MedPage Today February 20, 2025
— Algorithm showed better performance for schizophrenia
Key Takeaways
- A machine learning model showed better accuracy for predicting schizophrenia than bipolar disorder.
- The study used EHR data to predict mental health transitions within 5 years.
- Clinical notes were especially informative for diagnostic predictions.
A machine learning model trained on electronic health record (EHR) data predicted progression to schizophrenia or bipolar disorder, with better performance for schizophrenia.
In a cohort study of over 24,000 patients, an extreme gradient boosting (XGBoost) model predicted transition to the first occurrence of either schizophrenia or bipolar disorder with an area under the receiver operating characteristic curve (AUROC) of 0.70 (95% CI 0.70-0.70) on the training set and 0.64 (95%...
Today's Sponsors
Today's Sponsor