旨在从胸部电子计算机断层扫描中识别十种病理检查所见的综合人工智能算法使用的诊断和经济评估

封面图片

如何引用文章

全文:

详细

论证。人工智能技术打算帮助解决射线检验中遗漏发现的问题。一个重要的问题是对采用人工智能技术的经济效益进行的评估。

该研究的目的是评估在私人医疗中心环境下，与不应用技术的放射科医生相比，使用全面的、经过专家验证的人工智能进行胸部电子计算机断层扫描的检测频率和经济潜力。

材料和方法。进行了一项观察性、单中心的回顾性研究。本研究包括2022年6月1日至2022年7月31日在“Clinical Hospital on Yauza”（莫斯科）进行的没有静脉注射对比剂的胸部器官电子计算机断层扫描图像。电子计算机断层扫描图像由人工智能的综合算法处理，用于10种病症：病毒性肺炎（大流行条件下的COVID-19）的肺部浸润性病变；肺结节；胸膜腔内的游离液体；肺气肿；胸主动脉增宽；肺动脉干增宽；冠状动脉钙化；肾上腺厚度的评估；椎体高度和密度的评估。两位专家分析了电子计算机断层扫描图像，并对结果与人工智能分析进行了比较。对于诊所医生检测到和未检测到的所有发现，根据临床指南确定了进一步路由。对于每个病人，根据诊所的价格表，计算出未提供的医疗服务费用。

结果。最后一组由160个带有描述的胸部器官电子计算机断层扫描图像组成。人工智能识别出90个（56%）有病变的研究，其中81个（51%）协议至少有一个遗漏的病变。81名患者的所有病变的未提供的“第二阶段”医疗服务的总成本估计为2,847,760卢布（37,250.99美元或256,217.95人民币）。只有那些被医生遗漏但被人工智能检测出来的病变的未提供医疗服务费用为2,065,360卢布（27,016.57美元或185,824.05人民币）。

结论。来为分析胸部电子计算机断层扫描数据而使用的作为放射科医生助手的人工智能允许大大减少遗漏病变的情况。与不应用这种技术放射科医生工作的标准模式相比，使用人工智能可以为每项医疗服务带来3.6倍的成本，因此，在私人医疗中心环境下的应用具有成本效益。

作者简介

Valeria Yu. Chernina

IRA Labs

Email: v.chernina@ira-labs.com
ORCID iD: 0000-0002-0302-293X
SPIN 代码: 8896-8051
Scopus 作者 ID: 57210638679
Researcher ID: AAF-1215-2020
俄罗斯联邦, Moscow

Mikhail G. Belyaev

IRA Labs

Email: belyaevmichel@gmail.com
ORCID iD: 0000-0001-9906-6453
SPIN 代码: 2406-1772

Cand. Sci. (Phys.-Math.), Professor

俄罗斯联邦, Moscow

Anton Yu. Silin

Clinical Hospital on Yauza

Email: silin@yamed.ru
ORCID iD: 0000-0003-4952-2347
SPIN 代码: 4411-8745
俄罗斯联邦, Moscow

Ivan O. Avetisov

Clinical Hospital on Yauza

Email: avetisov@yamed.ru
ORCID iD: 0009-0007-3550-7556
俄罗斯联邦, Moscow

Ilya A. Pyatnitskiy

IRA Labs; The University of Texas at Austin

Email: i.pyatnitskiy@ira-labs.com
ORCID iD: 0000-0002-2827-1473
SPIN 代码: 6150-4961
俄罗斯联邦, Moscow; Austin, Texas, USA

Ekaterina A. Petrash

IRA Labs; N.N. Blokhin National Medical Research Center of Oncology

Email: e.a.petrash@gmail.com
ORCID iD: 0000-0001-6572-5369
SPIN 代码: 6910-8890

MD, Cand. Sci. (Med.)

