Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia

Abstract

Background: Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.

Methods: Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality.

Results: 315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) μg/L vs 1.4 (5.9) μg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001).

Conclusion: CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.

Keywords: Imaging/CT MRI etc; Pneumonia; Respiratory Infection.

Figure 1

Datasets for CAPE model development and prospective cohort study. (A) Retrospective dataset for model training, validation and testing. (B) Prospective cohort study to assess model discrimination for 30-day mortality. CAPE, CAP AI predictive Engine; CXR, chest radiography.

Figure 2

AI generated Grad-CAM heatmap of a CXR with community-acquired pneumonia. Frontal chest radiograph (A) of a patient presenting with acute respiratory failure secondary to pneumonia, performed in the emergency department. Grad-CAM heatmap (B) highlights areas of greatest class activation by the AI model, which corresponds to areas of pulmonary consolidation, with the extent and intensity of activation mirroring the severity of pneumonia. AI, artificial intelligence; CXR, chest radiography; Grad-CAM, gradient-weighted class activation map.

Figure 3

(A) CAPE mortality risk score and pneumonia severity scores receiver operator characteristic curves for 30-day mortality. (B) PSI+CAPE mortality risk score and PSI receiver operator characteristic curves for 30-day mortality. (C) CURB-65+ CAPE mortality risk score and CURB-65 receiver operator characteristic curves for 30-day mortality. AUROC, area under the receiver operating characteristic curve; CAPE, CAP AI predictive Engine; CURB-65, Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 years old; PSI, Pneumonia Severity Index.