A nomogram for predicting mortality in acute ischemic stroke patients complicated by Enterobacteriaceae bloodstream...

Gram-negative Enterobacteriaceae bloodstream infection (BSI) is an increasingly recognized complication in patients with acute ischemic stroke (AIS) and is associated with substantial mortality. However, validated prognostic tools specifically targeting this high-risk population are lacking. This study aimed to identify the determinants of mortality in patients with AIS complicated by Enterobacteriaceae BSI and to construct a validated nomogram for individualized risk prediction. All adults with AIS who developed Enterobacteriaceae BSI between January 1, 2010 and August 31, 2025 at The First People's Hospital of Jiande were retrospectively enrolled. After excluding subjects with ≥ 5% missing data, 125 patients were retained. Univariable logistic regression was first performed to identify candidate predictors of in-hospital mortality. Subsequently, the Boruta algorithm was applied to select the most informative variables, which were then incorporated into a logistic regression-based nomogram. Discrimination, calibration, and clinical utility were evaluated by the area under the receiver operating characteristic curve, calibration plots (1000 bootstrap resamples), and decision curve analysis, respectively. Overall in-hospital mortality was 12.8% (16/125). After Boruta selection, 5 variables remained independently associated with mortality: admission to the intensive care unit, concurrent shock and respiratory failure, decreased hemoglobin, and decreased platelet count. The nomogram demonstrated excellent discrimination (area under the curve = 0.936, 95% CI = 0.866-0.988), good calibration, and superior net clinical benefit across a wide range of threshold probabilities in decision curve analysis. Intensive care unit admission, concomitant shock and respiratory failure, anemia, and decreased platelet count are key determinants of death in AIS patients with Enterobacteriaceae BSI. The proposed nomogram offers clinicians a practical, bedside tool for early risk stratification and may guide individualized therapeutic decisions in this vulnerable population.