俄罗斯联邦, Moscow; Moscow

Maria V. Basova

IRA Labs

Email: m.basova@ira-labs.com
ORCID iD: 0009-0000-3325-8452
俄罗斯联邦, Moscow

Valentin E. Sinitsyn

Lomonosov Moscow State University; Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: vsini@mail.ru
ORCID iD: 0000-0002-5649-2193
SPIN 代码: 8449-6590

MD, Dr. Sci. (Med.), Professor

俄罗斯联邦, Moscow; Moscow

Vitaly V. Omelyanovskiy

The Center for Healthcare Quality Assessment and Control; Russian Medical Academy of Continuous Professional Education; Scientific and research financial institute

Email: vvo@rosmedex.ru
ORCID iD: 0000-0003-1581-0703
SPIN 代码: 1776-4270

MD, Dr. Sci. (Med.), Professor

俄罗斯联邦, Moscow; Moscow; Moscow

Victor A. Gombolevskiy

IRA Labs; Artificial Intelligence Research Institute

编辑信件的主要联系方式.
Email: gombolevskii@gmail.com
ORCID iD: 0000-0003-1816-1315
SPIN 代码: 6810-3279

MD, Cand. Sci. (Med.)

俄罗斯联邦, Moscow; Moscow

参考

  1. Aberle DR, Adams AM, Berg CD, et al.; National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med. 2011;365(5):395–409. doi: 10.1056/NEJMoa1102873
  2. Pastorino U, Silva M, Sestini S, et al. Prolonged lung cancer screening reduced 10-year mortality in the MILD trial: new confirmation of lung cancer screening efficacy. Ann Oncol. 2019;30(7):1162–1169. doi: 10.1093/annonc/mdz117
  3. Grover H, King W, Bhattarai N, et al. Systematic review of the cost-effectiveness of screening for lung cancer with low dose computed tomography. Lung Cancer. 2022;170:20–33. doi: 10.1016/j.lungcan.2022.05.005
  4. Nikolaev AE, Gombolevskiy VA, Gonchar AP, et al. Incidental findings during lung cancer screening by low-dose computed tomography. Tuberculosis Lung Dis. 2018;96(11):60–67. (In Russ). doi: 10.21292/2075-1230-2018-96-11-60-67
  5. Kilsdonk ID, de Roos MP, Bresser P, et al. Frequency and spectrum of incidental findings when using chest CT as a primary triage tool for COVID-19. Eur J Radiol Open. 2021;(8):100366. doi: 10.1016/j.ejro.2021.100366
  6. Beltsevich DG, Melnichenko GA, Kuznetsov NS, et al. Russian Association of Endocrinologists clinical practice guideline for adrenal incidentalomas differential diagnosis. Endocrine Sur. 2016;10(4):31–42. (In Russ). doi: 10.14341/serg2016431-42
  7. Emphysema of the lungs. Clinical recommendations (approved by the Ministry of Health of the Russian Federation, 2021). (In Russ). Available from: https://www.garant.ru/products/ipo/prime/doc/402775957/. Accessed: 25.08.2021.
  8. Thoracic and thoracoabdominal aortic aneurysms. Clinical recommendations (approved by the Ministry of Health of the Russian Federation, 2023). (In Russ). Available from: https://www.angiolsurgery.org/library/recommendations/2022/aneurysms_thoracic_thoracoabdominal_aorta/recommendation.pdf. Accessed: 25.08.2021.
  9. Vasiliev YuA, Vladzimirsky AV, Arzamasov KM, et al. Computer vision in radiation diagnostics: the first stage of the Moscow experiment. Monograph. 2nd ed., revised and updated. Ed. by Yu.A. Vasiliev, A.V. Vladzimirsky. Moscow: Izdatel’skie resheniya; 2023. 376 p. (In Russ).
  10. Zakharov A, Pisov M, Bukharaev A, et al. Interpretable vertebral fracture quantification via anchor-free landmarks localization. Med Image Anal. 2023;(83):102646. doi: 10.1016/j.media.2022.102646
  11. Goncharov M, Pisov M, Shevtsov A, et al. CT-Based COVID-19 triage: Deep multitask learning improves joint identification and severity quantification. Med Image Anal. 2021;(71):102054. doi: 10.1016/j.media.2021.102054
  12. Shirokikh B, Shevtsov A, Dalechina A, et al. Accelerating 3D medical image segmentation by adaptive small-scale target localization. J Imaging. 2021;7(2):35. doi: 10.3390/jimaging7020035
  13. Goncharov M, Pisov M, Belyaev M, et al. Quantification of epicardial adipose tissue in low-dose computed tomography images. Lecture Notes Electrical Engineering. 2022;784(1):98–107. doi: 10.1007/978-981-16-3880-0_11
  14. Husereau D, Drummond M, Augustovski F, et al.; CHEERS 2022 ISPOR Good Research Practices Task Force. Consolidated health economic evaluation reporting standards 2022 (cheers 2022) statement: Updated reporting guidance for health economic evaluations. Value Health. 2022;25(1):3–9. doi: 10.1016/j.jval.2021.11.1351
