使用机器学习在儿科急诊区分川崎病与其他发热儿童
这项诊断研究纳入4家医院(2家医疗中心、2家区域医院)2010年1月1日至2019年12月31日收治的74 641例5岁以下发热儿童,其中川崎病1142例、对照组73 499例。研究利用电子病历中的人口学数据和实验室检查(全血细胞计数及分类、尿液分析、生化)作为候选参数,采用监督式eXtreme Gradient Boosting(XGBoost)机器学习方法建立预测模型,以是否满足川崎病诊断标准为主要结局,用混淆矩阵和似然比评价模型性能。测试集中模型最佳性能为敏感度92.5%、特异度97.3%、阳性预测值34.5%、阴性预测值99.9%、阳性似然比34.0,受试者工作特征曲线下面积为0.980(95%CI 0.974-0.987)。作者认为,客观实验室检查结果可能成为川崎病的预测指标,XGBoost机器学习可帮助儿科急诊医生以出色的敏感度、特异度和准确度区分川崎病与其他发热儿童。
要点
- 测试集敏感度92.5%、特异度97.3%、阳性预测值34.5%、阴性预测值99.9%,阳性似然比34.0。
- 受试者工作特征曲线下面积为0.980(95%CI 0.974-0.987)。
- 川崎病组以男性为主(OR 1.79;95%CI 1.55-2.06),年龄较对照组更小(均值差-0.6岁[95%CI -0.6至-0.5岁])。
- 模型输入为电子病历中的人口学数据与实验室检查(全血细胞计数及分类、尿液分析、生化)。
- 研究纳入4家医院(2家医疗中心、2家区域医院)74 641例5岁以下发热儿童,其中川崎病1142例。
适用人群与场景
- 5岁以下发热儿童,来自4家医院(2家医疗中心、2家区域医院),2010年1月1日至2019年12月31日招募。
- 川崎病组1142例(平均[SD]年龄1.1[0.8]岁;男性687例[60.2%]),对照组73 499例发热儿童(平均[SD]年龄1.6[1.4]岁;男性41 465例[56.4%])。
研究设计与关键结果
- 诊断研究,纳入74 641例5岁以下发热儿童,来自4家医院(2家医疗中心、2家区域医院),川崎病1142例、对照组73 499例。
- 川崎病组男性比例更高(OR 1.79;95%CI 1.55-2.06),年龄更小(均值差-0.6岁[95%CI -0.6至-0.5岁])。
- 测试集模型最佳性能:敏感度92.5%、特异度97.3%、阳性预测值34.5%、阴性预测值99.9%、阳性似然比34.0。
- 受试者工作特征曲线下面积0.980(95%CI 0.974-0.987)。
证据类型、等级与局限
- 诊断研究;采用监督式XGBoost机器学习方法建立预测模型,用混淆矩阵和似然比评价性能。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,客观实验室检查结果可能成为川崎病的预测指标。
- 作者认为,XGBoost机器学习可帮助儿科急诊医生以出色的敏感度、特异度和准确度区分川崎病与其他发热儿童。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
IMPORTANCE: Early awareness of Kawasaki disease (KD) helps physicians administer appropriate therapy to prevent acquired heart disease in children. However, diagnosing KD is challenging and relies largely on subjective diagnosis criteria.
OBJECTIVE: To develop a prediction model using machine learning with objective parameters to differentiate children with KD from other febrile children.
DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study included 74 641 febrile children younger than 5 years who were recruited from 4 hospitals, including 2 medical centers and 2 regional hospitals, between January 1, 2010, and December 31, 2019. Statistical analysis was performed from October 2021 to February 2023.
MAIN OUTCOMES AND MEASURES: Demographic data and laboratory values from electronic medical records, including complete blood cell count with differential, urinalysis, and biochemistry, were collected as possible parameters. The primary outcome was whether the febrile children fulfilled the diagnostic criteria of KD. The supervised eXtreme Gradient Boosting (XGBoost) machine learning method was applied to establish a prediction model. The confusion matrix and likelihood ratio were used to evaluate the performance of the prediction model.
RESULTS: This study included a total of 1142 patients with KD (mean [SD] age, 1.1 [0.8] years; 687 male patients [60.2%]) and 73 499 febrile children (mean [SD] age, 1.6 [1.4] years; 41 465 male patients [56.4%]) comprising the control group. The KD group was predominantly male (odds ratio, 1.79; 95% CI, 1.55-2.06) with younger age (mean difference, -0.6 years [95% CI, -0.6 to -0.5 years]) compared with the control group. The prediction model's best performance in the testing set was able to achieve 92.5% sensitivity, 97.3% specificity, 34.5% positive predictive value, 99.9% negative predictive value, and a positive likelihood ratio of 34.0, which indicates outstanding performance. The area under the receiver operating characteristic curve of the prediction model was 0.980 (95% CI, 0.974-0.987).
CONCLUSIONS AND RELEVANCE: This diagnostic study suggests that results of objective laboratory tests had the potential to be predictors of KD. Furthermore, these findings suggested that machine learning with XGBoost can help physicians differentiate children with KD from other febrile children in pediatric emergency departments with excellent sensitivity, specificity, and accuracy.
参考来源
- Tsai CM, Lin CR, Kuo HC, et al. Use of Machine Learning to Differentiate Children With Kawasaki Disease From Other Febrile Children in a Pediatric Emergency Department. JAMA Netw Open. 2023. PMID: 37040115. doi:10.1001/jamanetworkopen.2023.7489
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。