Because symptoms differ widely between patients, a more specific method is needed to stratify individuals with psychosis—beyond clinical high-risk and recent-onset, suggests a study published in JAMA Psychiatry. To better identify and categorize symptoms, researchers developed a machine learning model to “redraw boundaries” within early psychosis.
The study involved 749 participants and 10 sites across Europe and the United Kingdom. The researchers divided participants into 4 groups: clinical high risk for psychosis (CHR-P), recent-onset psychosis (ROP), recent-onset depression (ROD), and healthy control participants. They validated and compared the results, analyzing premorbid risk factors, 18-month longitudinal illness courses, and schizophrenia polygenic risk scores (PRS). They measured clinical data as well as biological data obtained from MRI scans of grey and white matter and cerebrospinal fluid measurements.
The researchers found depression symptoms in 51% of the CHR-P and ROP and in 26% of a high-functioning subgroup. They also found an underlying genetic risk of early illness. These and other discoveries around genetic cognitive risk factors support the use of “neurodevelopmental preventive strategies and provide a homogeneous target that could enhance the possibility of translation,” the investigators believe.
The researchers admitted that classifying individuals with early illness is difficult because symptoms may change rapidly. They also stated that the patterns found “could be further probed for more sensitive underlying dimensions and subgroups.”
In conclusion, “associations between the modalities were not straightforward and may indicate relatively independent preventive targets,” the researchers stated. “The results provide important context beyond positive symptom severity in these groups and their associations to brain volume reductions.”
Dwyer DB, Buciuman MO, Ruef A, et al. Clinical, Brain, and Multilevel Clustering in Early Psychosis and Affective Stages Published online, 2022 May 18. JAMA Psychiatry. 2022;10.1001/jamapsychiatry.2022.1163. doi:10.1001/jamapsychiatry.2022.1163