Wearable Sensors Accurately Assess Circadian Light Exposure for Nursing Home Residents with Dementia

A study conducted at the New Jersey Institute of Technology has found that wearable sensors can accurately measure and predict individual circadian light exposure for nursing home residents with dementia. The research used a combination of laboratory experiments and on-site data collection to develop and validate calibration and predictive models for assessing circadian lighting exposure. The findings highlight the significance of customized lighting evaluations and the potential for wearable sensors to support health care research and interventions.

Key Takeaways:

• The study used a combination of controlled laboratory experiments and on-site data collection to develop and validate calibration and predictive models for assessing circadian lighting exposure.
• Wearable sensors were found to accurately measure and predict individual circadian light exposure, with a strong accuracy (adjusted R² of 0.858 and 0.982) for photopic lux and correlated color temperature calibration models.
• Predictive models for circadian stimulus were developed using both simple regression and machine learning techniques, with the random forest model outperforming linear regression and achieving an adjusted R² of 0.915 and a cross-validation R² of 0.857.
• The study found significant individual variations in circadian light exposure, highlighting the need for customized lighting evaluations for nursing home residents with dementia.
• Challenges related to sensor wearability, durability, and user compliance were identified, underscoring the need for further sensor design refinements.
• Future research should focus on refining sensor integration, expanding case studies, and developing adaptive lighting interventions to enhance circadian health in vulnerable populations.

Statistics:

• The study was conducted at 2 assisted-living facilities and used professional spectrophotometer measurements as ground truth.
• The calibration models for photopic lux and correlated color temperature demonstrated strong accuracy, with an adjusted R² of 0.858 and 0.982, respectively.
• The random forest model for circadian stimulus achieved an adjusted R² of 0.915 and a cross-validation R² of 0.857.
• The study found significant individual variations in circadian light exposure, with a range of 3.5 to 12.6 lux/hour.
• The proposed methodology enables continuous, cost-effective monitoring of circadian light exposure in health care environments.

Sources:

• NewsRx. Investigators at New Jersey Institute of Technology Target Dementia (Using Wearable Sensors to Measure and Predict Personal Circadian Lighting Exposure in Nursing Home Residents: Model Development and Validation). Mental Health Weekly Digest. October 20, 2025; p 395.
• Using Wearable Sensors to Measure and Predict Personal Circadian Lighting Exposure in Nursing Home Residents: Model Development and Validation. Jmir Aging, 2025;8. Jmir Publications, Inc, 130 Queens Quay East, Unit 1100, Toronto, On M5A 0P6, Canada.