New Delhi, Jan 4 : A team of US researchers has developed a novel artificial intelligence (AI) system that can help doctors identify patients at risk for suicide.

Researchers from the Vanderbilt University Medical Center said that AI-driven clinical alerts can potentially improve prevention efforts in routine medical settings.

The team tested the AI system, called the Vanderbilt Suicide Attempt and Ideation Likelihood model (VSAIL), in three neurology clinics at VUMC. They analysed 7,732 patient visits over six months for suicide risk during regular clinic visits.

The findings, reported in JAMA Network Open, showed that the AI model could effectively prompt doctors -- 596 total screening alerts ' by analysing routine information from electronic health records and calculating a patient's 30-day risk of a suicide attempt.

Further, the team compared two approaches -- automatic pop-up alerts that interrupted the doctor's workflow versus a more passive system that simply displayed risk information in the patient's electronic chart.

The interruptive alerts were found to be far more effective, leading doctors to conduct suicide risk assessments in connection with 42 per cent of screening alerts, compared to just 4 per cent with the passive system.

While 'universal screening isn't practical in every setting' the new VSAIL can 'help identify high-risk patients and prompt focused screening conversations," the researchers said, suggesting that similar systems could be tested in other medical settings.

The team found that although interruptive alerts were more effective at prompting screenings, they could potentially contribute to "alert fatigue" among doctors.

The team said that doctors can become overwhelmed by frequent automated notifications. They urged future studies to examine this concern.

/IANS