Artificial intelligence has achieved substantial success in analyzing individual biomedical data types, particularly medical images. However, real-world clinical decision-making relies on the integration of heterogeneous data sources, including imaging, genomics, and patient-specific clinical information. This keynote examines the limitations of single-modality AI and introduces multimodal intelligence as a critical next step toward comprehensive healthcare solutions. Drawing on recent advances in machine learning and biomedical research, we illustrate how multimodal frameworks can capture complex disease mechanisms and support more accurate and personalized predictions. We further discuss the transformative potential of foundation models to unify diverse biomedical data and enable scalable learning across domains. Challenges related to data integration, interpretability, and clinical adoption are also addressed. This talk outlines future directions for developing robust, trustworthy, and clinically impactful AI systems.

Dr. Le Nguyen Quoc Khanh is an Associate Professor at Taipei Medical University and leads the AIBioMed Research Group. His research focuses on AI in medicine, including medical imaging, genomics, and multimodal data integration. He has published widely in top journals and is recognized among the world’s top 2% scientists. Dr. Khanh serves on the editorial boards of several international journals and is actively involved in global research collaborations. His work emphasizes translating AI methods into clinically meaningful applications.