The data set analyzed in this study.

ObjectiveThis study aimed to develop and validate a simple-to-use nomogram for predicting severe scrub typhus (ST) in children.MethodsA retrospective study of 256 patients with ST was performed at the Kunming Children’s Hospital from January 2015 to November 2022. ALL patients were divided into a common and severe group based on the severity of the disease. A least absolute shrinkage and selection operator (LASSO) regression model was used to identify the optimal predictors, and the predictive nomogram was plotted by multivariable logistic regression. The nomogram was assessed by calibration, discrimination, and clinical utility.ResultsLASSO regression analysis identified that hemoglobin count (Hb), platelet count (PLT), lactate dehydrogenase (LDH), blood urea nitrogen (BUN), creatine kinase isoenzyme MB(CK-MB) and hypoproteinemia were the optimal predictors for severe ST. The nomogram was plotted by the six predictors. The area under the receiver operating characteristic (ROC) curve of the nomogram was 0.870(95% CI = 0.812 ~ 0.928) in training set and 0.839(95% CI = 0.712 ~ 0.967) in validation set. The calibration curve demonstrated that the nomogram was well-fitted, and the decision curve analysis (DCA) showed that the nomogram was clinically beneficial.ConclusionsThis study developed and validated a simple‐to‐use nomogram for predicting severe ST in children based on six predictors including Hb, PLT, LDH, BUN, CK-MB and hypoproteinemia, demonstrating excellent predictive accuracy for the data, though external and prospective validation is required to assess its potential clinical utility.研究目的：本研究旨在开发并验证一款易于使用的列线图（nomogram），用于预测儿童重型丛林斑疹伤寒（scrub typhus, ST）。 研究方法：本研究为回顾性研究，纳入2015年1月至2022年11月于昆明市儿童医院就诊的256例丛林斑疹伤寒患儿。所有患儿根据病情严重程度分为普通组与重症组。采用最小绝对收缩和选择算子（least absolute shrinkage and selection operator, LASSO）回归模型筛选最优预测因子，并通过多变量logistic回归绘制预测列线图。通过校准度、区分度及临床实用性对该列线图进行评估。 研究结果：LASSO回归分析显示，血红蛋白计数（Hb）、血小板计数（PLT）、乳酸脱氢酶（LDH）、血尿素氮（BUN）、肌酸激酶同工酶MB（CK-MB）及低蛋白血症为儿童重型丛林斑疹伤寒的最优预测因子。基于上述6项预测因子绘制列线图。训练集内该列线图的受试者工作特征（receiver operating characteristic, ROC）曲线下面积为0.870（95%CI：0.812~0.928），验证集内为0.839（95%CI：0.712~0.967）。校准曲线结果显示该列线图拟合效果良好，决策曲线分析（decision curve analysis, DCA）表明该列线图具有临床获益价值。 研究结论：本研究基于Hb、PLT、LDH、BUN、CK-MB及低蛋白血症6项预测因子，开发并验证了一款易于使用的儿童重型丛林斑疹伤寒预测列线图，该模型展现出优异的预测效能，但仍需开展外部前瞻性验证以评估其潜在临床应用价值。