Explainable deep learning algorithm for distinguishing IVIG-Resistant Kawasaki disease in Shandong peninsula, China
LightGBM can predict IVIG-resistance well in KD patients in Shandong Peninsula, China. C-reactive protein, Serum sodium, Albumin, HB, Neutrophil percentage, and PLT are important indicators, enhanced explainable of the model.
Authors
- Sibao Wang (ORCID: https://orcid.org/0000-0002-5880-0815)
- Zhixian Ji
- Huashu Liu
- Gang Luo (ORCID: https://orcid.org/0000-0003-0623-6236)
- Zhixin Li (ORCID: https://orcid.org/0000-0001-9962-3942)
- Silin Pan (ORCID: https://orcid.org/0000-0001-9831-4961)
Institutions
- Qingdao University (CN)
- Affiliated Hospital of Qingdao University (CN)
- Qingdao Municipal Hospital (CN)
- Qingdao Women and Children's Hospital (CN)
Publication Details
- Journal
- BMC Pediatrics
- Published
- 2025-08-28
- DOI
- https://doi.org/10.1186/s12887-025-06082-w
- Primary Topic
- Kawasaki Disease and Coronary Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Key Research and Development Program of China