Purpose/Significance To construct a specialized Kawasaki disease (KD) platform based on multimodal data, so as to support optimized clinical diagnosis and treatment as well as scientific research exploration.Method/Process Based on the diagnostic and treatment data of KD children in the Children’s Hospital, Zhejiang University School of Medicine from 2019 to 2024, multi-source heterogeneous data are aggregated by using extraction, transformation and loading (ETL) technology. Data are cleaned, standardized and structured using natural language processing (NLP), computer vision and data governance techniques, a specialized disease database is established. On this basis, a specialized disease platform integrating functional modules such as patient management, intelligent search, research project and follow-up management is constructed. Result/Conclusion A specialized KD database containing 10 689 confirmed cases and 300 data items across 18 modules is established. The platform can provide strong support for clinical diagnosis and treatment as well as disease course management, laying a foundation for conducting large-sample clinical study and scientific research innovation.