ISSN: 1859 - 2872
Effectiveness of artificial intelligence in chest radiograph interpretation
Main Article Content
Keywords
Abstract
Objective: To evaluate the effectiveness of the DrAid artificial intelligence (AI) software in interpreting posteroanterior chest radiographs. Subjects and Methods: A cross-sectional descriptive study was conducted on 637 posteroanterior chest X-rays performed at 108 Military Central Hospital from October 2024 to March 2025. The sensitivity, specificity, and area under the curve (AUC) of the DrAid AI system were assessed and compared with interpretations by radiologists, using computed tomography (CT) findings as the reference standard. Results: Across different lesion types, the AI model achieved a sensitivity ranging from 64.58% to 85.91%, a specificity between 83% and 98.52%, and an area under the ROC curve (AUC) from 0.792 to 0.885. AI model demonstrated higher sensitivity, specificity, and AUC than radiologists in detecting most types of pulmonary abnormalities assessed in the study, both in independent readings and when AI assistance was provided. The use of AI reduced the average image interpretation time by 17.03 seconds, equivalent to a 21% improvement in reading efficiency. Conclusion: Artificial intelligence proves to be an effective tool for enhancing the quality and efficiency of chest X-ray interpretation. However, optimal effectiveness requires a clear understanding of the AI system’s capabilities and limitations.
Article Details
References
2. Souhail Bennani, Nor-Eddine Regnard et al (2023) Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs 309(3): 230860.
3. Lili Guo, Changsheng Zhou et al (2024) Deep Learning for Chest X-ray Diagnosis: Competition Between Radiologists with or Without Artificial Intelligence Assistance, Journal of Imaging Informatics in Medicine 37(3): 922-934.
4. Lind Plesner L, Müller FC et al (2023) Commercially Available Chest Radiograph AI Tools for Detecting Airspace Disease, Pneumothorax, and Pleural Effusion, Radiology, 308(3), p. e231236.
5. Y. Vasilev, A. Vladzymyrskyy et al. (2023), AI-Based CXR First Reading: Current Limitations to Ensure Practical Value, Diagnostics (Basel), 13(8).
6. J. Hofmeister N Garin et al (2024) Validating the accuracy of deep learning for the diagnosis of pneumonia on chest x-ray against a robust multimodal reference diagnosis: a post hoc analysis of two prospective studies, Eur Radiol Exp 8(1): 20.
7. Julius Henning Niehoff, Jana Kalaitzidis et al (2023) Evaluation of the clinical performance of an AI-based application for the automated analysis of chest X-rays, Scientific Reports 13(1): 3680.
8. Queralt Miró Catalina, Josep Vidal-Alaball et al (2024), Real-world testing of an artificial intelligence algorithm for the analysis of chest X-rays in primary care settings, Scientific Reports 14(1): 5199.
9. Ahn JS, Ebrahimian S et al (2022) Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency, JAMA Netw Open 5(8): 2229289.
10. Shelmerdine SC, Langan D et al (2018) Chest radiographs versus CT for the detection of rib fractures in children (DRIFT): A diagnostic accuracy observational study. Lancet Child Adolesc Health 2(11): 802-811.
11. Self WH, Courtney DM et al (2013) High discordance of chest x-ray and computed tomography for detection of pulmonary opacities in ED patients: Implications for diagnosing pneumonia, Am J Emerg Med 31(2): 401-405.
12. Pamela G Anderson, Hannah Tarder-Stoll et al (2024) Deep learning improves physician accuracy in the comprehensive detection of abnormalities on chest X-rays, Scientific Reports 14(1): 25151.
13. Lee HW, Jin KN et al (2023) Artificial Intelligence Solution for Chest Radiographs in Respiratory Outpatient Clinics: Multicenter Prospective Randomized Clinical Trial. Ann Am Thorac Soc 20(5): 660-667.
14. Hussein Soleimantabar, Ali Mahdavi et al (2025) Artificial Intelligence in Radiology: Perceptions, Adoption Barriers, and Trust Among Iranian Radiologists in a Global Context & InfoScience Trends 2(3): 1-12.
15. Niehoff JH, Kalaitzidis J et al (2023) Evaluation of the clinical performance of an AI-based application for the automated analysis of chest X-rays. Sci Rep 13(1): 3680.
16. Banerjee I, Bhattacharjee K et al (2023) "Shortcuts" Causing Bias in Radiology Artificial Intelligence: Causes, Evaluation, and Mitigation. J Am Coll Radiol 20(9): 842-851.
17. Brandon G Hill, Frances L Koback et al (2024) The risk of shortcutting in deep learning algorithms for medical imaging research, Scientific Reports 14(1): 29224.
Article Sidebar