  15. Morozov SP, Vladzimirsky AV, Kljashtorny VG, et al. Clinical trials of software based on intelligent technologies (radiology diagnostics). Preprint № CDT-2019-1. Best Practice in Radiation Oncology and Instrumental Diagnostics. Vol. 23. Moscow: Center for Diagnostics and Telemedicine; 2019. 33 р. (In Russ).
  16. Gombolevskiy VA, Blokhin IA, Laipan AS, et al. Methodological guidelines for lung cancer screening. Best Practice in Radiation and Instrumental Diagnostics. Vol. 56. Moscow: Center for Diagnostics and Telemedicine; 2020. 57 р. (In Russ).
  17. Morozov SP, Protsenko DN, Smetanina SV, et al. Radiation diagnosis of coronavirus disease (COVID-19): Organization, methodology, interpretation of results: Guidelines. Best Practices in Radiation and Instrumental Diagnostics Series. Vol. 65. Moscow: Center for Diagnostics and Telemedicine; 2020. 78 р. (In Russ).
  18. Temporary methodological recommendations. Prevention, diagnosis and treatment of new coronavirus infection (COVID-19). Ministry of Health of the Russian Federation. Version 17 (12/14/2022). (In Russ). Available from: https://static-0.minzdrav.gov.ru/system/attachments/attaches/000/061/254/original/%D0%92%D0%9C%D0%A0_COVID-19_V17.pdf?1671088207. Accessed: 17.03.2023.
  19. Lynch DA, Austin JH, Hogg JC, et al. CT-definable subtypes of chronic obstructive pulmonary disease: A statement of the Fleischner Society. Radiology. 2015;277(1):192–205. doi: 10.1148/radiol.2015141579
  20. Hersh CP, Washko GR, Estépar RS, et al. Paired inspiratory-expiratory chest CT scans to assess for small airways disease in COPD. Respir Res. 2013;146(1):42. doi: 10.1186/1465-9921-14-42
  21. Walker C, Chung JH. Muller’s imaging of the chest e-book: Expert radiology series. Elsevier Health Sciences; 2018.1104 р.
  22. Erbel R, Aboyans V, Boileau C et al. ESC Committee for Practice Guidelines. 2014 ESC Guidelines on the diagnosis and treatment of aortic diseases: Document covering acute and chronic aortic diseases of the thoracic and abdominal aorta of the adult. The task force for the diagnosis and treatment of aortic diseases of the European society of cardiology (ESC). Eur Heart J. 2014;35(41):2873–2926. doi: 10.1093/eurheartj/ehu281
  23. Wanhainen A, Verzini F, Van Herzeele I, et al. Clinical practice guidelines on the management of abdominal aorto-iliac artery aneurysms. Eur J Vascul Endovascul Sur. 2019;57(1):8–93. doi: 10.1016/j.ejvs.2018.09.020
  24. Jurgens PT, Carr JJ, Terry JG, et al. Association of abdominal aorta calcium and coronary artery calcium with incident cardiovascular and coronary heart disease events in black and white middle-aged people: The coronary artery risk development in young adults study. J Am Heart Assoc. 2021;10(24):23–37. doi: 10.1161/JAHA.121.023037
  25. Galiè N, Humbert M, Vachiery JL, et al. 2015 ESC/ERS Guidelines for the diagnosis and treatment of pulmonary hypertension: The joint task force for the diagnosis and treatment of pulmonary hypertension of the European society of cardiology (ESC) and the European respiratory society (ERS): Endorsed by: Association for European paediatric and congenital cardiology (AEPC), international society for heart and lung transplantation (ISHLT). Eur Respir J. 2015;46(4):903–975. doi: 10.1183/13993003.01032-2015
  26. Agatston AS, Janowitz WR, Hildner FJ et al. Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol. 1990;15(4):827–832. doi: 10.1016/0735-1097(90)90282-t
  27. Zhuravlev KN. Coronary CT angiography. Best practices in radiation and instrumental diagnostics series. Vol. 65. Moscow: Center for Diagnostics and Telemedicine; 2020. 35 р. (In Russ).
  28. Mayo-Smith WW, Song JH, Boland GL, et al. Management of incidental adrenal masses: A white paper of the ACR incidental findings committee. J Am Coll Radiol. 2017;14(8):1038–1044. doi: 10.1016/j.jacr.2017.05.001
