health in autism spectrum disorder.
