Domain-Expert-Guided Hybrid Mixture-of-Experts for Medical AI: Integrating Data-Driven Learning with Clinical Priors
This addresses the challenge of robust medical AI for clinicians by combining data-driven and expert-guided approaches, though it is incremental as it builds on existing MoE methods.
The paper tackled the problem of limited effectiveness of Mixture-of-Experts models in medical AI due to small datasets by proposing DKGH-MoE, which integrates data-driven learning with clinical priors like clinician gaze patterns, resulting in improved performance and interpretability.
Mixture-of-Experts (MoE) models increase representational capacity with modest computational cost, but their effectiveness in specialized domains such as medicine is limited by small datasets. In contrast, clinical practice offers rich expert knowledge, such as physician gaze patterns and diagnostic heuristics, that models cannot reliably learn from limited data. Combining data-driven experts, which capture novel patterns, with domain-expert-guided experts, which encode accumulated clinical insights, provides complementary strengths for robust and clinically meaningful learning. To this end, we propose Domain-Knowledge-Guided Hybrid MoE (DKGH-MoE), a plug-and-play and interpretable module that unifies data-driven learning with domain expertise. DKGH-MoE integrates a data-driven MoE to extract novel features from raw imaging data, and a domain-expert-guided MoE incorporates clinical priors, specifically clinician eye-gaze cues, to emphasize regions of high diagnostic relevance. By integrating domain expert insights with data-driven features, DKGH-MoE improves both performance and interpretability.