Extended Data Fig. 3: Attributes identified by the join expert–XAI auditing procedure as key influences on the output of individual dermatology AI classifiers, when evaluated on the Fitzpatrick17k dataset. | Nature Biomedical Engineering

Extended Data Fig. 3: Attributes identified by the join expert–XAI auditing procedure as key influences on the output of individual dermatology AI classifiers, when evaluated on the Fitzpatrick17k dataset.

From: Auditing the inference processes of medical-image classifiers by leveraging generative AI and the expertise of physicians

Extended Data Fig. 3

In contrast to main text Fig. 2, attributes are ordered by the proportion of counterfactual pairs from the specified AI classifier in which experts noted that attribute differs, enabling examination of attributes relevant to a particular AI classifier but not necessarily to other AI classifiers.

Back to article page