基于人工智能的自主排序模型在胸部常规影像学检查结果中的应用:医学和经济效益
- 作者: Vasilev Y.A.1, Sychev D.A.2, Bazhin A.V.1, Shulkin I.M.1, Vladzymyrskyy A.V.1, Golikova A.Y.1, Arzamasov K.M.1, Mishchenko A.V.2, Bekdzhanyan G.A.2, Goldberg A.S.2, Rodionova L.G.1
-
隶属关系:
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
- Medical Academy of Continuous Professional Education
- 期: 卷 6, 编号 1 (2025)
- 页面: 5-22
- 栏目: 原创性科研成果
- URL: https://journal-vniispk.ru/DD/article/view/310048
- DOI: https://doi.org/10.17816/DD641703
- ID: 310048
如何引用文章
全文:
详细
论证。本文提出了一种基于人工智能技术的医疗设备模型,用于组织胸部常规影像学检查的预防性结果,通过设置最大灵敏度为1.0(95%置信区间1.0;1.0)来进行自主排序。该分类将大规模预防性检查(胸部透视和胸部X线摄影)结果分为两类:“非正常”和“正常”。 “非正常”类包括所有任何偏差(病理状态、疾病和手术后遗症、年龄和先天性特点等),这些需要提交给放射科医生进行描述。“正常”类则包括没有病理偏差的结果,可能无需放射科医生进一步描述。
目的。评估基于人工智能技术的自主排序模型在胸部常规影像学检查中的可行性、效果和效率。
方法。进行了前瞻性的多中心诊断研究,评估基于人工智能技术的医疗设备在胸部常规影像学检查中的安全性和质量,采用了分析和统计学研究方法。
结果。本研究纳入了575,549份预防性放射学检查结果,包括胸部透视和胸部X线摄影,并通过3款基于人工智能技术的医疗设备进行处理。在自主排序结果中,54.8%的检查结果被归类为“正常”,从而节省了放射科医生在解读和描述研究结果上的劳动量。自主排序的完全正确率为99.95%。临床上显著的偏差出现在0.05%的案例中(95%置信区间:0.04%;0.06%)。
结论。本研究证明了基于人工智能技术的医疗设备在胸部常规影像学检查中的医学和经济效益。下一步应针对相关法规的更新以及在预防医学任务中合法应用人工智能技术医疗设备的使用进行改进。
作者简介
Yuriy A. Vasilev
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: npcmr@zdrav.mos.ru
ORCID iD: 0000-0002-5283-5961
SPIN 代码: 4458-5608
MD, Dr. Sci. (Medicine)
俄罗斯联邦, MoscowDmitry A. Sychev
Medical Academy of Continuous Professional Education
Email: dimasychev@mail.ru
ORCID iD: 0000-0002-4496-3680
SPIN 代码: 4525-7556
MD, Dr. Sci. (Medicine), Professor, academician of the Russian Academy of Sciences
俄罗斯联邦, MoscowAlexander V. Bazhin
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: BazhinAV@zdrav.mos.ru
ORCID iD: 0000-0003-3198-1334
SPIN 代码: 6122-5786
MD, Cand. Sci. (Medicine)
俄罗斯联邦, MoscowIgor M. Shulkin
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: ShulkinIM@zdrav.mos.ru
ORCID iD: 0000-0002-7613-5273
SPIN 代码: 5266-0618
MD, Cand. Sci. (Medicine)
俄罗斯联邦, MoscowAnton V. Vladzymyrskyy
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
编辑信件的主要联系方式.
