@Article{info:doi/10.2196/46817,
author="Tenda, Eric Daniel
and Yunus, Reyhan Eddy
and Zulkarnaen, Benny
and Yugo, Muhammad Reynalzi
and Pitoyo, Ceva Wicaksono
and Asaf, Moses Mazmur
and Islamiyati, Tiara Nur
and Pujitresnani, Arierta
and Setiadharma, Andry
and Henrina, Joshua
and Rumende, Cleopas Martin
and Wulani, Vally
and Harimurti, Kuntjoro
and Lydia, Aida
and Shatri, Hamzah
and Soewondo, Pradana
and Yusuf, Prasandhya Astagiri",
title="Comparison of the Discrimination Performance of AI Scoring and the Brixia Score in Predicting COVID-19 Severity on Chest X-Ray Imaging: Diagnostic Accuracy Study",
journal="JMIR Form Res",
year="2024",
month="Mar",
day="7",
volume="8",
pages="e46817",
keywords="artificial intelligence; Brixia; chest x-ray; COVID-19; CAD4COVID; pneumonia; radiograph; artificial intelligence scoring system; AI scoring system; prediction; disease severity",
abstract="Background: The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. Objective: The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. Methods: We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. Results: The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95{\%} CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95{\%} CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95{\%} CI 0.818-0.908). Conclusions: The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings. ",
issn="2561-326X",
doi="10.2196/46817",
url="https://formative.jmir.org/2024/1/e46817",
url="https://doi.org/10.2196/46817",
url="http://www.ncbi.nlm.nih.gov/pubmed/38451633"
}