The feasibility of double automated reading of chest radiographic screening results (based on the Moscow experiment on computer vision in radiology)

Introduction: Mass preventive chest imaging examinations (fluorography and X-ray) play a critical role in identifying diseases of public health significance, yet place an additional burden on the healthcare system. Automated sorting of imaging studies using medical devices (MD) powered by artificial intelligence (AI) technologies facilitates optimization by relieving radiologists from having to review studies without pathological findings. However, despite high AI accuracy, rare false-negative findings remain possible, which can be critical in medical screening.

Objective: The purpose of this retrospective study was to evaluate an automated dual reading method for autonomous sorting of preventive imaging studies.

Materials and methods: The study included 411 clinical cases previously misclassified as «normal.» Each study was reanalyzed by a different AI model.

Results: As a result, the re-classification yielded 31.6% correct pathology identification and reduced clinically important discrepancies by 25.5%. When simulating the automated dual reading, the proportion of false-negative findings decreased from 0.071% to 0.052%.

Discussion: The simulation revealed significant performance variability across the AI models, emphasizing the need for careful post-authorization monitoring to replace underperforming applications.

Conclusion: Thus, automated dual reading improves the safety of autonomous sorting by minimizing the number of missed pathological findings. At the same time, the method requires a strategic approach to AI model selection as it poses a risk of reducing the system’s operating efficiency. The optimal benefit-risk ratio should be determined against contribution of preventive programs to public health interest.

1. [Ignatyeva V.I., Kontsevaya A.V., Kalinina A.M. et al. Socio-economic efficiency of the early cancer detection during the medical checkup. The Russian Journal of Preventive Medicine, 2024, Vol. 27, No. 1, рр. 36–44 (In Russ.)]. https://doi.org/10.17116/profmed20242701136.

2. [Kravchenko A.F., Shepeleva L.P. Effectiveness and cost-effectiveness of mass fluorography screening of the population on the example of Sakha (Yakutia) Republic. CTRI Bulletin, 2021, No. 1, рр. 76–86 (In Russ.)]. https://doi.org/10.7868/S258766782101009X.

3. [Golubev N.А., Ogryzko E.V., Tyurina E.M. еt al. Features of the development of the radiation diagnostics service in the Russian Federation for 2014–2019. Current problems of health care and medical statistics, 2021, рр. 356– 375 (In Russ.)]. https://doi.org/10.24412/2312-2935-2021-2-356-376.

4. [Trofimova T.N., Kozlova O.V. Radiology in Saint-Petersburg‚ 2019. Diagnostic radiology and radiotherapy, 2020, Vol. 11, No. 4, рр. 96–99 (In Russ.)]. https://doi.org/10.22328/2079-5343-2020-11-4-96-99.

5. [Tyurin I.Е. Radiology in the Russian Federation. Journal of oncology: diagnostic radiology and radiotherapy, 2018, No. 1 (4), рр. 43–51 (In Russ.)]. https://doi.org/10.37174/2587-7593-2018-1-4-43-51.

6. [Shelekhov P.V. Personnel situation in radiative diagnostics. Current problems of health care and medical statistics, 2019, Vol. 1, рр. 265–275 (In Russ.)]. https://doi.org/10.24411/2312-2935-2019-10018.

7. [Nikitin E., Plaksin N., Garetz M., Gutin E. Comparison of the methods of operation of the artificial intelligence system in the ultra-high sensitivity mode for the autonomous description of chest X-rays without pathology. Digital Diagnostics, 2024, Vol. 5, No. S1, рр. 71–73 (In Russ.)]. doi: https://doi.org/10.17816/DD626001.

8. [Borodulin B.B., Gogoberidze Yu.T., Zhilinskaya K.V. et al. The experience of using artificial intelligence for automated analysis of digital radiographs in a city hospital. Digital Diagnostics, 2024, Vol. 5, No. S1, рр. 127–129 (In Russ.)]. doi: https://doi.org/10.17816/DD629896.

9. [Vasilev Yu.A., Tyrov I.A., Vladzymyrskyy A.V. et al. A New Model of Organizing Mass Screening Based on Stand-Alone Artificial Intelligence Used for Fluorography Image Triage. Public Health and Life Environment — PH&LE, 2023, Vol. 31, No. 11, рр. 23–32 (In Russ.)]. https://doi.org/10.35627/2219-5238/2023-31-11-23-32.

10. [Vasilev Yu.A., Sychev D.A., Bazhin A.V. et al. Autonomous artificial intelligence for sorting results of preventive radiological examinations of chest organs: medical and economic efficiency. Digital Diagnostics, 2025, Vol. 6, No. 1, рр. 5–22 (In Russ.)]. doi: https://doi.org/10.17816/DD641703.

11. Morozov S., Guseva E., Ledikhova N. еt al. Telemedicine-based system for quality management and peer review in radiology // Insights Imaging. 2018. Vol. 9, No. 3. Р. 337–341. doi: 10.1007/s13244-018-0629-y.

12. Guseva E., Morozov S., Burenchev D. еt al. Remote radiological audit: a regional quality assurance system // Insights Imaging. 2018. Vol. 9 (Suppl. 1). Р. 228–230. doi: 10.1007/s13244-018-0603-8.

13. Dyer T., Dillard L., Harrison M. et al. Diagnosis of normal chest radiographs using an autonomous deep-learning algorithm // Clin. Radiol. 2021. Jun; Vol. 76, No. 6. Р. 473. e9–473.e15. doi: 10.1016/j.crad.2021.01.015.

14. Kim T.K., Yi P.H., Wei J. et al. Deep Learning Method for Automated Classification of Anteroposterior and Posteroanterior Chest Radiographs // J. Digit Imaging. 2019. Dec. Vol. 32, No. 6. Р. 925–930. doi: 10.1007/s10278-019-00208-0.

15. Park C.M. AI: Workload Reduction by Autonomous Reporting of Normal Chest Radiographs // Radiology. 2023. May. Vol. 307, No. 3. e230252. doi: 10.1148/radiol.230252.

16. Plesner L.L., Müller F.C., Nybing J.D. et al. Autonomous Chest Radiograph Reporting Using AI: Estimation of Clinical Impact // Radiology. 2023. Vol. 307, No. 3. e222268. doi: 10.1148/radiol.222268.

17. [Vasilev Yu.A., Pamova A.P., Arzamasov K.M. et al. Presentation of diagnostic accuracy metrics based on classification of artificial intelligence software in radiology // Medical doctor and information technology, 2025, No. 1, рр. 58–69 (In Russ.)]. doi: 10.25881/18110193_2025_1_58.

18. Arzamasov K., Vasilev Y., Zelenova M. et al. Independent evaluation of the accuracy of 5 artificial intelligence software for detecting lung nodules on chest X-rays // Quant Imaging Med. Surg. 2024. Vol. 14, No. 8. Р. 5288–5303. doi: 10.21037/qims-24-160.

19. [Vasilev Yu.A., Vladzimirskyy A.V., Omelyanskaya O.V. et al. Review of meta-analyses on the use of artificial intelligence in radiology. Medical Visualization, 2024, Vol. 28, No. 3, рр. 22–41 (In Russ.)]. https://doi.org/10.24835/1607-0763-1425.

20. Kelly B.S., Judge C., Bollard S.M. et al. Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE) [published correction appears in Eur. Radiol. 2022. Nov; Vol. 32, No. 11. Р. 8054. doi: 10.1007/s00330-022-08832-1.] // Eur. Radiol. 2022. Vol. 32, No. 11. Р. 7998–8007. doi:10.1007/s00330-022-08784-6.

21. Ng C.K.C. Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection and Diagnosis in Pediatric Radiology: A Systematic Review // Children (Basel). 2023. Vol. 10, No. 3. Р. 525. Published 2023. Mar 8. doi:10.3390/children10030525.