Yang Hancao, Wu Meng, Liang Keqing, Li Yi, Yang Ran, Yuan Beibei, Wu Ming, Xu Jin
Department of Clinical Laboratory, Children's Hospital of Fudan University & National Children Medical Center, Shanghai, China.
Department of Clinical Laboratory, Children's Hospital of Nanjing Medical University, Nanjing, China.
Front Genet. 2025 Aug 15;16:1646032. doi: 10.3389/fgene.2025.1646032. eCollection 2025.
Kawasaki disease (KD) patients could develop coronary artery lesions (CALs) which threatens children's life. We aimed to develop and validate an artificial intelligence model that can predict CALs risk in KD patients. A total of 506 KD patients were included at Children's Hospital of Fudan University. Seven predictive features were identified for model building. Among different machine learning (ML) models tested, Multi-Layer Perceptron Classifier (MLPC), Random Forest (RF) and Extra Tree (ET) demonstrated optimal performance. These were finally chosen for time-across validation. Among three of them, MLPC stands out with its highest accuracy. Besides, Mendelian randomization (MR) analysis also provided genetic evidence. Among seven predictive features, two of them were identified as causal associations with CALs. They are activated partial thromboplastin time (APTT) and red cell distribution width (RDW). The causal mechanism reinforced the biological plausibility of the model. ML-based prediction models, combined with genetic validation through MR, offer a reliable approach for early CALs risk stratification in KD patients. This strategy may facilitate timely clinical interventions.
川崎病（KD）患者可能会出现冠状动脉病变（CALs），这会威胁儿童生命。我们旨在开发并验证一种能够预测KD患者发生CALs风险的人工智能模型。复旦大学附属儿科医院共纳入了506例KD患者。为模型构建确定了7个预测特征。在测试的不同机器学习（ML）模型中，多层感知器分类器（MLPC）、随机森林（RF）和极端随机树（ET）表现出最佳性能。最终选择这些模型进行跨时间验证。在这三种模型中，MLPC以其最高的准确率脱颖而出。此外，孟德尔随机化（MR）分析也提供了遗传证据。在7个预测特征中，其中两个被确定与CALs存在因果关联。它们是活化部分凝血活酶时间（APTT）和红细胞分布宽度（RDW）。因果机制增强了模型的生物学合理性。基于ML的预测模型，结合通过MR进行的遗传验证，为KD患者早期CALs风险分层提供了一种可靠的方法。这一策略可能有助于及时进行临床干预。
