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

Abstract

BackgroundChest 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.MethodsDeep-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.Results315 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).ConclusionCXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach

“…Risk prediction using “deep learning extracted” radiographic features sidesteps the need for accurate image annotation. However, these black box models suffer greatly from lack of accountability and interpretability, which are crucial for responsible implementation of AI systems in safety–critical applications 2 , 3 , 5 . According to the authors, regions of airspace and interstitial opacification were apparently highlighted by saliency mapping.…”

Artificial intelligence for the optimal management of community-acquired pneumonia

“…Revolutionary methods for identifying individuals with an elevated risk of severe CAP are imperative. The realm of AI in healthcare is undergoing rapid advancements, with ongoing research delving into innovative approaches to enhance the efficacy of AIdriven disease risk scores specifically tailored for CAP [ 24,34]. The potential of AI and ML in refining severity scores for CAP may help identify unobserved characteristics and patterns, leading to more accurate classifications of patients with different phenotypes of CAP.…”

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: Efficient development of auditable risk prediction models via a fine-tuning approach

“…Risk prediction using "deep learning extracted" radiographic features sidesteps the need for accurate image annotation. However, these black box models suffer greatly from lack of accountability and interpretability, which are crucial for responsible implementation of AI systems in safety-critical applications 2,3,5 .…”

“…Conventional chest radiography is inexpensive, routinely obtained in the emergency department (ED), and available in low resource settings. However, radiographic features have only been used for fully automated clinical risk prediction in relatively few machine learning models [1][2][3][4][5] .…”