AI predicts schizophrenia symptoms in at-risk population
November 2020
National Institute of Mental Health and Neuro Sciences, Bangalore, India(1)
University of Alberta, Edmonton, Canada(2)
University of Alberta, Edmonton, Canada(2)
First-degree relatives of schizophrenia patients have up to a 19 per cent risk of developing schizophrenia during their lifetime, compared with the general population risk of less than one per cent. The tool EMPaSchiz (Ensemble algorithm with Multiple Parcellations for Schizophrenia prediction) can predict a diagnosis of schizophrenia with 87 per cent accuracy by examining patient brain scans. Functional magnetic resonance images of 57 healthy first-degree relatives (siblings or children) of schizophrenia patients were analyzed. The method accurately identified the 14 individuals who scored highest on a self-reported schizotypal personality trait scale.
The next step is to test the accuracy of the tool on nonfamilial individuals with schizotypal traits and to track assessed individuals over time to learn whether they develop schizophrenia later in life.
Extending schizophrenia diagnostic model to predict schizotypy in first-degree relatives
Ganesan Venkatasubramanian(1), Sunil Vasu Kalmady(2)
Added on: 02-11-2021
[1] https://www.nature.com/articles/s41537-020-00119-y