  29. Belaya ZE, Belova KYu, Biryukova EV, et al. Federal clinical guidelines for diagnosis, treatment and prevention of osteoporosis. Osteoporosis Bone Diseases. 2021;24(2):4–47. (In Russ). doi: 10.14341/osteo12930
  30. Genant HK, Jergas M. Assessment of prevalent and incident vertebral fractures in osteoporosis research. Osteoporosis Int. 2003;14(3):43–55. doi: 10.1007/S00198-002-1348-1
  31. Pathological fractures complicating osteoporosis. Clinical recommendations. Moscow; 2018. 90 p. (In Russ). Available from: https://neirodoc.ru/wp-content/uploads/2019/10/patologicheskie-perelomy-oslozhnyayuschie-osteoporoz-2018.pdf. Accessed: 17.03.2023.
  32. Kolbin AS, Gomon YuM, Balykina YuE, et al. Socioeconomic and global burden of COVID-19. Good Clin Pract. 2021;(1):24–34. (In Russ). doi: 10.37489/2588-0519-2021-1-24-34
  33. Pickhardt PJ, Correale L, Hassan C. AI-based opportunistic CT screening of incidental cardiovascular disease, osteoporosis, and sarcopenia: Cost-effectiveness analysis. Abdom Radiol (NY). 2023;(3):1181–1198. doi: 10.1007/s00261-023-03800-9
  34. Behr CM, Koffijberg H, Degeling K, et al. Can we increase efficiency of CT lung cancer screening by combining with CVD and COPD screening? Results of an early economic evaluation. Eur Radiol. 2022;32(5):3067–3075. doi: 10.1007/s00330-021-08422-7
  35. Chintanapakdee W, Mendoza DP, Zhang EW, et al. Detection of extrapulmonary malignancy during lung cancer screening: 5-year analysis at a tertiary hospital. J Am Coll Radiol. 2020;17(12):1609–1620. doi: 10.1016/j.jacr.2020.09.032
  36. Girling A, Lilford R, Cole A, et al. Headroom approach to device development: Current and future directions. Int J Technol Assess Health Care. 2015;31(5):331–338. doi: 10.1017/S0266462315000501
  37. Ijzerman MJ, Steuten LM. Early assessment of medical technologies to inform product development and market access: A review of methods and applications. Appl Health Econ Health Policy. 2011;9(5):331–347. doi: 10.2165/11593380-000000000-00000
  38. Izerman MJ, Koffijberg H, Fenwick E, et al. Emerging use of early health technology assessment in medical product development: A scoping review of the literature. Pharmacoeconomics. 2017;35(7):727–740. doi: 10.1007/s40273-017-0509-1
  39. Sahiner B, Pezeshk A, Hadjiiski LM, et al. Deep learning in medical imaging and radiation therapy. Med Phys. 2019;46(1):1–36. doi: 10.1002/mp.13264
  40. Allen BJ, Seltzer SE, Langlotz CP, et al. A road map for translational research on artificial intelligence in medical imaging: From the 2018 national institutes of health/RSNA/ACR/The academy workshop. J Am Coll Radiol. 2019;16(9):1179–1189. doi: 10.1016/j.jacr.2019.04.014
  41. Xia C, Rook M, Pelgrim GJ, et al. Early imaging biomarkers of lung cancer, COPD and coronary artery disease in the general population: rationale and design of the ImaLife (Imaging in Lifelines) Study. Eur J Epidemiol. 2020;35(1):75–86. doi: 10.1007/s10654-019-00519-0
  42. Ziegelmayer S, Graf M, Makowski M, et al. Cost-Effectiveness of artificial intelligence support in computed tomography-based lung cancer screening. Cancers (Basel). 2022;14(7):1729. doi: 10.3390/cancers14071729
  43. McDonald RJ, Schwartz KM, Eckel LJ, et al. The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. Acad Radiol. 2015;22(9):1191–1198. doi: 10.1016/j.acra.2015.05.007
  44. Sokolovskaya E, Shinde T, Ruchman RB, et al. The effect of faster reporting speed for imaging studies on the number of misses and interpretation errors: A pilot study. J Am Coll Radiol. 2015;12(7):683–688. doi: 10.1016/j.jacr.2015.03.040
  45. 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
  46. Lauritzen PM, Hurlen P, Sandbæk G, et al. Double reading rates and quality assurance practices in Norwegian hospital radiology departments: Two parallel national surveys. Acta Radiol. 2015;56(1):78–86. doi: 10.1177/0284185113519988
  47. Morozov SP, Chernina VYu, Andreychenko AE, et al. How does artificial intelligence effect on the assessment of lung damage in COVID-19 on chest CT scan? Digital Diagnostics. 2020;2(1):27−38. (In Russ). doi: 10.17816/DD60040