Email: vladzimirskijAV@zdrav.mos.ru
ORCID iD: 0000-0002-2990-7736
SPIN 代码: 3602-7120
MD, Dr. Sci. (Medicine)
俄罗斯联邦, MoscowAlexandra Yu. Golikova
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: GolikovaAY1@zdrav.mos.ru
ORCID iD: 0009-0001-5020-2765
俄罗斯联邦, Moscow
Kirill M. Arzamasov
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: ArzamasovKM@zdrav.mos.ru
ORCID iD: 0000-0001-7786-0349
SPIN 代码: 3160-8062
MD, Cand. Sci. (Medicine)
俄罗斯联邦, MoscowAndrei V. Mishchenko
Medical Academy of Continuous Professional Education
Email: dr.mishchenko@mail.ru
ORCID iD: 0000-0001-7921-3487
SPIN 代码: 8825-4704
MD, Dr. Sci. (Medicine)
俄罗斯联邦, MoscowGevorg A. Bekdzhanyan
Medical Academy of Continuous Professional Education
Email: rmapo@rmapo.ru
ORCID iD: 0009-0007-7150-7166
SPIN 代码: 4579-9457
俄罗斯联邦, Moscow
Arcadiy S. Goldberg
Medical Academy of Continuous Professional Education
Email: goldarcadiy@gmail.com
ORCID iD: 0000-0002-2787-4731
SPIN 代码: 8854-0469
MD, Cand. Sci. (Medicine)
俄罗斯联邦, MoscowLarisa G. Rodionova
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: RodionovaLG@zdrav.mos.ru
ORCID iD: 0009-0008-9862-8205
俄罗斯联邦, Moscow
参考
- Boenk EA, Roginko NI, Dzeranova NG, et al. All-Russian medical examination of adult population within the framework of the national project "Healthcare". Vestnik Roszdravnadzora. 2021;(1):21–29. EDN: FIPEZH
- Garifullin TYu, Avdeeva MV, Filatov VN, et al. Improvement of medical check-up process on the basis of lean technologies in outpatient settings. Russian Journal of Preventive Medicine and Public Health. 2023;26(3):30–38. doi: 10.17116/profmed20232603130 EDN: AGSZJF
- Zakharchenko OO, Shikina IB, Terentyeva DS. Results of the medical examination of the adult population over 60 years in the Russian Federation (2016–2021). Preventive And Clinical Medicine. 2023;3(88):103–114. doi: 10.47843/2074-9120_2023_3_103 EDN: YNHXOE
- Ignatyeva VI, Kontsevaya AV, Kalinina AM, et al. Socio-economic effectiveness of early cancer detection during medical checkup. Russian Journal of Preventive Medicine and Public Health. 2024;27(1):36–44. doi: 10.17116/profmed20242701136 EDN: CNVQRC
- Levshin VF, Slepchenko NI, Ryzhova NI, et al. Study of the attitude and participation of the population in the preventive and screening examinations and implementation of these examinations in the health care system. Lechaschi Vrach. 2022;25(10):81–87. doi: 10.51793/OS.2022.25.10.013 EDN: UFZZEB
- Stupina MI, Selezneva PA, Khaptanova VA. Medical screening of patients with coronary heart disease in outpatient settings. Nauchnyy Aspekt. 2024;34(4):4436–4455. (In Russ.) EDN: XOTAYU
- Golubev NA, Ogryzko EV, Tyurina EM, et 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;(2):356–376. doi: 10.24412/2312-2935-2021-2-356-376 EDN: EHSADW
- Ivashikin YM. (2024). Lung imaging screening during preventive medical examinations and medical screening. In: Higher education: scientific research. Proceedings of the Interuniversity International Congress. Moscow: Infinity Publishing House, 2024. P. 139–141. (In Russ.) doi: 10.34660/INF.2024.94.91.106 EDN: BXEOLF
- Trofimova TN, Kozlova OV. Radiology in Saint-Petersburg 2019. Diagnostic radiology and radiotherapy. 2021;4(11):96–99. doi: 10.22328/2079-5343-2020-11-4-96-99 EDN: HTVSUZ
- Tyurin IE. Radiology in the Russian Federation. Journal of Oncology: Diagnostic Radiology and Radiotherapy. 2018;1(4):43–51. EDN: QZSWYK
- Zubova NA. Effectiveness of mass preventive examinations in subjects of the Russian Federation with low morbidity rates of tuberculosis. Social Aspects of Population Health. 2016;4(50):8. doi: 10.21045/2071-5021-2016-50-4-8 EDN: WGIKUN
- Rubis LV. Efficiency of mass preventive examinations of the urban population for the purpose of early diagnosis of tuberculosis in primary health care institutions. Current Problems of Health Care and Medical Statistics. 2021;(3):1–13. doi: 10.24412/2312-2935-2021-3-1-13 EDN: VPLCTZ
- Shelekhov PV. Personnel situation in radiative diagnostics. Current Problems of Health Care and Medical Statistics. 2019;(1):265–275. doi: 10.24411/2312-2935-2019-10018 EDN: ZGZFPV
- Bobrovskaya TM, Vasilev YuA, Nikitin NYu, Arzamasov KM. Approaches to building radiology datasets. Medical Doctor and IT. 2023;(4):14–23. doi: 10.25881/18110193_2023_4_14 EDN: EQHEKE
- Vasiliev YuA, Vlazimirsky AV, Omelyanskaya OV, et al. Methodology for testing and monitoring artificial intelligence-based software for medical diagnostics. Digital Diagnostics. 2023;4(3):252–267. doi: 10.17816/DD321971 EDN: UEDORU
- Vasilev YuA, Arzamasov KM, Kolsanov AV, et al. Experience of application artificial intelligence software on 800 thousand fluorographic studies. Medical Doctor and IT. 2023;(4):54–65. doi: 10.25881/18110193_2023_4_54 EDN: MHCTUB
- Vasiliev YuA, Vladzimirsky AV, Arzamasov KM, et al. The first 10,000 mammography exams performed as part of the “Description and interpretation of mammography data using artificial intelligence” service. Manager Zdravookhranenia. 2023;(8):54–67. doi: 10.21045/1811-0185-2023-8-54-67 EDN: KZHPVW
- Vasilev YuA, Vladzimirsky AV, Arzamasov KM, et al. Computer vision in radiology: stage one of the Moscow experiment. 2nd ed. Moscow: Publishing solutions; 2023. (In Russ.)
