Deep learning models can predict violence and threats against healthcare providers using clinical notes
Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black · 2024
Read Deep learning models can predict violence and threats against healthcare providers using clinical notes by Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black (2024) 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-11621531.txt.
Description
Nicholas Dobbins and co-authors predict assaults on healthcare staff from chart text in a 2024 clinical informatics study. Violence and threats from patients drive turnover and distress across hospitals, yet warnings usually come too late to act on.
Two deep learning models forecast violent events three days ahead: one reading free-text clinical notes, one using structured data. The notes model edged out the structured one, and both clearly beat a psychiatry team reviewing the same files. A companion model tagged the note phrases driving risk, keeping the system explainable. The authors present it as an early-warning layer for staff safety.
Catalog record
| CREATOR | Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |