<ul><li>Researchers have developed a global explainability method for a deep abstaining classifier (DAC) used in the histology prediction task of cancer pathology reports.</li><li>The DAC framework allows the model to abstain on ambiguous or confusing cases, achieving high accuracy on retained samples but with decreased coverage.</li><li>By utilizing a local explainability technique, researchers were able to identify sources of errors and gain contextual reasoning for individual predictions.</li><li>The study suggests strategies such as exclusion criteria and focused annotation to improve the DAC's performance in complex real-world implementations.</li></ul>

Global explainability of a deep abstaining classifier

Discover more