Making the most of errors: Utilizing erroneous classifications generated by machine-learning models of neuroimaging data to capture disorder heterogeneity

Within-disorder heterogeneity complicates mapping neurobiological features of psychopathology to DSM conceptualizations. The present study explored patterns of diagnostic classification errors among disorders with commonly co-occurring features to examine this heterogeneity. We conducted classification analyses with the UCLA Phenomics Study database using a support vector classifier to differentiate disorders via whole-brain task-based functional connectivity, predicting that model misclassifications would provide insight about brain connectivity characteristics shared across disorders. We also explored whether symptoms and specific brain networks could account for misclassification rates. The classification model performed better than chance (44% accuracy, p = .01) and revealed that misclassification of schizophrenia (SCZ) as bipolar disorder (BD; 38%) and BD as SCZ (36%) was symmetrical. Attention-deficit/hyperactivity disorder (ADHD) was misclassified as BD at the highest rate (46%) and higher than the converse (17%). SCZ and ADHD were misclassified least (SCZ as ADHD 15%; ADHD as SCZ 22%). Considerable variance in misclassification of SCZ as BD (R2 = .83) and BD as SCZ (R2 = .71) could be accounted for by symptoms of both SCZ and BD. Permutation testing revealed disorder- and network-specific effects, with certain networks improving classification accuracy and others hindering it for specific disorders. An approach focused on classification errors replicated known disorder overlap, producing errors in the expected configuration. Further, it identified clinical and neural features within and across diagnostic categories that contribute to disorder misclassification and within-disorder heterogeneity. This approach may facilitate neurobiologically informed phenotypic differentiation within diagnostic groups.