Domain adaptive uplift modeling across heterogeneous mental health cohorts
Abdullah Nayem Wasi Emran, A. B. M. Alim Al Islam · 2026
Read Domain adaptive uplift modeling across heterogeneous mental health cohorts by Abdullah Nayem Wasi Emran, A. B. M. Alim Al Islam (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/pmc-13224034.txt.
Description
Abdullah Nayem Wasi Emran and A. B. M. Alim Al Islam test a 2026 machine-learning model that predicts who is most likely to worsen under stress, so mental-health support can be aimed where it helps most. Such uplift models are seldom checked across very different populations. Their test covered 2,624 people drawn from medical students, quarantined members of the public, and psychiatric patients.
Leaving one group out at a time, the authors compared plain training with four ways of adapting the model to a new population. Ranking worked positively in two groups, but the effect signal flipped sign in psychiatric patients. Adaptation brought only modest, tuning-sensitive gains, so the authors urge caution before deploying such models across cohorts.
Catalog record
| CREATOR | Abdullah Nayem Wasi Emran, A. B. M. Alim Al Islam |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 91 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |