Challenges in Cross-Site Validation of Machine Learning Models for Schizophrenia Diagnosis

In a recent study published in JAMA Psychiatry, researchers reported that a machine learning model was able to stratify risk for subsequent diagnosis of schizophrenia or bipolar disorder among individuals already receiving psychiatric treatment. Coauthor Søren Dinesen Østergaard, PhD, of Aarhus University in Denmark joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss. Related Content:

• Machine Learning Model Shows Promise in Early Detection of Serious Mental Illness
• Predicting Diagnostic Progression to Schizophrenia or Bipolar Disorder via Machine Learning