Explainable AI for mental health emergency returns: integrating large language models with predictive modeling
Abdulaziz Ahmed, Mohammad Saleem, Mohammed Alzeen, Badari Birur, Rachel E Fargason, Bradley G Burk, Ahmed Alhassan, Mohammed Ali Al-Garadi · 2026
Read Explainable AI for mental health emergency returns: integrating large language models with predictive modeling by Abdulaziz Ahmed, Mohammad Saleem, Mohammed Alzeen, Badari Birur, Rachel E Fargason, Bradley G Burk, Ahmed Alhassan, Mohammed Ali Al-Garadi (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/PMC13278837.txt.
Description
Abdulaziz Ahmed leads a 2026 study that joins large language models with machine learning to predict mental health returns to the emergency department. Repeat emergency visits for mental health conditions burden hospitals, and standard prediction models are hard to interpret. The team analyzed more than forty-two thousand visits by nearly twenty-eight thousand patients at one academic center from 2018 to 2022.
A language model sorted chief complaints and social factors, such as substance use and home environment, from free text with strong accuracy. Adding those features to a standard model improved prediction modestly. A hybrid explanation framework, blending the model with language-based context, made risk outputs far easier to interpret at patient and population levels.
Catalog record
| CREATOR | Abdulaziz Ahmed, Mohammad Saleem, Mohammed Alzeen, Badari Birur, Rachel E Fargason, Bradley G Burk, Ahmed Alhassan, Mohammed Ali Al-Garadi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71726 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |