Clinical predictors for etiology of acute diarrhea in children in resource-limited settings.
Clinical predictors for etiology of acute diarrhea in children in resource-limited settings.
复制标题
在资源有限的环境中，儿童急性腹泻病因的临床预测因子。
DOI：
10.1371/journal.pntd.0008677
复制
发表时间：
2020-10
影响因子：
3.8
通讯作者：
Leung DT
中科院分区：
文献类型：
--
作者：
Brintz BJ;Howard JI;Haaland B;Platts-Mills JA;Greene T;Levine AC;Nelson EJ;Pavia AT;Kotloff KL;Leung DT
腹泻是中低收入国家儿童发病和死亡的主要原因之一。在这种情况下，获得实验室诊断的机会往往有限，使用抗菌剂的决定往往是经验性的。临床预测因子是一种潜在的非实验室方法，可以更准确地评估腹泻病因，了解这些知识可以改善儿科腹泻的管理。我们使用来自全球肠道多中心研究（GEMS）的临床和定量分子病因学数据，这是一项前瞻性病例对照研究，旨在开发腹泻病因学的预测模型。使用随机森林，我们筛选了可用的变量，然后使用5倍交叉验证评估了随机森林回归模型和逻辑回归模型的预测性能。我们确定了1049例病毒是唯一病因的病例，并针对2317例病因已知但非病毒（细菌，原生动物或混合）的病例开发了预测模型。预测病毒病因的变量包括较低的年龄，干燥和寒冷的季节，增加的身高年龄z评分（HAZ），没有血性腹泻，呕吐的存在。交叉验证表明，使用5个变量的简约模型可以实现0.825的AUC，实现0.85的特异性、0.59的灵敏度、0.82的NPV和0.64的PPV。儿科腹泻病因的预测因子可供资源匮乏环境中的医疗服务提供者用于指导临床决策。使用非实验室方法诊断腹泻的病毒原因可能是减少全球不适当抗生素处方的一个步骤。腹泻是全世界幼儿死亡的主要原因之一。在资源匮乏的环境中，实验室检测不可用或过于昂贵，并且处方抗生素的决定通常是在没有检测的情况下做出的。利用临床信息来预测哪些病例是由病毒引起的，因此不需要抗生素，这将有助于改善抗生素的合理使用。我们使用了一项关于儿童腹泻的大型研究的数据，结合包括机器学习在内的先进统计方法，得出了可以预测腹泻病毒原因的主要临床因素。我们比较了1049例病毒是唯一原因的病例，以及2317例已知原因但不是病毒的病例。我们发现，较低的年龄，干燥和寒冷的季节，营养状况（由身高增加定义），缺乏血液腹泻和呕吐，是最能预测腹泻是否由病毒引起的临床因素。我们发现，仅使用这5个因素，我们就能够准确地预测病毒原因。我们的研究结果可以被医生用来指导儿童腹泻抗生素的适当使用。
Diarrhea is one of the leading causes of childhood morbidity and mortality in lower- and middle-income countries. In such settings, access to laboratory diagnostics are often limited, and decisions for use of antimicrobials often empiric. Clinical predictors are a potential non-laboratory method to more accurately assess diarrheal etiology, the knowledge of which could improve management of pediatric diarrhea. We used clinical and quantitative molecular etiologic data from the Global Enteric Multicenter Study (GEMS), a prospective, case-control study, to develop predictive models for the etiology of diarrhea. Using random forests, we screened the available variables and then assessed the performance of predictions from random forest regression models and logistic regression models using 5-fold cross-validation. We identified 1049 cases where a virus was the only etiology, and developed predictive models against 2317 cases where the etiology was known but non-viral (bacterial, protozoal, or mixed). Variables predictive of a viral etiology included lower age, a dry and cold season, increased height-for-age z-score (HAZ), lack of bloody diarrhea, and presence of vomiting. Cross-validation suggests an AUC of 0.825 can be achieved with a parsimonious model of 5 variables, achieving a specificity of 0.85, a sensitivity of 0.59, a NPV of 0.82 and a PPV of 0.64. Predictors of the etiology of pediatric diarrhea can be used by providers in low-resource settings to inform clinical decision-making. The use of non-laboratory methods to diagnose viral causes of diarrhea could be a step towards reducing inappropriate antibiotic prescription worldwide. Diarrhea is one of the leading causes of death in young children worldwide. In low-resource settings, laboratory testing is not available or too expensive, and the decision to prescribe antibiotics is often made without testing. Using clinical information to predict which cases are caused by viruses, and thus wouldn’t need antibiotics, would help to improve appropriate use of antibiotics. We used data from a large study of childhood diarrhea, paired with advanced statistical methods including machine learning, to come up with the top clinical factors that could predict a viral cause of diarrhea. We compared 1049 cases where a virus was the only cause, with 2317 cases where the cause was known but not a virus. We found that a lower age, dry and cold season, nutritional status defined by increased height, lack of blood diarrhea, and vomiting, were the clinical factors most predictive of whether the diarrhea was caused by a virus. We found that, using just those 5 factors, we were able to predict a viral cause with good accuracy. Our findings can be used by doctors to guide the appropriate use of antibiotics for diarrhea in children.
登录
查看更多内容
影响因子：
2.6
作者：
Saidi, SM;Iijima, Y;Honda, T
通讯作者：
Honda, T
影响因子：
11.8
作者：
Klein, Eileen J.;Boster, Daniel R.;Tarr, Phillip I.
通讯作者：
Tarr, Phillip I.
影响因子：
168.9
作者：
Kotloff, Karen L.;Nataro, James P.;Levine, Myron M.
通讯作者：
Levine, Myron M.
DOI：
10.1016/s2214-109x(18)30351-6
发表时间：
2018-12
期刊：
The Lancet. Global health
影响因子：
--
作者：
Rogawski ET;Liu J;Platts-Mills JA;Kabir F;Lertsethtakarn P;Siguas M;Khan SS;Praharaj I;Murei A;Nshama R;Mujaga B;Havt A;Maciel IA;Operario DJ;Taniuchi M;Gratz J;Stroup SE;Roberts JH;Kalam A;Aziz F;Qureshi S;Islam MO;Sakpaisal P;Silapong S;Yori PP;Rajendiran R;Benny B;McGrath M;Seidman JC;Lang D;Gottlieb M;Guerrant RL;Lima AAM;Leite JP;Samie A;Bessong PO;Page N;Bodhidatta L;Mason C;Shrestha S;Kiwelu I;Mduma ER;Iqbal NT;Bhutta ZA;Ahmed T;Haque R;Kang G;Kosek MN;Houpt ER;MAL-ED Network Investigators
通讯作者：
MAL-ED Network Investigators
影响因子：
7.2
作者：
Collins, Gary S.;Reitsma, Johannes B.;Moons, Karel G. M.
通讯作者：
Moons, Karel G. M.