Accuracy of Plain Radiograph Interpretation by General Physicians during Night Shifts at Phanatnikhom Hospital
Article Sidebar
Main Article Content
Abstract
Background: Accurate interpretation of plain radiographs is crucial for diagnosing diseases in the emergency department. M1-level hospitals often lack a radiologist consultation system during night shifts, so interpretation falls to general physicians. Their limited experience may lead to errors that affect patient care. Currently, there is a lack of evidence on the diagnostic accuracy of this group of physicians in the emergency setting.
Objective: To assess the diagnostic accuracy of general physicians in interpreting plain radiographs during night shifts in the emergency department and to analyze the characteristics of common errors.
Methods: This retrospective descriptive study reviewed 1,146 plain radiographs obtained between April 2024 and March 2025 at Phanatnikhom Hospital during night duty hours. A radiologist's interpretation was used as the reference standard. Their findings were compared with the interpretations by general physicians, and errors were categorized as false positives, false negatives, or partial interpretations.
Results: General physicians demonstrated an overall interpretation accuracy of 95.9%, with a sensitivity of 95.0%, a specificity of 96.4%, a PPV of 93.6%, and an NPV of 97.2%. A total of 32 errors (4.1%) were found: 14 false negatives (1.8%), mostly missed infiltrations 12 false positives (1.5%), primarily over-diagnoses of infiltration; and 6 partial interpretations (0.8%), such as reporting pneumothorax but missing a rib fracture, or reporting cephalization but missing a pleural effusion.
Conclusions: General physicians at an M1-level hospital demonstrate high accuracy in interpreting plain radiographs during night shifts. However, errors, particularly false negatives and partial interpretations of subtle findings, remain a concern. Further training and the consideration of using AI-assisted tools could help reduce these errors and improve the quality of patient care.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Gefter WB, Post BA, Hatabu H. Commonly Missed Findings on Chest Radiographs: Causes and Consequences. Chest 2023;163(3):650-61. doi: 10.1016/j.chest.2022.10.039.
Jimah BB, Baffour Appiah A, Sarkodie BD, Anim D. Competency in Chest Radiography Interpretation by Junior Doctors and Final Year Medical Students at a Teaching Hospital. Radiol Res Pract 2020;2020:8861206. doi: 10.1155/2020/8861206.
A Halim NI, Mohd Zaki F, Manan HA, Mohamed Z. An Evaluation of the Quality of Plain Radiograph Interpretations by Radiology Trainees: A Single Institution Experience. Diagnostics (Basel) 2022;12(8):1954. doi: 10.3390/diagnostics12081954.
Bergus GR, Franken EA Jr, Koch TJ, Smith WL, Evans ER, Berbaum KS. Radiologic interpretation by family physicians in an office practice setting. J Fam Pract 1995;41(4):352-6. PMID: 7561708
Petinaux B, Bhat R, Boniface K, Aristizabal J. Accuracy of radiographic readings in the emergency department. Am J Emerg Med 2011;29(1):18-25. doi: 10.1016/j.ajem.2009.07.011.
Pinto A, Reginelli A, Pinto F, Lo Re G, Midiri F, Muzj C, et al. Errors in imaging patients in the emergency setting. Br J Radiol 2016;89(1061):20150914. doi: 10.1259/bjr.20150914.
Huang J, Neill L, Wittbrodt M, Melnick D, Klug M, Thompson M, et al. Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department. JAMA Netw Open 2023;6(10):e2336100. doi: 10.1001/jamanetworkopen.2023.36100.
Ahn JS, Ebrahimian S, McDermott S, Lee S, Naccarato L, Di Capua JF, et al. Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency. JAMA Netw Open 2022;5(8):e2229289. doi:10.1001/jamanetworkopen.2022.29289.
Bennani S, Regnard NE, Ventre J, Lassalle L, Nguyen T, Ducarouge A, et al. Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs. Radiology 2023;309(3):e230860. doi: 10.1148/radiol.230860.
รุ่งนภา อนุพงศ์พิพัฒน์. การเปรียบเทียบการแปลผลภาพถ่ายรังสีทรวงอก: กรณีการแปลผลโดยรังสีแพทย์และเทคโนโลยีปัญญาประดิษฐ์ โรงพยาบาลกาฬสินธุ์. วารสารโรคมะเร็ง 2567;44(3):173-83.
