Using machine learning to predict the probability of incident 2-year depression in older adults with chronic diseases: a retrospective cohort study
Ying Zheng, Taotao Zhang, Shu Yang, Fuzhi Wang, Li Zhang, Yuwen Liu · 2024
Read Using machine learning to predict the probability of incident 2-year depression in older adults with chronic diseases: a retrospective cohort study by Ying Zheng, Taotao Zhang, Shu Yang, Fuzhi Wang, Li Zhang, Yuwen Liu (2024) 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-11610371.txt.
Description
Ying Zheng and colleagues build machine learning models to flag which chronically ill older adults will be depressed within two years, in this study from twenty twenty-four. The data come from China's national aging survey: seven thousand one hundred twenty-one participants with chronic disease, of whom about twenty-one percent developed depressive symptoms over the window.
Four algorithms competed. The winner was unfashionable: logistic regression, fattened with synthetic minority oversampling to handle the imbalance. It validated respectably on a later survey wave. The predictive handful was human, not molecular: sex, self-rated health, occupation, eyesight, memory, and life satisfaction. Discrimination stayed modest, as the authors admit, but calibration was honest. They offer the model as a triage sieve for community health workers, to catch risk while intervention is still cheap.
Catalog record
| CREATOR | Ying Zheng, Taotao Zhang, Shu Yang, Fuzhi Wang, Li Zhang, Yuwen Liu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |