Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosis

In this study we propose the Learning to Defer with Uncertainty (LDU) algorithm, an approach which considers the model's predictive uncertainty when identifying the patient group to be evaluated by human experts. By identifying patients for whom the uncertainty of computer-aided diagnosis is estimated to be high and defers them for evaluation by human experts, the LDU algorithm can be used to mitigate the risk of erroneous computer-aided diagnoses in clinical settings.