A New Model of Organizing Mass Screening Based on Stand-Alone Artificial Intelligence Used for Fluorography Image Triage

Introduction: A rapid development of artificial intelligence software, including that for the analysis of digital fluorography images, has been noted recently. Pre-registered as a medical device, this software can be used for stand-alone analysis and triage of test results, allowing radiologists to focus on pathological findings.

Objective: To substantiate the possibility and efficiency of using artificial intelligence software for stand-alone analysis and triage of digital fluorography images.

Materials and methods: 88,048 digital fluorograms obtained in the first quarter of 2023 were processed using the artificial intelligence software registered in the Russian Federation as a medical device and a ROC analysis of the findings was carried out.

Results: We established that default software settings with the sensitivity of 90.4 % (95 % CI: 88.2–92.7) produced specificity of 75.5 % (95 % CI: 75.2–75.8) and accuracy of 75.6 % (95 % CI: 75.3–75.9). At the maximum sensitivity of 100.0 % (95 % CI: 100–100), specificity was 77.4 % (95 % CI: 74.8–80.0) and accuracy was as high as 77.9 % (95 % CI: 75.3–80.5). We have proposed a model of organizing health care which provides for stand-alone sorting of fluorography images by the software, saving normal results without their verification by a radiologist, and sending images with abnormal findings to a radiologist for diagnosis (in the future, as artificial intelligence improves, the latter will be immediately sent to a physician of the clinical specialty).

Conclusions: The established optimal scenario includes the use of artificial intelligence software to identify normal findings, which examination by a radiologist is optional when the algorithm is set to maximum sensitivity. Only the findings classified as abnormal will be subject to mandatory revision. The annual economic benefit gained by practical implementation of this approach nationwide can reach 5.6 billion rubles.

1. Morozov SP, Vladzymyrskyy AV, Ledikhova NV. Teleradiology in Russian Federation: State-of-art. Vrach i Informatsionnye Tekhnologii. 2019;(2):67-73. (In Russ.)

2. Karpov AV, Bolotskikh VV, Karpov DS. [The value of digital fluorographic examination in the early diagnosis of pulmonary forms of tuberculosis in modern conditions.] Tuberkulez i Sotsial’no-Znachimye Zabolevaniya. 2019;(4):50-51. (In Russ.)

3. Lomakov SYu, Stroganov EA. [Modern aspects of organizing prophylactic radiation studies using fluorography.] Mezhdunarodnyy Akademicheskiy Vestnik. 2019;(11(43)):4-6. (In Russ.)

4. Markelov YuM, Shchegoleva LV. Clinical and economic aspects of tuberculosis detection during mass fluorographic examinations of the population. Vestnik Rentgenologii i Radiologii. 2021;102(3):148-154. (In Russ.) doi: 10.20862/0042-4676-2021-102-3-148-154

5. Markelov YuM, Schegoleva LV. Evaluation of clinical and economic efficiency and impact of mass fluorography screening on tuberculosis epidemiological rates in four federal districts of the Russian Federation with different levels of population coverage with mass fluorography screening. Tuberkulez i Bolezni Legkikh. 2023;101(1):816. (In Russ.) doi: 10.58838/2075-1230-2023-101-1-8-16

6. Rubis LV. Efficiency of mass preventive examinations of the urban population for the purpose of early diagnosis of tuberculosis in primary health care institutions. Sovremennye Problemy Zdravookhraneniya i Meditsinskoy Statistiki. 2021;(3):1-13. (In Russ.) doi: 10.24412/23122935-2021-3-1-13

7. Geijer H, Geijer M. Added value of double reading in diagnostic radiology,a systematic review. Insights Imaging. 2018;9(3):287–301. doi: 10.1007/s13244-018-0599-0

8. Posso M, Puig T, Carles M, Rué M, Canelo-Aybar C, Bonfill X. Effectiveness and cost-effectiveness of double reading in digital mammography screening: A systematic review and meta-analysis. Eur J Radiol. 2017;96:40-49. doi: 10.1016/j.ejrad.2017.09.013

9. Johnson AEW, Pollard TJ, Berkowitz SJ, et al. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data. 2019;6(1):317. doi: 10.1038/s41597-019-0322-0

10. Do HM, Spear LG, Nikpanah M, et al. Augmented radiologist workflow improves report value and saves time: A potential model for implementation of artificial intelligence. Acad Radiol. 2020;27(1):96-105. doi: 10.1016/j.acra.2019.09.014

11. Harris M, Qi A, Jeagal L, et al. A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis. PLoS One. 2019;14(9):e0221339. doi: 10.1371/journal.pone.0221339

12. Codlin AJ, Dao TP, Vo LNQ, et al. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci Rep. 2021;11(1):23895. doi: 10.1038/s41598-021-03265-0

13. Adams SJ, Henderson RDE, Yi X, Babyn P. Artificial intelligence solutions for analysis of X-ray images. Can Assoc Radiol J. 2021;72(1):60-72. doi: 10.1177/0846537120941671

14. Wu JT, Wong KCL, Gur Y, et al. Comparison of chest radiograph interpretations by artificial intelligence algorithm vs radiology residents. JAMA Netw Open. 2020;3(10):e2022779. doi: 10.1001/jamanetworkopen.2020.22779

15. Miró Catalina Q, Fuster-Casanovas A, Solé-Casals J, Vidal-Alaball J. Developing an artificial intelligence model for reading chest X-rays: Protocol for a prospective validation study. JMIR Res Protoc. 2022;11(11):e39536. doi: 10.2196/39536

16. Zinchenko V, Chetverikov S, Akhmad E, et al. Changes in software as a medical device based on artificial intelligence technologies. Int J Comput Assist Radiol Surg. 2022;17(10):1969-1977. doi: 10.1007/s11548-02202669-1

17. Yoo H, Kim EY, Kim H, et al. Artificial intelligence-based identification of normal chest radiographs: A simulation study in a multicenter health screening cohort. Korean J Radiol. 2022;23(10):1009-1018. doi: 10.3348/kjr.2022.0189

18. Bradley SH, Bhartia BS, Callister ME, et al. Chest X-ray sensitivity and lung cancer outcomes: A retrospective observational study. Br J Gen Pract. 2021;71(712):e862-e868. doi: 10.3399/BJGP.2020.1099

19. Ahn JS, Ebrahimian S, McDermott S, 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

20. Codlin AJ, Dao TP, Vo LNQ, et al. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci Rep. 2021;11(1):23895. doi: 10.1038/s41598-021-03265-0

21. Abedalla A, Abdullah M, Al-Ayyoub M, Benkhelifa E. Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures. PeerJ Comput Sci. 2021;7:e607. doi: 10.7717/peerj-cs.607

22. Albahli S, Nazir T. AI-CenterNet CXR: An artificial intelligence (AI) enabled system for localization and classification of chest X-ray disease. Front Med (Lausanne). 2022;9:955765. doi: 10.3389/fmed.2022.955765

23. Harkness R, Hall G, Frangi AF, Ravikumar N, Zucker K. The pitfalls of using open data to develop deep learning solutions for COVID-19 detection in chest X-rays. Stud Health Technol Inform. 2022;290:679-683. doi: 10.3233/SHTI220164