Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients

Abstract

Objective: To evaluate whether the initial chest X-ray (CXR) severity assessed by an AI system may have prognostic utility in patients with COVID-19.

Methods: This retrospective single-center study included adult patients presenting to the emergency department (ED) between February 25 and April 9, 2020, with SARS-CoV-2 infection confirmed on real-time reverse transcriptase polymerase chain reaction (RT-PCR). Initial CXRs obtained on ED presentation were evaluated by a deep learning artificial intelligence (AI) system and compared with the Radiographic Assessment of Lung Edema (RALE) score, calculated by two experienced radiologists. Death and critical COVID-19 (admission to intensive care unit (ICU) or deaths occurring before ICU admission) were identified as clinical outcomes. Independent predictors of adverse outcomes were evaluated by multivariate analyses.

Results: Six hundred ninety-seven 697 patients were included in the study: 465 males (66.7%), median age of 62 years (IQR 52-75). Multivariate analyses adjusting for demographics and comorbidities showed that an AI system-based score ≥ 30 on the initial CXR was an independent predictor both for mortality (HR 2.60 (95% CI 1.69 - 3.99; p < 0.001)) and critical COVID-19 (HR 3.40 (95% CI 2.35-4.94; p < 0.001)). Other independent predictors were RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.

Conclusion: AI- and radiologist-assessed disease severity scores on CXRs obtained on ED presentation were independent and comparable predictors of adverse outcomes in patients with COVID-19.

Trial registration: ClinicalTrials.gov NCT04318366 ( https://clinicaltrials.gov/ct2/show/NCT04318366 ).

Key points: • AI system-based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients. • Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease. • The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.

Keywords: Artificial intelligence; COVID-19; Prognosis; Radiography; Severe acute respiratory syndrome.

Fig. 1

Flow diagram of our retrospective single-center cohort study

Fig. 2

Examples of the AI system (qXR v2.1 c2, Qure.ai Technologies) analysis overlay on initial CXRs of two patients in our cohort showing the percentage of pixels involved by opacity or consolidation for each lung. a Posteroanterior CXR of an 18-year-old male (34% right lung; 9% left lung; Qure AI score [(34 + 9)/2] = 21.5). b Anteroposterior CXR of an 81-year-old male (70% right lung; 34% left lung; Qure AI score [(70 + 34)/2] = 52)

Fig. 3

Kaplan-Meier estimates of survival according to Qure AI score optimal cutoff

Fig. 4

Kaplan-Meier estimates of survival according to the Radiographic Assessment of Lung Edema (RALE) score optimal cutoff

Fig. 5

Kaplan-Meier estimates of ICU-free survival according to the Qure AI score optimal cutoff

Fig. 6

Kaplan-Meier estimates of ICU-free survival according to the Radiographic Assessment of Lung Edema (RALE) score optimal cutoff