CheXbreak: Misclassification Identification for Deep Learning Models Interpreting Chest X-rays

Emma Chen, Andy Kim, Rayan Krishnan, Andrew Y. Ng, and Pranav Rajpurkar (Stanford University)

Abstract: A major obstacle to the integration of deep learning models for chest x-ray interpretation into clinical settings is the lack of understanding of their failure modes. In this work, we first investigate whether there are clinical subgroups that chest x-ray models are likely to misclassify. We find that older patients and patients with a lung lesion or pneumothorax finding have a higher probability of being misclassified on some diseases. Second, we develop misclassification predictors on chest x-ray models using their outputs and clinical features. We find that our best performing misclassification identifier achieves an AUROC close to 0.9 for most diseases. Third, employing our misclassification identifiers, we develop a corrective algorithm to selectively flip model predictions that have high likelihood of misclassification at inference time. We observe F1 improvement on the prediction of Consolidation (0.008, 95%CI[0.005, 0.010]) and Edema (0.003, 95%CI[0.001, 0.006]). By carrying out our investigation on ten distinct and high-performing chest x-ray models, we are able to derive insights across model architectures and offer a generalizable framework applicable to other medical imaging tasks.