24 November 2025
How can closely related mental illnesses with similar symptoms be reliably distinguished from one another? As part of a German-Chinese collaboration, researchers from Forschungszentrum Jülich and Heinrich Heine University Düsseldorf (HHU) have helped develop a decision tree aimed at improving diagnostic accuracy. The team used a combination of diagnostic techniques and artificial intelligence (AI). As the authors report in Science Advances, their findings could substantially increase the precision of psychiatric diagnoses.
People with schizophrenia, bipolar disorder with psychotic symptoms or schizoaffective disorder often show very similar signs - hallucinations, delusions, changes in mood or a loss of contact with reality. Yet these are distinct conditions that require different treatment approaches.
The research team has now identified which brain features differentiate these disorders, what they share, and which objective markers can be used to clearly diagnose the conditions and assess their severity. Prof. Dr. Sarah Genon and Prof. Dr. Simon Eickhoff from the Institute of Neuroscience and Medicine - Brain and Behaviour (INM-7) at Forschungszentrum Jülich, and several members of his team contributed to the study.
Prof. Dr. Simon Eickhoff, Director at INM-7 explains: "We identified objective and measurable brain characteristics that allow for a clearer distinction between mental illnesses. This could be an important step towards making diagnoses more accurate and faster, and ensuring that those affected receive more targeted treatment."
Prof. Dr. Sarah Genon, co-author of the study, adds: "Furthermore, the study illustrates that AI and neurobiological data can work together to help us better understand the complex differences between mental illnesses."
