The combination of a person's genetic data and health records could potentially be used to predict a mental disorder diagnosis prior to a clinical assessment, according to a study appearing this week in JAMA Psychiatry. Current diagnostic practices in psychiatry lack objective markers for predicting psychiatric diagnosis and the course of illness that could help improve the consistency in the diagnostic process and enable more precise prevention and treatment of mental disorders. Aiming to leverage advances in machine learning to address this shortcoming, a team led by scientists from the University of Copenhagen developed a computational prediction model using genotype data and matched longitudinal health register information from more than 63,000 people in the Danish population-based Integrative Psychiatric Research Consortium case-cohort study. Individuals in the study included people with ADHD, autism, major depressive disorder, and schizophrenia, as well as controls. The model, the researchers show, could predict specific diagnoses with high accuracy, with the most severe cases being the most easily predictable. The results, the study's authors write, "suggest the possibility of combining genetics and registry data to predict both mental disorder diagnosis and disorder progression in a clinically relevant, cross-diagnostic setting prior to clinical assessment."