An Algorithm to Predict Psychotic Illnesses

Summary: A new AI algorithm can successfully predict which children with microdeletion of chromosome 22 will develop schizophrenia and other mental health disorders later in life.

Source: eLife.

One out of three children with a microdeletion of chromosome 22 will later be affected with a psychotic illness such as schizophrenia. But how do we get to know which of these children might be affected? Recently, several studies have contributed to the understanding of the neurobiological mechanisms that are linked to the development of psychotic illnesses. The problem is that the potential to identify those at risk and adapt their treatment accordingly is still limited.

For the study, a team from the University of Geneva (UNIGE) has collaborated with a team from the EPFL to adapt and use in a longitudinal manner an artificial intelligence tool: the network analysis method.

This algorithm corresponds to many variables from different backgrounds – neurobiological, psychological, cognitive, etc. – over a period of twenty years, in order to identify what present symptoms are predictive of a psychotic illness in the child’s future developmental trajectory.

Not being able to take into account the degree of importance of each symptom can be problematic in determining the course of the disease and adapting to the most appropriate treatment for the patient.

To examine the methodology, 40 variables were taken into account for 70 children who are affected from a microdeletion of chromosome 22, observed every three years from childhood to adulthood.

Visual representations then highlighted the significant variables that determine the development of psychological problems three years later.

The researchers observed that an anxious 10-year-old whose anxiety turns into an inability to cope with stress in adolescence is likely to catch a psychological illness. The evolution of anxiety is therefore an important warning signal. Similarly, sadness, which over time turns into a feeling of guilt, is also a very important symptom.

In order to have detailed confirmation about the results of their algorithm, the researchers applied it to other cohorts who are at risk to psychotic illnesses that have been followed for many years, and were thus able to confirm that the computer tool functions well. The aim is now to use it as a predictive tool, but also to perfect it by integrating other variables, such as weight, to contribute to the clinical examination.