AI used to predict early schizophrenia symptoms

News

University of Alberta researchers have developed an AI tool to predict schizophrenia by analysing brain scans, aiming for earlier diagnosis and treatment.

Sunil Kalmady Vasu (centre) led a recent study with fellow U of A researchers including Russ Greiner (left), Andrew Greenshaw (right) and Serdar Dursun (not pictured), showing that a machine learning tool could help predict early symptoms of schizophrenia in siblings and children of patients

In a recently published study, researchers explained how their tool was used to analyse functional magnetic resonance images of 57 healthy first-degree relatives (siblings or children) of schizophrenia patients. According to the team, the tool accurately identified the 14 individuals who scored highest on a self-reported schizotypal personality trait scale.

Schizophrenia, which can cause delusions, hallucinations, disorganised speech, trouble with thinking and lack of motivation, is usually treated with a combination of drugs, psychotherapy and brain stimulation. Sunil Kalmady Vasu, senior machine learning specialist in the Faculty of Medicine & Dentistry and the paper’s lead author, said that the tool has been designed as a decision support tool and would not replace diagnosis by a psychiatrist.

Brain signals sensor boost for detecting injury and disease

“Our evidence-based tool looks at the neural signature in the brain, with the potential to be more accurate than diagnosis by the subjective assessment of the symptoms alone,” Kalmady Vasu commented. He pointed out that while having schizotypal personality traits may cause people to be more vulnerable to psychosis, it is not certain they will develop full-blown schizophrenia. 

Named EMPaSchiz (Ensemble algorithm with Multiple Parcellations for Schizophrenia prediction), the tool was developed by the Alberta team alongside the National Institute of Mental Health and Neurosciences in India. It was reportedly used to predict a diagnosis of schizophrenia with 87 per cent accuracy by analysing brain scans.

Kalmady Vasu said the next steps for the research will include testing the tool’s accuracy on non-familial individuals with schizotypal traits, and to track assessed individuals over time to learn whether they develop schizophrenia in later life. He is also using the same principles to develop algorithms to predict outcomes such as mortality and readmissions for heart failure in cardiovascular patients through the Canadian VIGOUR Centre.

“Severe mental illness and cardiovascular problems cause functional disability and impair quality of life,” Kalmady Vasu said. “It is very important to develop objective, evidence-based tools for these complex disorders that afflict humankind.”