External Validation of a Mobile Clinical Decision Support System for Diarrhea Etiology Prediction in Children: A Multicenter Study in Bangladesh and Mali

BackgroundDiarrheal illness is a leading cause of antibiotic use for children in low- and middle-income countries. Determination of diarrhea etiology at the point-of-care without reliance on laboratory testing has the potential to reduce inappropriate antibiotic use. MethodsThis prospective observational study aimed to develop and externally validate the accuracy of a mobile software application ("App") for the prediction of viral-only etiology of acute diarrhea in children 0-59 months in Bangladesh and Mali. The App used previously derived and internally validated models using combinations of "patient-intrinsic" information (age, blood in stool, vomiting, breastfeeding status, and mid-upper arm circumference), pre-test odds using location-specific historical prevalence and recent patients, climate, and viral seasonality. Diarrhea etiology was determined with TaqMan Array Card using episode-specific attributable fraction (AFe) >0.5. ResultsOf 302 children with acute diarrhea enrolled, 199 had etiologies above the AFe threshold. Viral-only pathogens were detected in 22% of patients in Mali and 63% in Bangladesh. Rotavirus was the most common pathogen detected (16% Mali; 60% Bangladesh). The viral seasonality model had an AUC of 0.754 (0.665-0.843) for the sites combined, with calibration-in-the-large =-0.393 (-0.455 - -0.331) and calibration slope {beta}=1.287 (1.207 - 1.367). By site, the pre-test odds model performed best in Mali with an AUC of 0.783 (0.705 - 0.86); the viral seasonality model performed best in Bangladesh with AUC 0.710 (0.595 - 0.825). ConclusionThe App accurately identified children with high likelihood of viral-only diarrhea etiology. Further studies to evaluate the Apps potential use in diagnostic and antimicrobial stewardship are underway.