Early Bedside Risk Stratification in ICU Patients with Suspected Invasive Pulmonary Aspergillosis: A Minimalist Clinical Decision Support Model.

Background: Early diagnosis of Invasive Pulmonary Aspergillosis (IPA) in non-neutropenic ICU patients remains challenging due to the low specificity of radiological findings and the limited reliability of individual biomarkers. This diagnostic uncertainty often delays antifungal treatment and contributes to the high mortality associated with IPA. We aimed to develop a clinically interpretable model for early bedside risk stratification. Methods: We conducted a retrospective study including 298 ICU patients. A Logistic LASSO regression approach was used to identify the most informative predictors of IPA and to develop a parsimonious predictive model. Model performance was assessed through internal exploration and robustness testing under noise perturbation. Results: Three routinely available clinical variables were retained in the final model: pulmonary galactomannan, non-specific pulmonary infiltrates, and patient age, reflecting fungal burden, lung involvement, and host vulnerability, respectively, and identifying patients with a higher probability of culture-positive Aspergillus detection within a clinical context compatible with IPA. The final model showed promising discriminative performance, with an AUC of 0.836 ± 0.075, sensitivity of 0.72, and specificity of 0.74. Despite relying on only three routinely available clinical variables, the model maintained stable performance during internal exploration and robustness analyses. Conclusions: Within this cohort, the combination of positive pulmonary galactomannan, radiological infiltrates, and advanced age identifies a subgroup of ICU patients with a higher probability of microbiological positivity and clinical suspicion of IPA, supporting early risk assessment rather than definitive diagnosis. This simple and transparent predictive model may support early clinical evaluation and risk stratification of ICU patients and assist clinicians in identifying patients requiring further diagnostic assessment.