Construction and validation of a predictive in-hospital mortality nomogram in patients with staphylococcus aureus...

We aimed to construct and validate a predictive nomogram to evaluate in-hospital mortality of patients with S.aureus BSI. A 10-year retrospective cohort design was conducted to analyze data from 484 patients diagnosed with S. aureus BSI between 2014 and 2023. Clinical data from 339 patients (2014 to 2021) were harnessed in training cohort to develop a predictive nomogram, which underwent rigorous internal validation. An independent cohort of 145 patients (2022 to 2023) were collected for external validation. The prognostic performance of the model was comprehensively assessed using AUC, calibration curve, and DCA. We ultimately identified several key factors that were incorporated into the final prognostic nomogram: the ECFC score, the CCI score, procalcitonin levels, admission to the intensive care unit, and multimicrobial BSI. Internal validation was assessed via 5-fold cross-validation, repeated 400 times on the training cohort, yielding an average AUC value of 0.930 vs. 0.940 of the total. External validation further confirmed the nomogram's accuracy, with an AUC value of 0.929. Additionally, the calibration curves and DCAs revealed excellent consistency and substantial net clinical benefits in both cohorts. The development of this predictive nomogram marks a substantial breakthrough in the management of patients with S. aureus BSI.