A biological age biomarker based on circadian rest‐activity rhythms and risk of dementia
Peng Li, Lei Gao, Haoqi Sun, Chenlu Gao, Ruixue Cai, Martin K Rutter, Kun Hu- Psychiatry and Mental health
- Cellular and Molecular Neuroscience
- Geriatrics and Gerontology
- Neurology (clinical)
- Developmental Neuroscience
- Health Policy
- Epidemiology
Abstract
Background
Circadian function is altered with aging, leading to changes in the ∼24‐h rhythms of behavior and physiology. Based on circadian rest‐activity rhythms (CRAR), we previously constructed a biological age biomarker to characterize the aging profile of circadian function—circadian age (CircAge)—in older adults (>65 years) and showed its association with risk of Alzheimer’s dementia. Here, we constructed CircAge in middle‐to‐older‐aged adults and tested whether it predicts all‐cause dementia.
Method
Participants from the UK Biobank with valid actigraphy data were studied (n = ∼97,000; 42‐78 years old). We developed a machine‐learning‐based regression model with 23 CRAR features derived from actigraphy (using cosinor, nonparametric, uniform‐phase‐empirical‐mode‐decomposition, and detrended‐fluctuation analyses). The fitting target was chronological age (ChrAge), and the prediction output was defined as CircAge. Model parameters were optimized using cross validation on 47,234 participants not performing shift work and without mental/behavioral or nervous system diseases. The optimized model was applied to all dementia‐free participants with valid CRAR (n = 80,805) to obtain their CircAge.
Result
CircAge was 1.03±0.01 years older per one‐year older in ChrAge that explained ∼25% of the variance of CircAge (p<0.0001). Male sex, European ethnicity, or having mental/behavioral/nervous system diseases were associated with a greater CircAge (all p<0.0001). We compared CircAge of current shift workers (n = 6,389) with that of matched non‐shift workers to examine whether CircAge captures CRAR perturbations and found that CircAge of current shift workers was 1.1±0.2 years greater (p<0.0001) than non‐shift workers. We then associated the difference between CircAge and ChrAge (DCC, = CircAge‐ChrAge) to incident all‐cause dementia using a Cox proportional hazards model adjusting for ChrAge, sex, ethnic groups, mental/behavioral diseases, and nervous system diseases. Results showed that greater DCC predicted higher adjusted risk of all‐cause dementia (n = 451): each decade higher DCC corresponding to a 1.10‐fold higher risk (95% CI: 1.02‐1.18; p = 0.009).
Conclusion
CRAR patterns can be translated into a biological aging biomarker for circadian function (CircAge), and greater CircAge than ChrAge is independently associated with risk of dementia in middle‐to‐older‐aged adults. Future studies are warranted to examine the use of CircAge (and/or in combination with other risk markers) for identifying at‐risk individuals in a clinical setting.