English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years the development of artificial intelligence (AI) systems forautomated medical image analysis has gained enormous momentum. At the sametime, a large body of work has shown that AI systems can systematically andunfairly discriminate against certain populations in various applicationscenarios. These two facts have motivated the emergence of algorithmic fairnessstudies in this field. Most research on healthcare algorithmic fairness to datehas focused on the assessment of biases in terms of classical discriminationmetrics such as AUC and accuracy. Potential biases in terms of modelcalibration, however, have only recently begun to be evaluated. This isespecially important when working with clinical decision support systems, aspredictive uncertainty is key for health professionals to optimally evaluateand combine multiple sources of information. In this work we studydiscrimination and calibration biases in models trained for automatic detectionof malignant dermatological conditions from skin lesions images. Importantly,we show how several typically employed calibration metrics are systematicallybiased with respect to sample sizes, and how this can lead to erroneousfairness analysis if not taken into consideration. This is of particularrelevance to fairness studies, where data imbalance results in drastic samplesize differences between demographic sub-groups, which, if not taken intoaccount, can act as confounders.

Towards unraveling calibration biases in medical image analysis