Towards unraveling calibration biases in medical image analysis

MARÍA AGUSTINA RICCI LARA; CANDELARIA MOSQUERA; ENZO FERRANTE; RODRIGO ECHEVESTE

Montevideo

Conferencia; Latin American Meeting In Artificial Intelligence, Khipu 2023; 2023

UDELAR

In recent years the development of AI systems for automated medical image analysis has gained enormous momentum. At the same time, a large body of work has shown that AI systems can systematically and unfairly discriminate against certain populations in various application scenarios. These two facts have motivated the emergence of algorithmic fairness studies in this field. Most research on healthcare algorithmic fairness to date has focused on the assessment of biases in terms of classical discrimination metrics such as AUC and accuracy. Potential biases in terms of model calibration, however, have only recently begun to be evaluated. This is especially important when working with clinical decision support systems, as predictive uncertainty is key for health professionals to optimally evaluate and combine multiple sources of information. In this work we study discrimination and calibration biases in models trained for automatic detection of malignant dermatological conditions from skin lesions images. Importantly, we show how a wide range of typically employed calibration metrics are highly sensitive to sample sizes. This is of particular relevance to fairness studies, where data imbalance results in drastic sample size differences between demographic subgroups, which if not taken into account can act as confounders.