Grassi2021 - Prediction of illness remission in patients with Obsessive-Compulsive Disorder with supervised machine learning

Example citation

Machine learning techniques have been used to predict the two-year remission status of patients with OCD, yielding a balanced accuracy of 72% in test data [@grassi2021].

Key takeaways

  • Gradient boosted decision trees (XGBoost in R)
  • n = 287, AUROC 0.78 (sens 73% spec 71%)
  • Small test data sites and large variations between sites.