<ul><li>Integrating AI in healthcare can greatly improve patient care and system efficiency, but the lack of explainability in AI systems hinders their clinical adoption.</li><li>Existing explainability methods for AI models in healthcare are limited to unimodal settings and fail to capture cross-modal interactions.</li><li>This paper introduces InterSHAP, a cross-modal interaction score that quantifies the contributions of individual modalities and their interactions without approximations.</li><li>InterSHAP accurately measures cross-modal interactions, handles multiple modalities, and provides detailed explanations for individual samples in multimodal medical datasets.</li></ul>

Measuring Cross-Modal Interactions in Multimodal Models

Discover more