Synergistic impact of Gram-negative bacterial co-infection on invasive pulmonary aspergillosis in non-neutropenic patients: a machine learning-based risk stratification approach

Key Points

• To evaluate how Gram-negative bacterial co-infection affects the risk of invasive pulmonary aspergillosis (IPA) in non-neutropenic patients.
• Utilized an ensemble machine learning model integrating seven predictive factors.
• Implemented in a multicenter prospective study setting for validation.
• Focused on clinical outcomes and actionable stratification.
• Confirmed significant amplification of IPA risk with bacterial co-infection.
• Achieved accurate and interpretable risk stratification for clinical use.
• Emphasized the need for precision prophylaxis and timely antifungal treatment.