Fair Uncertainty Quantification for Depression Prediction
This work addresses the need for trustworthy clinical depression prediction by focusing on fairness across demographic groups, representing an incremental advance in combining uncertainty quantification with fairness constraints.
The paper tackles the problem of ensuring both predictive reliability and algorithmic fairness in uncertainty quantification for depression prediction, proposing Fair Uncertainty Quantification (FUQ) which achieves optimal fairness under Equal Opportunity Coverage constraints through group-based conformal prediction and fairness-aware optimization.
Trustworthy depression prediction based on deep learning, incorporating both predictive reliability and algorithmic fairness across diverse demographic groups, is crucial for clinical application. Recently, achieving reliable depression predictions through uncertainty quantification has attracted increasing attention. However, few studies have focused on the fairness of uncertainty quantification (UQ) in depression prediction. In this work, we investigate the algorithmic fairness of UQ, namely Equal Opportunity Coverage (EOC) fairness, and propose Fair Uncertainty Quantification (FUQ) for depression prediction. FUQ pursues reliable and fair depression predictions through group-based analysis. Specifically, we first group all the participants by different sensitive attributes and leverage conformal prediction to quantify uncertainty within each demographic group, which provides a theoretically guaranteed and valid way to quantify uncertainty for depression prediction and facilitates the investigation of fairness across different demographic groups. Furthermore, we propose a fairness-aware optimization strategy that formulates fairness as a constrained optimization problem under EOC constraints. This enables the model to preserve predictive reliability while adapting to the heterogeneous uncertainty levels across demographic groups, thereby achieving optimal fairness. Through extensive evaluations on several visual and audio depression datasets, our approach demonstrates its effectiveness.