Clinical predictors for etiology of acute diarrhea in children in resource-limited settings

Background: 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. Methods: 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. Results: 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. Conclusion: 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. Author summary: 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.