Machine-Learning Model for Mortality Prediction in Patients With Community-Acquired Pneumonia: Development and Validation Study

• Published in: Chest Vol. 163; no. 1; pp. 77 - 88
• Main Authors: Cilloniz, Catia, Ward, Logan, Mogensen, Mads Lause, Pericàs, Juan M, Méndez, Raúl, Gabarrús, Albert, Ferrer, Miquel, Garcia-Vidal, Carolina, Menendez, Rosario, Torres, Antoni
• Format: Journal Article
• Language: English
• Published: United States 01-01-2023
• Subjects: Aged; Artificial Intelligence; Community-Acquired Infections; Hospital Mortality; Humans; Machine Learning; Pneumonia - diagnosis; Prognosis; Retrospective Studies; ROC Curve; Severity of Illness Index; mortality prediction; pneumonia; community-acquired pneumonia; machine learning; artificial intelligence
• ISSN: 1931-3543
• DOI: 10.1016/j.chest.2022.07.005

Artificial intelligence tools and techniques such as machine learning (ML) are increasingly seen as a suitable manner in which to increase the prediction capacity of currently available clinical tools, including prognostic scores. However, studies evaluating the efficacy of ML methods in enhancing the predictive capacity of existing scores for community-acquired pneumonia (CAP) are limited. We aimed to apply and validate a causal probabilistic network (CPN) model to predict mortality in patients with CAP.
Is a CPN model able to predict mortality in patients with CAP better than the commonly used severity scores?
This was a derivation-validation retrospective study conducted in two Spanish university hospitals. The ability of a CPN designed to predict mortality in sepsis (SepsisFinder [SeF]), and adapted for CAP (SeF-ML), to predict 30-day mortality was assessed and compared with other scoring systems (Pneumonia Severity Index [PSI], Sequential Organ Failure Assessment [SOFA], quick Sequential Organ Failure Assessment [qSOFA], and CURB-65 criteria [confusion, urea, respiratory rate, BP, age ≥ 65 years]). The SeF models are proprietary software. Differences between receiver operating characteristic curves were assessed by the DeLong method for correlated receiver operating characteristic curves.
The derivation cohort comprised 4,531 patients, and the validation cohort consisted of 1,034 patients. In the derivation cohort, the areas under the curve (AUCs) of SeF-ML, CURB-65, SOFA, PSI, and qSOFA were 0.801, 0.759, 0.671, 0.799, and 0.642, respectively, for 30-day mortality prediction. In the validation study, the AUC of SeF-ML was 0.826, concordant with the AUC (0.801) in the derivation data (P = .51). The AUC of SeF-ML was significantly higher than those of CURB-65 (0.764; P = .03) and qSOFA (0.729, P = .005). However, it did not differ significantly from those of PSI (0.830; P = .92) and SOFA (0.771; P = .14).
SeF-ML shows potential for improving mortality prediction among patients with CAP, using structured health data. Additional external validation studies should be conducted to support generalizability.