Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia.

Christian Salvatore,Matteo Interlenghi,Cristina Messa,Davide Ippolito,Marco Alì,Davide Gandola,Francesco Sardanelli,Isabella Castiglioni,Davide Capra,Andrea Cozzi,Caterina B Monti,Annalisa Polidori,Simone Schiaffino

doi:10.3390/diagnostics11030530

Abstract

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.

Highlights

Differential diagnosis of COVID-19 from other types of pneumonia has been a highpriority research topic and clinical aim since the early stages of the current pandemic [1,2].Prompt identification of COVID-19 cases is paramount to ensure proper management and better patient outcomes [3,4,5]
Any tool to be applied for this aim should have a good cost–benefit ratio for the healthcare service, be able to adapt to heterogeneous settings, and be useful outside COVID-19 pandemic peak, enabling accurate differential diagnosis with other types of pneumonia, such as non-COVID-19 community-acquired pneumonia (CAP) [2,5,6,7,8]
A total of 162 patients who underwent chest X-rays (CXRs) and tested positive for SARS-CoV-2 infection at reverse transcription polymerase chain reaction (RT-PCR) in Centers 1 and 2 from 21 February 2020 to 16 March 2020 were included in our retrospective evaluation

Summary

Introduction

Differential diagnosis of COVID-19 from other types of pneumonia has been a highpriority research topic and clinical aim since the early stages of the current pandemic [1,2].Prompt identification of COVID-19 cases is paramount to ensure proper management and better patient outcomes [3,4,5]. The use of CT implies higher healthcare costs since CT scanners have relatively limited availability, even in high-income countries, and CT equipment and rooms need sanitization after each use involving suspected or confirmed cases unless a continuous series of confirmed cases has to be studied [14,15,16]. In this context, the use of chest X-ray imaging (CXR)

Objectives

Methods

Results

Discussion

Conclusion