AI-model flags suicide-related behaviour per 1000 ER visits (IMAGE)
Caption
Table showing true/false positives/negatives per 1000 visits, based on the AI confusion matrix in Figure 3 of the research study.
Researchers from the University of Johannesburg (UJ) have published a promising AI-based approach for early detection of people at risk of suicide-related behaviour (SRB) visiting hospital Emergency Rooms (ERs) in the journal Scientific Reports. (https://doi.org/10.1038/s41598-026-64073-y )
The study describes using an AI algorithm, routine patient intake data, and light-weight computing to estimate SRB. The model is intended to assist ER staff, rather than replace them, during very busy periods at resource-constrained hospitals.
Credit
Therese van Wyk, University of Johannesburg (UJ)
Usage Restrictions
Credit must be given to the creator. No derivatives or adaptations of the work are permitted.
License
CC BY-ND