Prediction of Incident Alzheimer's Disease in Older Community‐Dwelling Adults using Wrist Accelerometry and Deep Learning
Julie Midroni, Lei Yu, Jennifer S Rabin, Xilin Liu, Maged Goubran, Aron S Buchman, David A Bennett, Andrew Lim · 2025
Read Prediction of Incident Alzheimer's Disease in Older Community‐Dwelling Adults using Wrist Accelerometry and Deep Learning by Julie Midroni, Lei Yu, Jennifer S Rabin, Xilin Liu, Maged Goubran, Aron S Buchman, David A Bennett, Andrew Lim (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11716780.txt.
Description
Julie Midroni and co-authors predict Alzheimer disease years ahead from wrist motion data plus simple personal facts, in work from twenty twenty-five. Drugs work best before symptoms, but brain scans cost too much for mass screening. A wrist sensor worn ten days records daily activity rhythms. A neural network fuses those rhythms with easy clinical facts. Cohort elders without dementia at recording form the study base.
The fused model catches most future cases in the test group. Its balance of misses and false alarms beats single-source models. Motion-only and facts-only networks both trail the combination clearly. Accuracy holds for those with and without mild impairment. Survival analysis confirms the output tracks disease-free years. Cheap wrist screening could triage who needs costly scans.
Catalog record
| CREATOR | Julie Midroni, Lei Yu, Jennifer S Rabin, Xilin Liu, Maged Goubran, Aron S Buchman, David A Bennett, Andrew Lim |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |