An explainable machine learning framework for analyzing and predicting mental health problems among university students in Bangladesh
Mst Nilufar Yasmin, Mohammad Mizanur Rahman, Nusrat Y Ahmed, Amrin Binte Ahmed, Adisha Dulmini, Muhammad Khairul Alam, Atikur Rahman, Rumana Rois · 2026
Read An explainable machine learning framework for analyzing and predicting mental health problems among university students in Bangladesh by Mst Nilufar Yasmin, Mohammad Mizanur Rahman, Nusrat Y Ahmed, Amrin Binte Ahmed, Adisha Dulmini, Muhammad Khairul Alam, Atikur Rahman, Rumana Rois (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-13396588.txt.
Description
Nilufar Yasmin and co-authors apply, in a 2026 study, machine learning that can show its work to mental health data from students in Bangladesh. They stress care in how such tools are read: the sample was not drawn by chance, and it holds one point in time. The survey ran in July 2024, a time of unrest, and held 424 students. Rates of mid to grave signs were high: about 66 percent for low mood, 73 percent for anxiety, and 52 percent for stress. Near half the group met the bar for all three at once.
Eight models were tested with split runs and cross checks. One model type held steady for low mood and stress; a second did best on anxiety. Two tools that open the model's logic flagged sleep trouble, thought complaints, and behavior strain as top inputs.
Catalog record
| CREATOR | Mst Nilufar Yasmin, Mohammad Mizanur Rahman, Nusrat Y Ahmed, Amrin Binte Ahmed, Adisha Dulmini, Muhammad Khairul Alam, Atikur Rahman, Rumana Rois |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |