A nomogram for early risk stratification of 30-day mortality in confirmed Acinetobacter baumannii bloodstream infection

Purpose Acinetobacter baumannii bloodstream infection (BSI) carries high mortality. This study aimed to develop and validate a nomogram incorporating age and routine laboratory parameters to predict 30-day mortality in patients with confirmed A. baumannii BSI, before antimicrobial susceptibility results are available. Methods This single-center retrospective study split into training (n=202) and validation (n=87) cohorts. Demographic data (sex, age) and laboratory parameters at diagnosis were collected for model development, with the aim of providing early risk stratification after confirmation of A. baumannii BSI but before susceptibility results are available. Clinical characteristics were recorded for baseline description only. LASSO regression, the Boruta algorithm and multivariate logistic regression were employed to identify independent predictors from sex, age, and all laboratory indicators. Results The overall 30-day mortality rate was 33.17%. Five independent risk factors were identified: older age, elevated blood urea nitrogen (Urea), elevated sodium (Na), prolonged activated partial thromboplastin time (APTT), and lower mean corpuscular hemoglobin concentration (MCHC). The nomogram incorporating these factors demonstrated good discrimination, with an area under the ROC curve of 0.813 in the training cohort and 0.808 in the validation cohort. Calibration and decision curve analyses confirmed its accuracy and clinical utility. Conclusion The developed nomogram may serve as a potential tool for predicting 30-day mortality in patients with confirmed A. baumannii BSI, before antimicrobial susceptibility results are available. It is intended to support early risk assessment rather than to guide empirical antibiotic selection, which requires further prospective validation.