New research suggests that artificial intelligence (AI) may have the potential in the future to identify individuals at risk for suicide. By scanning patients' health history using AI, it may be possible to determine if there is an increased risk for suicide.
Researchers used the data on more than 2000 suicides in a Welsh cohort since 2001 with 20 controls per case.
The findings were based on the fact that the majority of individuals committing suicide attend services other than mental health in the final year for unrelated reasons. More than 80% of such individuals had contacted their GP during their past year. The researchers believe it is possible to develop an algorithm using routinely collected health data which can flag individuals at risk for suicide. Clinicians can then ask them appropriate questions regarding their thoughts and feelings if needed.
AI could help process millions of health records taking into consideration thousands of variables to quickly build a risk model. The preliminary findings showed a 75% accuracy for the AI system. Researchers are now looking at slowly increasing the system's complexity in order to improve its precision before subjecting it to clinical trials.