Mitigating Gender Bias in Depression Detection via Counterfactual Inference
This addresses fairness concerns in mental health diagnostics for patients by mitigating gender bias, though it is an incremental improvement over existing debiasing strategies.
The paper tackled gender bias in audio-based depression detection models, which over-diagnose females and underperform on males due to imbalanced data, by proposing a Counterfactual Debiasing Framework that reduces bias and improves overall detection performance on the DAIC-WOZ dataset.
Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models to learn spurious correlations between gender and depression. Consequently, models tend to over-diagnose female patients while underperforming on male patients, raising significant fairness concerns. To address this, we propose a novel Counterfactual Debiasing Framework grounded in causal inference. We construct a causal graph to model the decision-making process and identify gender bias as the direct causal effect of gender on the prediction. During inference, we employ counterfactual inference to estimate and subtract this direct effect, ensuring the model relies primarily on authentic acoustic pathological features. Extensive experiments on the DAIC-WOZ dataset using two advanced acoustic backbones demonstrate that our framework not only significantly reduces gender bias but also improves overall detection performance compared to existing debiasing strategies.