- Arzamasov KM, Semenov SS, Kokina DY, et al. Criteria for the applicability of computer vision for preventive studies on the example of chest X-ray and fluorography. Meditsinskaya Fizika. 2022;4(96):56–63. doi: 10.52775/1810-200X-2022-96-4-56-63 EDN: MXKUVL
- Vasilev YuA, Tyrov IA, Vladzymyrskyy AV, 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. 2023;31(11):23–32. doi: 10.35627/2219-5238/2023-31-11-23-32 EDN: SYIQBX
- Vasilev YuA, Tyrov IA, Vladzymyrskyy AV, et al. Autonomous artificial intelligence for sorting the preventive imaging studies’ results. Russian Journal of Preventive Medicine. 2024;27(7):23–29. doi: 10.17116/profmed20242707123 EDN: ODGHNM
- Morozov SP, Vetsheva NN, Ledikhova NV, et al. Assessing the quality of radiologic studies. Moscow: Moscow Center for Diagnostics and Telemedicine; 2019. (In Russ.)
- Alekseeva TR, Amosov VI, Anikeeva OYu, et al. Chest radiology: national guidelines. Moscow: GEOTAR-Media; 2014. (In Russ.) EDN: VRXFKX
- Vasilev YuA, Vladzymyrskyy AV, Omelyanskaya OV, et al. Assessing the maturity of artificial intelligence technologies for healthcare. Moscow: Moscow Center for Diagnostics and Telemedicine; 2023. (In Russ.)
- Orlov EM, Sokolova ON. Efficiency category in public health services system. Fundamental’nye issledovaniya. 2010;(4):70–75. EDN: MSPQTJ
- Kucherenko VZ, Fleck VO, Putin ME, et al. Evaluation of the effectiveness of medical organizations. Vyalkov AI, editor. Moscow: GEOTAR-Med; 2004.
- Arzamasov KM, Vasilev YuA, Vladzymyrskyy AV, et al. The use of computer vision for the mammography preventive research. Russian Journal of Preventive Medicine and Public Health. 2023;26(6):117–123. doi: 10.17116/profmed202326061117 EDN: YBKHPS
- Arzamasov KM, Vasilev YuA, Vladzymyrskyy AV, et al. An international non-inferiority study for the benchmarking of AI for routine radiology cases: chest X-ray, fluorography and mammography. Healthcare. 2023;11(10):1684. doi: 10.3390/healthcare11121684 EDN: FWVMPQ
- Berlin L. Radiologic errors and malpractice: a burry distinction. American Journal of Roentgenology. 2007;189(3):517–522. doi: 10.2214/AJR.07.2209
- Brady AP. Error and discrepancy in radiology: inevitable or avoidable? Insights into Imaging. 2017;8(1):171–182. doi: 10.1007/s13244-016-0534-1 EDN: FSSDNE
- Bruno MA, Walker EA, Abujudeh HH. Understanding and confronting our mistakes: the epidemiology of error in radiology and strategies for error reduction. RadioGraphics. 2015;35(6):1668–1676. doi: 10.1148/rg.2015150023
- Cascade PN, Kazerooni EA, Gross BH, et al. Evaluation of competence in the interpretation of chest radiographs. Academic Radiology. 2001;8(4):315–321. doi: 10.1016/S1076-6332(03)80500-7
- Morozov S, Guseva E, Ledikhova N, et al. Telemedicine-based system for quality management and peer review in radiology. Insights into Imaging. 2018;9(3):337–341. doi: 10.1007/s13244-018-0629-y EDN: YCIRMT
- Quekel LGBA, Kessels AGH, Goei R, van Engelshoven JMA. Miss rate of lung cancer on the chest radiograph in clinical practice. Chest. 1999;115(3):720–724. doi: 10.1378/chest.115.3.720
- Satia I, Bashagha S, Bibi A, et al. Assessing the accuracy and certainty in interpreting chest X-rays in the medical division. Clinical Medicine. 2013;13(4):349–352. doi: 10.7861/clinmedicine.13-4-349
- Topff L, Steltenpool S, Ranschaert ER, et al. Artificial intelligence-assisted double reading of chest radiographs to detect clinically relevant missed findings: a two-centre evaluation. European Radiology. 2024;34(9):5876–5885. doi: 10.1007/s00330-024-10676-w EDN: RUJICB
- Vasilev YuA, Vladzymyrskyy AV, Omelyanskaya OV, et al. AI-based CXR first reading: current limitations to ensure practical value. Diagnostics. 2023;13(8):1430. doi: 10.3390/diagnostics13081430 EDN: MPQYUP
补充文件
