According to a study by researchers at the Max Planck Institute of Psychiatry, led by Nikolaos Koutsouleris, a combination of human and artificial intelligence optimizes the prediction of mental health problems , including psychosis.
The study combined psychiatric assessments with machine learning models that analyze clinical and biological data.
Predictions of the course of the disease
Although psychiatrists can make very accurate predictions about the positive outcomes of mental illness, they can underestimate the frequency of adverse events that lead to relapses.
Therefore, algorithmic pattern recognition helps clinicians better predict the course of the disease .
The results of the study show that it is the combination of artificial and human intelligence that optimizes the prediction of mental illness, and not just one or the other . With the algorithm, then, clinicians can identify at an early stage which patients need therapeutic intervention and those who do not. As Koutsouleris explains:
This algorithm allows us to improve the prevention of psychosis, especially in young patients at high risk or with emerging depression, and to intervene in a more specific and timely manner.
Therefore, the algorithm is not a substitute for treatment performed by medical professionals ; rather, it aids decision-making and provides recommendations on whether further examinations should be performed on an individual basis.
The results of our study could help drive a reciprocal and interactive clinical validation process and improve prognostic tools in real-world screening services.
Norman Bates would celebrate.