AbstractBackgroundIn older adults, circadian rhythms show alterations in multiple dimensions with aging and during Alzheimer’s dementia progression. We propose that circadian function may serve as a unique gauge of biological age (i.e., circadian age), and that individuals with greater circadian age than chronological age have increased risk of Alzheimer’s dementia.MethodWe constructed a regression model with chronological age as the predicting target. The model prediction was termed circadian age. A softplus activation function was used to ensure positivity. The model was optimized to minimize the mean‐squared prediction error while penalizing the covariance between chronological age and prediction error. Cosinor analysis, nonparametric analysis, uniform phase empirical mode decomposition, and detrended fluctuation analysis were performed on baseline actigraphy data of 882 participants (age: 80.1±7.3; female/male: 692/190) from the Rush Memory and Aging Project who were cognitively intact and were not taking sleep medications. These analyses resulted in 23 features for circadian daily activity patterns as model inputs. The optimal model was trained through cross‐validation for the penalization parameter and applied to follow‐up actigraphy data. We compared circadian age among participants at different cognitive stages, evaluated the longitudinal change of circadian age, and examined the association of circadian age with incident Alzheimer’s dementia.ResultChronological age explained 24.8% of the variance in circadian age. At analytical baseline, participants with Alzheimer’s dementia had significantly greater circadian–chronological age deviation (CCD) than cognitively normal participants (2.98±1.43 vs. ‐0.13±0.42 years, p=0.04). For each 1‐year increase in chronological age, circadian age increased by 1.05±0.06 years (p<0.001), suggesting accelerated circadian aging. Among baseline cognitively normal participants, greater CCD was associated with an increased risk of Alzheimer’s dementia independent from chronological age, sex, total daily activity, sleep fragmentation, vascular disease and risk factors, and depressive symptoms. For a 10‐year increase in CCD, the hazard ratio was 1.23 (95% CI: 1.06‐1.42).ConclusionCircadian daily patterns can be integrated to predict chronological age. Older circadian age than chronological age is an independent risk factor for Alzheimer’s dementia. Future work should refine the determination of health status for training dataset and examine whether circadian age links with endogenous circadian function.