Predicting positron emission tomography brain amyloid positivity using interpretable machine learning models with wearable sensor data and lifestyle factors
Noriyuki Kimura, Tomoki Aota, Yasuhiro Aso, Kenichi Yabuuchi, Kotaro Sasaki, Teruaki Masuda, Atsuko Eguchi, Yoshitaka Maeda, Ken Aoshima, Etsuro Matsubara · 2023
Read Predicting positron emission tomography brain amyloid positivity using interpretable machine learning models with wearable sensor data and lifestyle factors by Noriyuki Kimura, Tomoki Aota, Yasuhiro Aso, Kenichi Yabuuchi, Kotaro Sasaki, Teruaki Masuda, Atsuko Eguchi, Yoshitaka Maeda, Ken Aoshima, Etsuro Matsubara (2023) 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-10714506.txt.
Description
Noriyuki Kimura and co-authors built models to predict brain amyloid from wearable sensors and lifestyle data in a 2023 paper. A cheap screen for high amyloid could cut costs and patient burden in Alzheimer trials and care. Their study followed older adults in a Japanese city who had mild memory problems or memory complaints but no dementia. Participants wore sensors, answered surveys, took thinking tests, and had brain scans.
Records from more than one hundred twenty people, with follow ups in later years, fed the learning models. Three model types were trained to call whether a scan showed high amyloid, set by a standard cut off. The models were built to stay readable, so users can see why a call was made. Scores were averaged over many rounds of cross checking. The work tests whether daily life data can flag who most needs a costly brain scan.
Catalog record
| CREATOR | Noriyuki Kimura, Tomoki Aota, Yasuhiro Aso, Kenichi Yabuuchi, Kotaro Sasaki, Teruaki Masuda, Atsuko Eguchi, Yoshitaka Maeda, Ken Aoshima, Etsuro Matsubara |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |