Uncertainty-Aware Training for Cardiac Resynchronisation Therapy Response Prediction
This work addresses the need for interpretability and trust in predictive models for sensitive healthcare applications like cardiac therapy, though it appears incremental as it builds on existing methods.
The paper tackled the problem of improving trust in deep learning models for healthcare by quantifying data and model uncertainty in Cardiac Resynchronisation Therapy response prediction from cardiac images, and proposed an uncertainty-aware loss function that increased confidence in true positive predictions.
Evaluation of predictive deep learning (DL) models beyond conventional performance metrics has become increasingly important for applications in sensitive environments like healthcare. Such models might have the capability to encode and analyse large sets of data but they often lack comprehensive interpretability methods, preventing clinical trust in predictive outcomes. Quantifying uncertainty of a prediction is one way to provide such interpretability and promote trust. However, relatively little attention has been paid to how to include such requirements into the training of the model. In this paper we: (i) quantify the data (aleatoric) and model (epistemic) uncertainty of a DL model for Cardiac Resynchronisation Therapy response prediction from cardiac magnetic resonance images, and (ii) propose and perform a preliminary investigation of an uncertainty-aware loss function that can be used to retrain an existing DL image-based classification model to encourage confidence in correct predictions and reduce confidence in incorrect predictions. Our initial results are promising, showing a significant increase in the (epistemic) confidence of true positive predictions, with some evidence of a reduction in false negative confidence.