On the trade-off between fairness and performance in glioma grade prediction using pre-processing and post-processing techniques to mitigate bias

Abstract This research paper investigates the impact of demographic biases, specifically race and gender, on machine learning-based glioma grading using the TCGA data set compiled from The Cancer Genome Atlas. It applies three common classifiers (logistic regression, random forests, and extreme gradient boosting) and explores pre-processing (reweighting) and post-processing (equalized odds) strategies for bias mitigation. The study evaluates prediction performance (Matthews correlation coefficient, recall, specificity) and fairness (disparate impact, equal opportunity difference, error rate difference) metrics, highlighting trade-offs between fairness and accuracy across demographic groups. In the case of the most severe bias (race), the pre-trained logistic regression model using the reweighting algorithm shows some deterioration in prediction outcomes for the under-represented group and even an increase in unfairness, while the post-processing approach improves results for the under-represented group and provides significant fairness gains. These results are interesting because they could be taken into account in real-world clinical decision-making or in outcomes for under-represented patient groups.