A Simple Probabilistic Model for Uncertainty Estimation
This work addresses uncertainty estimation for medical diagnostics, specifically in ECG-based atrial fibrillation detection, representing an incremental improvement in a domain-specific application.
The paper tackled the problem of estimating predictive uncertainty in atrial fibrillation detection from single-lead ECG signals by predicting parameters of a beta distribution over class probabilities, resulting in improved detection of atypical recordings and enhanced algorithm quality on confident predictions.
The article focuses on determining the predictive uncertainty of a model on the example of atrial fibrillation detection problem by a single-lead ECG signal. To this end, the model predicts parameters of the beta distribution over class probabilities instead of these probabilities themselves. It was shown that the described approach allows to detect atypical recordings and significantly improve the quality of the algorithm on confident predictions.