Artificial Intelligence-Based Monitoring Devices for the Identification of Circadian Parameters as Digital Predictive Biomarkers of Neurodegenerative Diseases in Older Adults: A Systematic Review
ABSTRACT
Background:
Neurodegenerative diseases such as Alzheimer's, Parkinson's, and multiple sclerosis are increasing globally, particularly among older adults. Disruptions in circadian rhythms have been associated with the progression of these diseases. Recent advances in wearable technologies and artificial intelligence (AI) offer novel tools for monitoring circadian parameters, potentially serving as digital biomarkers for neurodegenerative conditions.
Objective:
This systematic review aims to synthesize current evidence on the use of wearable devices combined with AI for monitoring circadian rhythms in older adults, and to evaluate their potential application as digital biomarkers in the context of neurodegenerative diseases.
Methods:
A systematic literature search was conducted in June 2025 across PubMed, Scopus, and JMIR databases, targeting studies published in English or Spanish between 2015 and 2025. The search strategy focused on terms related to wearable devices, circadian data, aging, and AI. Studies involving older or aging populations and evaluating AI-based wearables for circadian monitoring were included (n = 12). Data extraction followed PRISMA 2020 guidelines, encompassing study characteristics, device types, circadian parameters, AI methods, and primary findings, no formal risk-of-bias assessment was conducted due to heterogeneity.
Results:
The review included a wide range of wearable technologies, such as wrist-worn actigraphy, EEG headbands, and multisensor chest patches. These devices extracted circadian parameters including interdaily stability (IS), intradaily variability (IV), MESOR, amplitude, and acrophase. AI methods ranged from supervised models (e.g., logistic regression) to unsupervised clustering techniques. Several studies reported associations between disrupted circadian rhythms and increased risk of neurodegenerative outcomes. However, limitations such as reduced accuracy in advanced disease stages, lack of algorithm transparency, and underrepresentation of diverse populations were noted.
Conclusions:
Wearable technologies enhanced by AI demonstrate potential for the non-invasive monitoring of circadian rhythms in older adults and may serve as digital biomarkers of neurodegeneration. Future research should focus on longitudinal validation, integration of multimodal sensors, and implementation of explainable and ethically compliant AI methods to enable broader clinical applicability.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.