Generalizability of Risk Models for Treatment-Resistant Depression Across Three Health Systems.
medRxiv : the preprint server for health sciences May 27, 2025 Colin G Walsh, Michael Ripperger, Thomas H McCoy et al. preprint
Predicting which people with major depressive disorder will develop treatment-resistant depression from electronic health record data alone is not yet accurate enough for clinical use. Models built using sociodemographic features, medications, and diagnosis codes from three large U.S. health systems performed only slightly better than chance, with discrimination scores (AUROC) between 0.58 and 0.64 within the same health system and dropping to 0.51–0.58 when applied to a different system. Agreement between models from different sites was low, with concordance correlation coefficients ranging from 0.13 to 0.38. Age and sex were the most important features driving differences in model predictions. The findings suggest that readily available electronic health record data are insufficient for reliable prediction and that further improvement will require additional data types.