Abstract Diarrheal diseases are the among the leading cause of death in children worldwide, most of which occur in low-income countries. In high-income countries, pediatric diarrhea remains a major utilization of healthcare resources. The cornerstone for management of diarrhea is rehydration, though antimicrobials are beneficial in some instances. Unfortunately, given that treatment is frequently empiric, based mostly on clinical suspicion for bacterial causes, antimicrobials are overused in management of diarrheal illness worldwide. In high-income countries, diagnostic testing is oftentimes overutilized. Thus, there is a need for clinical decision support tools for antimicrobial and diagnostic stewardship in many settings. Current clinical prediction tools are based mostly on patient-intrinsic properties such as the clinical exam and symptom history specific for that patient. We have preliminary data suggesting that the integration of patient-extrinsic data, including climate and seasonality parameters, and population-level pre-test probabilities (from prior patients and prior years’ prevalence), can improve the performance of a clinical prediction model. We also have preliminary data showing the potential for an electronic clinical decision-support tool (eCDST) that estimates diarrheal etiology to decrease antibiotic prescription rates. Our overarching goal is to: 1) improve diarrhea clinical prediction through integration of patient-extrinsic data sources, and 2) explore the potential feasibility and utility of an eCDST, such as a smartphone application or an electronic health record tool. In Aim 1, we will use data from several prospective clinical studies of pediatric diarrhea to build improved clinical prediction models that includes patient-extrinsic data sources. In Aim 2, we will determine the potential feasibility, utility, and economic impact of an eCDST for antibiotic and diagnostic stewardship by examining clinican and caregiver perspectives through in-depth interviews and focus groups. We will also perform an economic evaluation of eCDST in a US setting. Completion of the Aims will result in an optimized clinical prediction model using big data and lay the groundwork needed to inform the design of implementation studies of eCDSTs for management of pediatric diarrhea.