0
0
A groundbreaking study has introduced an AI-powered solution for nonintrusive mental health monitoring.
A new study published in JMIR Aging has developed and tested an artificial intelligence (AI) model named HOPE, which utilizes Wi-Fi-based motion sensor data to detect depression in older adults. This innovative approach eliminates the need for intrusive wearable devices and provides a promising alternative for mental health monitoring.
The research, led by Professor Samira A. Rahimi from McGill University and the Mila-Quebec AI Institute, explored whether everyday movement and sleep patterns collected through Wi-Fi-based sensors could serve as early indicators of depression in adults aged 65 and older. With an impressive accuracy rate exceeding 87%, this technology presents a potential breakthrough for early intervention in mental health care.
Addressing a Growing Mental Health Concern
Depression is a significant public health issue among older adults, affecting an estimated 10–15% of community-dwelling seniors and 30–40% of individuals in long-term care facilities. Unfortunately, nearly half of depression cases remain undiagnosed, leading to adverse effects such as declining physical health, increased hospitalizations, and diminished quality of life.
Traditional diagnostic methods, including clinical interviews and wearable-based monitoring, often pose challenges due to resource constraints, invasiveness, and difficulties in technology adoption among older individuals. The HOPE model addresses these limitations by leveraging existing Wi-Fi infrastructure to enable passive and continuous monitoring without requiring active participation from users.
Explainable AI and Sleep as Key Indicators
A notable feature of the HOPE model is its use of explainable AI (XAI) techniques, ensuring transparency and clinical interpretability. Rahimi’s research team incorporated machine learning models that identified the most influential factors in depression detection.
Findings from the study emphasized the critical role of sleep-related factors in predicting depression. Key indicators included sleep duration, frequency of sleep interruptions, and frailty levels. These insights align with prior research linking sleep disturbances to mental health conditions and highlight the need for further investigation in this area.
Professor Rahimi underscored the significance of this research, stating, “Too often, the mental health of older adults is overlooked, leaving many to suffer in silence. Our HOPE model acts as a caring companion, using everyday Wi-Fi data to detect early signs of depression in a nonintrusive manner. It’s about leveraging technology to offer a helping hand, particularly for those who may struggle to reach out.”
Implications and Future Research
The study demonstrates the potential of smart home technology in mental health assessments. While the results are promising, researchers emphasize the need for larger-scale studies to validate and refine this approach. If further validated, this technology could support early intervention efforts and significantly improve the well-being of older adults at risk of depression.
Disclaimer
This article is for informational purposes only and does not constitute medical advice. Individuals experiencing mental health concerns should consult a qualified healthcare professional for proper diagnosis and treatment.
For more details, refer to the original study: Shayan Nejadshamsi et al., Development and Feasibility Study of HOPE Model for Prediction of Depression Among Older Adults Using Wi-Fi-based Motion Sensor Data: Machine Learning Study, JMIR Aging (2025). DOI: 10.2196/67715.
