Transforming post-acute pneumonia management: risk stratification using machine learning
Catia Cillóniz, Mads Lause Mogensen, Logan Ward · ERJ Open Research · 2026
Extract Community-acquired pneumonia (CAP) remains an important cause of morbidity and mortality worldwide, particularly among high-risk populations such as young children, immunosuppressed patients and elderly individuals with multiple comorbidities [1–3]. Advances in the diagnosis, antimicrobial treatment and general management of CAP has improved short-term prognosis [4]. However, the long-term sequelae, and particularly post-acute mortality in pneumonia are also frequently underestimated and neglected [5]. For example, a study from Spain highlights that 1-year mortality after hospitalisation for CAP is significant. 7.2% (93 out of 1284 patients) died within one year, with the most deaths occurring within the first 6 months. Early re-admission and comorbidities such as COPD, diabetes mellitus, cancer and dementia were strong predictors of long-term mortality [6].