Extended Data Fig. 2: Attributes identified by the joint expert–XAI auditing procedure as key influences on the output of individual dermatology AI classifiers, when evaluated on the ISIC dataset. | Nature Biomedical Engineering

Extended Data Fig. 2: Attributes identified by the joint expert–XAI auditing procedure as key influences on the output of individual dermatology AI classifiers, when evaluated on the ISIC dataset.

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

Extended Data Fig. 2

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 most AI classifiers (for example, prominence of skin grooves or dermatoglyphs, which influences Scanoma and ModelDerm).

Back to article page