Expert-aware uncertainty estimation for quality control of neural-based blood typing
This work addresses the need for reliable uncertainty estimation in neural-based blood typing to support second-opinion systems in medical diagnostics, representing an incremental improvement over existing ensemble methods.
The paper tackled the problem of inaccurate uncertainty estimation in neural-based models for medical diagnostics by integrating expert assessments of case complexity into the learning process, resulting in a 2.5-fold improvement with expert labels and a 35% increase in performance with neural-based expert consensus estimates.
In medical diagnostics, accurate uncertainty estimation for neural-based models is essential for complementing second-opinion systems. Despite neural network ensembles' proficiency in this problem, a gap persists between actual uncertainties and predicted estimates. A major difficulty here is the lack of labels on the hardness of examples: a typical dataset includes only ground truth target labels, making the uncertainty estimation problem almost unsupervised. Our novel approach narrows this gap by integrating expert assessments of case complexity into the neural network's learning process, utilizing both definitive target labels and supplementary complexity ratings. We validate our methodology for blood typing, leveraging a new dataset "BloodyWell" unique in augmenting labeled reaction images with complexity scores from six medical specialists. Experiments demonstrate enhancement of our approach in uncertainty prediction, achieving a 2.5-fold improvement with expert labels and a 35% increase in performance with estimates of neural-based expert consensus.