Researchers from the University of Tokyo, in collaboration with an international consortium, have developed a machine-learning tool capable of predicting the onset of psychosis by analyzing MRI brain scans. The tool, trained on data from over 2,000 individuals across 21 global locations, demonstrated 85% accuracy in distinguishing between those not at risk and those later experiencing overt psychotic symptoms. In new data, the accuracy remained at 73%. Identifying individuals at risk of psychosis before symptoms occur could lead to earlier interventions and improved outcomes. Psychosis, characterized by delusions and hallucinations, is treatable, and early intervention is crucial for recovery.
Psychotic episodes can affect anyone and are often characterized by delusions, hallucinations, or disorganized thinking. While there is no single cause, factors such as illness, injury, trauma, drug or alcohol use, medication, or genetic predisposition can contribute. Psychosis is treatable, and most individuals recover. However, because the most common age for a first episode is during adolescence or early adulthood, it can be challenging to identify young people in need of help.
Associate Professor Shinsuke Koike from the University of Tokyo's Graduate School of Arts and Sciences highlighted that only about 30% of clinically high-risk individuals later experience overt psychotic symptoms, emphasizing the need for tools to identify those at risk using subclinical signs and biological markers.
The machine-learning tool uses brain MRI scans to identify individuals at risk of psychosis before symptoms manifest. While previous studies suggested structural differences in the brain after the onset of psychosis, this research is groundbreaking in identifying differences in the brains of those at very high risk who have not yet experienced psychosis.
MRI research into psychotic disorders faces challenges due to variations in brain development and MRI machines, making it difficult to obtain accurate and comparable results. Additionally, distinguishing between changes due to typical development and those related to mental illness in young people adds complexity to the research. The collaborative effort involved 21 institutions from 15 countries and gathered a large and diverse group of adolescent and young adult participants. The findings provide a promising avenue for early intervention in individuals at risk of psychosis.