(1) Background: Urinary tract infection (UTI) is a leading cause of emergency department visits and hospital admissions. Despite many studies identifying UTI-related risk factors for bacteremia or sepsis, a significant gap remains in developing predictive models for in-hospital mortality or the necessity for emergent intensive care unit admission in the emergency department. This study aimed to construct interpretable machine learning models capable of identifying patients at high risk for critical outcomes. (2) Methods: This was a retrospective study of adult patients with urinary tract infection (UTI), extracted from the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database. The critical outcome is defined as either in-hospital mortality or transfer to an intensive care unit within 12 h. ED visits were randomly partitioned into a 70%/30% split for training and validation. The extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) algorithms were constructed using variables selected from the stepwise logistic regression model. The XGBoost model was then compared to the traditional model and clinical decision rules (CDRs) on the validation data using the area under the curve (AUC). (3) Results: There were 3622 visits among 3235 unique patients diagnosed with UTI. Of the 2535 patients in the training group, 836 (33%) experienced critical outcomes, and of the 1087 patients in the validation group, 358 (32.9%) did. The AUCs for different machine learning models were as follows: XGBoost, 0.833; RF, 0.814; and SVM, 0.799. The XGBoost model performed better than others. (4) Conclusions: Machine learning models outperformed existing traditional CDRs for predicting critical outcomes of ED patients with UTI. Future research should prospectively evaluate the effectiveness of this approach and integrate it into clinical practice.

Background and Objectives: In patients with urolithiasis-related obstructive pyelonephritis (UROP), sepsis represents a critical and concerning complication that can substantially increase the mortality rate. This study aimed to identify the risk factors for sepsis in UROP patients and to develop a predictive nomogram model. Materials and Methods: We analyzed data from 148 patients who met the UROP criteria and were admitted to Chang Gung Memorial Hospital between 1 January 2016 and 31 December 2021. The primary outcome evaluated was the incidence of sepsis, as defined by the most recent Sepsis-3 guidelines. To identify potential risk factors for sepsis, we employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression technique. Subsequently, we utilized multivariable logistic regression to construct the predictive model. Results: There was a total of 102 non-sepsis cases and 46 sepsis cases. Risk factors for sepsis in multivariable analysis were a history of diabetes mellitus (DM) (OR = 4.24, p = 0.007), shock index (SI) (×10⁻¹) (OR = 1.55, p < 0.001), C-reactive protein (CRP) (mg/dL) (OR = 1.08, p = 0.005), and neutrophil to lymphocyte ratio (NLR) (×10) (OR = 1.58, p = 0.007). The nomogram exhibited an area under the receiver operating characteristic curve of 0.890 (95% CI 0.830–0.949). Conclusions: Our study demonstrated that patients with UROP who have DM, higher SI, higher NLR, and elevated CRP levels are significantly more likely to develop sepsis. These insights may aid in risk stratification, and it is imperative that clinicians promptly initiate treatment for those identified as high risk.