Machine Learning Model for Predicting Suicide Risks Among Patients With Posttraumatic Stress Disorder Who Received Opioids
Shu Huang, Amie J. Goodin, Jill A. Star, Serena Jingchuan Guo, Jiang Bian, Jie Xu, Tianze Jiao · 2026
Read Machine Learning Model for Predicting Suicide Risks Among Patients With Posttraumatic Stress Disorder Who Received Opioids by Shu Huang, Amie J. Goodin, Jill A. Star, Serena Jingchuan Guo, Jiang Bian, Jie Xu, Tianze Jiao (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/PMC13420204.txt.
Description
Huang and co-authors build a suicide risk predictor in this 2026 study for a doubly vulnerable group: patients who have both posttraumatic stress disorder and opioid prescriptions. Using Florida health data from the OneFlorida+ network, they trained machine learning models to flag suicide-related outcomes within six-month windows.
The development cohort held 5,578 patients, of whom 709, or 12.7 percent across follow-up, experienced a suicide-related outcome. A random forest model performed best. It reached a C-statistic of 83.6 percent internally. It hit the same figure in an external 2019 to 2021 cohort of 4,849 patients. In plain terms, it ranked a random patient who later had an outcome above one who did not about five times in six. Sorting patients into ten risk bands concentrated 79.2 percent of suicide intervals in the top three bands, a triage pattern clinics could act on.
Catalog record
| CREATOR | Shu Huang, Amie J. Goodin, Jill A. Star, Serena Jingchuan Guo, Jiang Bian, Jie Xu, Tianze Jiao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |