Background: To construct a predictive model for intravenous immunoglobulin (IVIG) resistant Kawasaki disease (KD) based on the gradient boosting decision tree (GBDT), so as to early identify children with IVIG resistance and actively take additional treatment to prevent adverse events. Methods: The case data of KD children hospitalized in the Pediatric Department of Lanzhou University Second Hospital from October 2015 to July 2020 were collected. All KD patients were divided into IVIG responsive group and IVIG resistant group. GBDT was used to explore the influencing factors of IVIG-resistant KD and to construct a prediction model. Then compared with previous models, the optimal model was selected. Results: In the process of GBDT model construction, 80% of the data were used as the test set, and 20% of the data were used as the validation set. Among them, the verification set was used to adjust the hyperparameters in GDBT learning. The model performed best with a hyperparameter tree depth of 5. The area under the curve of the GBDT model constructed based on the best parameters was 0.87 (95% CI: 0.85–0.90), the sensitivity was 72.62%, the specificity was 89.04%, and the accuracy was 61.65%. The contribution degree of each feature value to the model was total bilirubin, albumin, C-reactive protein, fever time, and Na in order. Conclusion: The GBDT model is more suitable for the prediction of IVIG-resistant KD in this study area.

Objective The aim of this study was to evaluate the predictive value of the monocyte-to-high-density lipoprotein ratio (MHR) in Kawasaki disease (KD) complicated with coronary artery lesions (CALs) and to construct a nomogram prediction model. Methods The medical records of KD inpatients diagnosed in the Department of Pediatrics of Lanzhou University Second Hospital from May 2015 to September 2021 were retrospectively analyzed. ROC curves were applied to evaluate the predictive value of MHR in KD complicated with CALs, and logistic regression analysis was used to screen independent risk factors. We constructed a nomogram model and performed internal validation. Results A total of 568 KD patients were enrolled in the study. MHR was significantly higher in KD patients complicated with CALs and was identified as an independent risk factor for CALs (OR: 1.604, 95% CI: 1.292–1.990). The area under the ROC curve for MHR in predicting CALs was 0.661. The C-index of the nomogram model constructed by incorporating MHR was 0.725 (95% CI: 0.682–0.768), and the calibration curve revealed good agreement between the predicted and actual probabilities. Conclusions MHR may not be suitable as a single biomarker to predict the occurrence of CALs, but the nomogram model constructed in combination with other independent risk factors had acceptable predictive performance. Impact The inflammatory response plays an important role in the pathogenesis of Kawasaki disease. The monocyte-to-high-density lipoprotein ratio is a novel systemic inflammation marker. The monocyte-to-high-density lipoprotein ratio is an independent risk factor for Kawasaki disease complicated with coronary artery lesions. The nomogram established by incorporating the monocyte-to-high-density lipoprotein ratio has satisfactory predictive performance for coronary artery lesion formation.

目的 分析肺炎支原体(MP)感染对川崎病(KD)患儿心血管损伤的特点,为临床诊治提供指导.方法 回顾性分析2018年1月—2021年3月收治于某三级综合医院小儿心血管科的KD患儿临床资料,根据MP感染情况分为KD合并MP感染组(KD-MP组)和KD未合并MP感染组(KD组),比较两组患儿血小板参数、凝血相关指标、心肌酶谱及不良结局发生率的差异.结果 共纳入270例KD患儿,其中KD-MP组70例,KD组200例.KD-MP组平均血小板体积(MPV)中位水平[10.00(9.08,11.00)fL]较KD组[9.60(8.83,10.68)fL]更高,差异有统计学意义(P<0.05).KD-MP组冠状动脉损伤(CAL)、冠状动脉轻度扩张、心包积液的占比分别为55.71％、47.14％、15.71％,高于KD组的38.50％、30.50％、5.50％,差异均有统计学意义(均P<0.05).结论 合并MP感染的KD患儿更易并发CAL和心包积液,面临更大的心血管损伤风险,临床医生应及时采取抗感染治疗.