Depression prediction and key factors: A comparative analysis of logistic regression and machine learning models
Kripa Josten, Vennila Jaganathan · 2026
Read Depression prediction and key factors: A comparative analysis of logistic regression and machine learning models by Kripa Josten, Vennila Jaganathan (2026) 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/plos-pone-0354668.txt.
Description
Kripa Josten and Vennila Jaganathan compared old-fashioned statistical regression against ten machine learning models for predicting depression, using survey data from the World Health Organization's aging study in India. Their 2026 analysis weighed social, health, and psychological factors, asking both which factors matter and which method predicts best for screening programs.
Depression was more common among younger adults, women, and people reporting poor health, stress, and broken sleep. The machine learning models were only modestly accurate, barely beating chance-adjusted expectations, and a regularized regression actually topped the list. Across all methods, age, self-rated health, quality of life, and low mood itself carried the signal. The authors recommend pairing interpretable regression with machine learning rather than trusting either alone.
Catalog record
| CREATOR | Kripa Josten, Vennila Jaganathan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29551 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |