Optimizing chest X-rays as a leading diagnostic modality for handling COVID-19: a diagnostic study
Open Access
- 1 June 2025
- journal article
- Published by Institute of Advanced Engineering and Science in International Journal of Public Health Science (IJPHS)
- Vol. 14 (2) , 799-807
Abstract
Recent studies have highlighted that chest CT scans are crucial for accurately diagnosing COVID-19. However, in rural areas of Indonesia, people may have difficulty assessing CT scans, leading to increased undetected cases. To address this issue, we investigated whether chest X-rays (CXR) could replace CT scans in diagnosing COVID-19 patients. A diagnostic cross-sectional-based study was conducted at Fatmawati General Hospital from January to September 2021. The study included suspected COVID-19 patients in isolation wards and ICU who were over 18, with or without comorbidities, and had complete clinical data and laboratory tests. We analyzed imaging data through reverse transcription-polymerase chain reaction (RT-PCR) tests, CXR, and chest CT scans. This study enrolled 150 eligible patients. With RT-PCR as the gold standard, we found that CXR had a sensitivity of 86.6% (95% CI: 78.9-92.3%) and chest CT scan had a sensitivity of 91.1% (95% CI: 84.2-95.6%). Similar performance was observed when detecting ground glass opacities (GGO), bilateral laterobasal, and influenza-like syndrome and dyspnea (ILI) between CXR and CT scans. Receiver operating characteristic (ROC) curves demonstrated that CXR is comparable to CT scan, especially in ground glass opacity (GGO) and consolidation (AUC=0.72; 95% CI: 0.61-0.83 and AUC=0.710; 95% CI: 0.64-0.78). The proposed CXR method can be a reliable primary imaging tool for diagnosing COVID-19 by considering ILI. However, chest CT scans remain the most effective diagnostic method for COVID-19. These findings may be useful for the utilization of CXR for diagnosing COVID-19 in areas with limited access to CT scans.Keywords
This publication has 35 references indexed in Scilit:
- A comprehensive review of analyzing the chest X-ray images to detect COVID-19 infections using deep learning techniquesSoft Computing, 2023
- COVID-19 chest X-ray image classification in the presence of noisy labelsDisplays, 2023
- COV-RadNet: A Deep Convolutional Neural Network for Automatic Detection of COVID-19 from Chest X-Rays and CT ScansComputer Methods and Programs in Biomedicine Update, 2022
- A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray imagesComputers in Biology and Medicine, 2021
- Fully automated unified prognosis of Covid-19 chest X-ray/CT scan images using Deep Covix-Net modelComputers in Biology and Medicine, 2021
- FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image SegmentationBiocybernetics and Biomedical Engineering, 2021
- Comparing CT scan and chest X-ray imaging for COVID-19 diagnosisBiomedical Engineering Advances, 2021
- Multimodality imaging of COVID-19 pneumonia: from diagnosis to follow-up. A comprehensive reviewEuropean Journal of Radiology, 2020
- Thoracic imaging tests for the diagnosis of COVID-19Cochrane Database of Systematic Reviews, 2020
- Baseline chest X-ray in coronavirus disease 19 (COVID-19) patients: association with clinical and laboratory dataLa radiologia medica, 2020