Contrastive Learning Approach to Predict Radiologist's Error Based on Gaze Data

The increase in medical imaging and, consequently, the growing workload of radiologists requires workflow optimization. The interaction between radiologists and artificial intelligence is a promising area because it can improve radiologist productivity and reduce diagnostic errors. In this study, we describe an eye-tracking experiment with four practicing radiologists who cumulatively examined 1,000 unique chest X-ray images that included samples with multiple pathologies. We demonstrate the feasibility of a self-supervised approach for gazebased data for problems with a small amount of labeled data. We achieve an accuracy of 64.7% for binary classification of radiologist diagnostic error with 218 samples per label. The proposed approach can be used in the system for assessing the need for a second opinion to improve the quality of diagnostics.