Proposal Summary Acute kidney injury (AKI) affects up to 33% of hospitalized pediatric patients within the United States. Patients with hospitalizations complicated by AKI have an increased mortality rate of 15.3%. AKI is associated with adverse short-term outcomes such as increased length of hospital stays and increased mortality among adult and pediatric populations. Additionally, pediatric patients who develop AKI are at a high risk for developing chronic kidney disease (CKD). The etiology of AKI is multifactorial as demographic information, disease, illness severity, nephrotoxic medication (NTMx) administration, and therapeutic factors all increase a patient’s risk of developing AKI. Currently, there is no existing prediction model available to identify non-critically ill patients risk of AKI development. Early recognition of AKI will decrease adverse events such as the development of CKD, prolonged hospitalizations, and will ultimately promote the improved quality of life for these patients. Therefore, the purpose of this study is to develop a clinical prediction model to estimate the risk of AKI development among non-critically ill hospitalized pediatric patients. The specific aims of the proposed project are to: 1. Develop and validate a clinical prediction model at the point of admission for AKI among non-critically ill hospitalized pediatric patients, that closes the gap between actual and NINJA identified AKI. The potential predictors in the model include comorbidities, sex, age, race, height, weight, prior hospitalizations, and serum creatinine. Predictors will be selected to maximize the sensitivity and specificity of the prediction model, 2. Determine if inpatient factors during the hospitalization, such as fluid balance and nephrotoxic medication administration, enhance the prediction model. The NINJA database was established in 2016 and monitors for NTMx administration among hospitalized pediatric patients using variables from the EHR. It has the ability to capture when a patient has developed AKI or is at risk for developing AKI based on the NTMx they are receiving. The risk factors of AKI listed in Aim 1 will inform the development of the prediction model. Then, inpatient factors during a hospitalization will be incorporated to further enhance the prediction model. This innovative work holds significant promise to improve renal outcomes in children, a goal that is perfectly aligned with the strategic priority of NIDDK to prevent the development and halt the progression of kidney disease. This provides an exceptional training opportunity to the applicant to develop the analytic skills to develop a prediction model using regression modeling.