Data-driven clustering identifies features distinguishing multisystem inflammatory syndrome from acute COVID-19 in children and adolescents.
Data-driven clustering identifies features distinguishing multisystem inflammatory syndrome from acute COVID-19 in children and adolescents.
复制标题
DOI：
10.1016/j.eclinm.2021.101112
复制
发表时间：
2021-10
影响因子：
15.1
通讯作者：
Overcoming COVID-19 Investigators
中科院分区：
文献类型：
--
作者：
Geva A;Patel MM;Newhams MM;Young CC;Son MBF;Kong M;Maddux AB;Hall MW;Riggs BJ;Singh AR;Giuliano JS;Hobbs CV;Loftis LL;McLaughlin GE;Schwartz SP;Schuster JE;Babbitt CJ;Halasa NB;Gertz SJ;Doymaz S;Hume JR;Bradford TT;Irby K;Carroll CL;McGuire JK;Tarquinio KM;Rowan CM;Mack EH;Cvijanovich NZ;Fitzgerald JC;Spinella PC;Staat MA;Clouser KN;Soma VL;Dapul H;Maamari M;Bowens C;Havlin KM;Mourani PM;Heidemann SM;Horwitz SM;Feldstein LR;Tenforde MW;Newburger JW;Mandl KD;Randolph AG;Overcoming COVID-19 Investigators
儿童多系统炎症综合征（MIS-C）共识标准设计为最大敏感性，因此捕获急性COVID-19肺炎患者。我们对2020年3月15日至2020年12月31日期间入院的1526名<21岁的covid -19相关疾病患者（684名临床医生标记为misc）的数据进行了无监督聚类。我们比较了集群中分配的misc标签和临床特征的患病率，然后通过递归特征消除来识别可能被错误分类的misc标签患者的特征。在测试的94个临床特征中，有46个被保留用于聚类。第1组患者（N = 498； 92%标记为misc）大多数以前健康（71%），平均年龄为7.2±0.4岁，主要是心血管（77%）和/或粘膜皮肤（82%）受累，高炎症生物标志物，大多数SARS-CoV-2 PCR阴性（60%）。第2组患者（N = 445； 27%标记为misc）经常有既往病史（79%，其中39%为呼吸道疾病），年龄相似（7.4±2.1岁），通常有胸片浸润（79%）和PCR检测阳性（90%）。第3组患者（N = 583例，19%标记为misc）较年轻（2.8±2.0岁），PCR阳性（86%），炎症较少。肺部浸润的影像学表现和阳性的SARS-CoV-2 PCR能准确区分第2组misc标记的患者和第1组患者。使用数据驱动，无监督的方法，我们确定了将患者聚类为具有高可能性的MIS-C组的特征。其他特征确定了一组更有可能患有急性严重COVID-19肺部疾病的患者，临床医生标记为misc的患者可能被错误分类。这些数据驱动的表型可能有助于改进MIS-C的诊断。这项工作由美国疾病控制与预防中心（75D30120C07725）和国立卫生研究院（K12HD047349和R21HD095228）资助。
Multisystem inflammatory syndrome in children (MIS-C) consensus criteria were designed for maximal sensitivity and therefore capture patients with acute COVID-19 pneumonia. We performed unsupervised clustering on data from 1,526 patients (684 labeled MIS-C by clinicians) <21 years old hospitalized with COVID-19-related illness admitted between 15 March 2020 and 31 December 2020. We compared prevalence of assigned MIS-C labels and clinical features among clusters, followed by recursive feature elimination to identify characteristics of potentially misclassified MIS-C-labeled patients. Of 94 clinical features tested, 46 were retained for clustering. Cluster 1 patients (N = 498; 92% labeled MIS-C) were mostly previously healthy (71%), with mean age 7·2 ± 0·4 years, predominant cardiovascular (77%) and/or mucocutaneous (82%) involvement, high inflammatory biomarkers, and mostly SARS-CoV-2 PCR negative (60%). Cluster 2 patients (N = 445; 27% labeled MIS-C) frequently had pre-existing conditions (79%, with 39% respiratory), were similarly 7·4 ± 2·1 years old, and commonly had chest radiograph infiltrates (79%) and positive PCR testing (90%). Cluster 3 patients (N = 583; 19% labeled MIS-C) were younger (2·8 ± 2·0 y), PCR positive (86%), with less inflammation. Radiographic findings of pulmonary infiltrates and positive SARS-CoV-2 PCR accurately distinguished cluster 2 MIS-C labeled patients from cluster 1 patients. Using a data driven, unsupervised approach, we identified features that cluster patients into a group with high likelihood of having MIS-C. Other features identified a cluster of patients more likely to have acute severe COVID-19 pulmonary disease, and patients in this cluster labeled by clinicians as MIS-C may be misclassified. These data driven phenotypes may help refine the diagnosis of MIS-C. This work was funded by the US Centers for Disease Control and Prevention (75D30120C07725) and National Institutes of Health (K12HD047349 and R21HD095228).
登录
查看更多内容
影响因子：
76.2
作者：
Calfee, Carolyn S.;Delucchi, Kevin;Parsons, Polly E.;Thompson, B. Taylor;Ware, Lorraine B.;Matthay, Michael A.
通讯作者：
Matthay, Michael A.
影响因子：
82.9
作者：
Long, Quan-Xin;Liu, Bai-Zhong;Huang, Ai-Long
通讯作者：
Huang, Ai-Long
影响因子：
120.7
作者：
Feldstein, Leora R.;Tenforde, Mark W.;Randolph, Adrienne G.
通讯作者：
Randolph, Adrienne G.
影响因子：
36.4
作者：
Goetzinger, Florian;Santiago-Garcia, Begona;Tebruegge, Marc
通讯作者：
Tebruegge, Marc
影响因子：
81.5
作者：
Matthay, Michael A.;Zemans, Rachel L.;Calfee, Carolyn S.
通讯作者：
Calfee, Carolyn S.