Construction of a Risk Assessment Model for Short-Term Mortality in Patients with Invasive Fungal Diseases...

To develop and validate a predictive model for assessing the risk of short-term mortality in patients with invasive fungal diseases (IFDs) following cardiac surgery. This retrospective study analyzed clinical data from patients diagnosed with postoperative IFDs in the cardiac surgical intensive care unit (ICU) of Qilu Hospital of Shandong University (QLH), between January 2020 and December 2023. A total of 98 patients were included and divided into a non-survival group (n = 42) and a survival group (n = 56) based on 28-day mortality. Demographic, clinical, and postoperative parameters were collected. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for variable selection, and selected variables were then entered into multivariate logistic regression to identify independent risk factors. A nomogram was developed, and its predictive performance was evaluated using the receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and clinical impact curve (CIC). Multivariate logistic regression, following variable selection by LASSO, identified a history of smoking, an elevated SOFA score, mean arterial pressure (MAP) below 70 mmHg, and tachyarrhythmia as independent risk factors for short-term mortality in this cohort (p < 0.05). The prediction model demonstrated excellent discrimination, with an area under the ROC curve (AUC) of 0.886 (95% CI: 0.816-0.957). The calibration curve showed good agreement between predicted and observed outcomes, with a mean absolute error of 0.023. Decision curve analysis indicated a net clinical benefit across a threshold probability range of 0.1 to 0.87. The clinical impact curve confirmed a high concordance between predicted mortality and actual outcomes. A history of smoking, an elevated SOFA score, MAP below 70 mmHg, and tachyarrhythmia independently predict short-term mortality in patients with IFDs after cardiac surgery. Therefore, the nomogram constructed from these factors provides an accurate and clinically applicable tool for risk stratification.