FEATURES OF LEARNING FROM HIGH-FREQUENCY COGNITIVE ASSESSMENTS AS DIGITAL BIOMARKERS OF COGNITIVE CHANGE
Zita Oravecz, Joachim Vandekerckhove, Cuiling Wang, Mindy Katz, Jonathan Hakun, Martin Sliwinski · 2023
Read FEATURES OF LEARNING FROM HIGH-FREQUENCY COGNITIVE ASSESSMENTS AS DIGITAL BIOMARKERS OF COGNITIVE CHANGE by Zita Oravecz, Joachim Vandekerckhove, Cuiling Wang, Mindy Katz, Jonathan Hakun, Martin Sliwinski (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-10736254.txt.
Description
Phones and wearables can test thinking skills many times a day, producing dense bursts of data that may flag cognitive decline early. Zita Oravecz and co-authors build a statistical model to read such data well. In these measurement burst designs, people repeat tests several times daily for days, and the bursts repeat over years. The raw scores mix several processes at once: genuine aging, learning from practice, warm up within each burst, and day to day wobble.
Their Bayesian model separates those threads for each person. It estimates how much someone gains from practice between bursts, how fast they warm up, where their peak performance sits, and how that peak drifts over time. These personal features are then linked, in the same analysis, to life circumstances and to biological markers of decline. The authors show how the model yields probability statements about whether a given person is declining.
Catalog record
| CREATOR | Zita Oravecz, Joachim Vandekerckhove, Cuiling Wang, Mindy Katz, Jonathan Hakun, Martin Sliwinski |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 1 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |