Swansea University research using AI to predict suicide
Researchers at Swansea University are hoping to develop technology which would alert doctors to people with a high chance of taking their own lives.
Up to three hundred and fifty people kill themselves in Wales each year and it is the leading cause of death for people under twenty five.
The BBC reports the researchers found that 80% of people who take their own lives saw their GP at least once in the last year.
Researchers used the university’s SAIL Databank to obtain information about more than two thousand suicides held in SID-Cymru, an electronic database of self-inflicted and undetermined intent deaths in Wales since 2001.
Dr Marcos del Pozo Banos, an expert in mental health informatics and AI, said the team wanted to develop an algorithm which analyses routinely collected health data to flag people at risk. He described the preliminary results, which recorded almost 75% accuracy, as very promising.
The team now plans to gradually increase the complexity of the AI system to improve its precision before carrying out thorough trials.
Professor Ann John, who is chair the national advisory group to Welsh Government on suicide and self-harm prevention, said “AI methods have huge potential to improve suicide prevention, and this is an exciting development. However, we are still at the early development stages before any practical use.”