0195 Integrated actigraphy-based biomarker for the risk of Alzheimer’s dementia
Bibliographic record
Abstract
Abstract Introduction Many physiological measures derived from actigraphy including physical activity, sleep, circadian/daily rhythm, and temporal correlations have been shown to predict Alzheimer’s dementia (AD). This study aimed to combine these actigraphy-based measures to develop an integrated actigraphy biomarker (IAB) for AD and to test its link to the genetic risk for AD. Methods We analyzed data of 1107 participants (age 80.9±7.3(mean±SD)) from the Rush Memory and Aging Project who were non-demented and had actigraphy (~10 days) at baseline, and had annual cognitive assessment during the follow-up (1-15 years). 270 developed AD (mean = 7.4 years). To construct the IAB for the AD’s risk, we trained a random forest survival model, in which time to incident AD was the outcome, and inputs included 10 features derived from actigraphy data: physical activity level, 3 features for sleep (sleep duration, sleep fragmentation, activity fragmentation), 4 features for circadian rhythmicity (amplitude, acrophase, interdaily stability, and intradaily variability of 24-hr rhythms), and 2 features for temporal correlations (at timescales between 1-90 min and 120-480 min). Polygenic risk score (PRS) was calculated using 457 independent SNPs strongly associated with Alzheimer’s disease (p<0.001). Cox proportional hazard ratio models were performed with different combinations of IAB, PRS, age, sex, and education, and the concordance score (C-score) was used to evaluate model performance. Results The derived IAB was 0.6 SD larger in the AD group as compared with the controls. The IAB alone achieved a C-score = 0.61 in predicting AD, with a hazard ratio=1.5 for 1-SD increase in IAB. The IAB and PRS were not correlated (r2=0.0004, p=0.25), and both significantly contributed to the prediction (both p<=0.0001) when included in one model, giving a C-score of 0.65. C-score was 0.7 in the model using only age, sex and educations yielded, and increased to 0.74 after including IAB and PRS (both effects remained significant p<0.0001). Conclusion The integrated actigraphy biomarker may provide complementary information for early prediction and detection of AD, independent of the known demographic and genetic risk factors. Support (If Any) NIH (RF1AG064312, RF1AG059867, R01AG56352, R01AG17917, T32GM007592, and R03AG067985); The BrightFocus Foundation (A2020886S).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".