补充文件

附件文件
动作
1. JATS XML
下载
2. Fig. 1. Study design.

下载 (395KB)
索引源数据
3. Fig. 2. Study result by the number of findings detected with and without AI.

下载 (161KB)
索引源数据
4. Fig. 3. Number of findings (ranked by the number of significant missed pathological findings).

下载 (210KB)
索引源数据
5. Fig. 4. Analysis of the cost of medical services not provided because of missed pathological findings, and all CT scans performed.

下载 (319KB)
索引源数据
6. Fig. 5. Range of costs of medical services not provided due to the use of the combined AI service for chest CT scans in a clinic. AI, artificial intelligence; CT, computed tomography; CNMS, cost of non-provided medical services.

下载 (286KB)
索引源数据
7. Fig. 6. An example of AI use. Patient B, 76 years old. A radiologist correctly identified bilateral hydrothorax and emphysematous changes but did not describe the lung nodule in the right lung. An AI algorithm revealed all three pathological findings: hydrothorax is highlighted with a yellow line, emphysematous changes are highlighted in orange, and the lung nodule is indicated by a red square.

下载 (196KB)
索引源数据
8. Fig. 7. An example of AI use. Patient B., 79 years old. Chest CT scans: a) axial section: a radiologist and an algorithm correctly identified a lung nodule in the left lung (indicated by a red square) and coronary calcification (outlined by an orange line). In addition, the algorithm indicated an increase in the volume of epicardial fat (filled in yellow; this pathological finding was not considered in the study); b) sagittal section: a radiologist and an algorithm correctly identified compression fractures of Th6 and Th9 vertebral bodies, Genant 3 (three columns are marked with red lines); however, the radiologist did not indicate deformities of Th5 and Th12 vertebral bodies, Genant 2 (three columns are marked with yellow lines) in the protocol.

下载 (263KB)
索引源数据
9. Fig. 8. Potential cost of medical services not provided because a combined AI service was not used for chest CT scans in a clinic, considering the cost of using AI.

下载 (242KB)
索引源数据
10. 图1。研究设计。

下载 (357KB)
索引源数据
11. 图2。在使用/不使用人工智能的情况下所见的发现数量的研究结果。

下载 (162KB)
索引源数据
12. 图3。发现数量的研究结果（按重大遗漏数量排列）。

下载 (197KB)
索引源数据
13. 图4。在进行电子计算机断层扫描（CT）的范围内，由于遗漏病变而导致的未提供医疗服务的费用分析。

下载 (305KB)
索引源数据
14. 图5。医疗机构使用复合人工智能进行胸部CT检查的未提供医疗服务的费用谱。CT——电子计算机断层扫描。

下载 (316KB)
索引源数据
15. 图6。人工智能算法工作原理的实例。患者B，76岁。医生正确地发现了双侧胸水和气肿性改变，但没有描述右肺的肺结节。人工智能算法确定了所有3种病变：胸水用黄线勾勒，气肿性改变用橙色标出，肺结节用红色方块标记。

下载 (164KB)
索引源数据
16. 图7。人工智能算法工作原理的实例。患者V，79岁。胸部计算机断层扫描：a——轴向切片：医生和算法正确地发现了左肺的肺结节（用红色方块标记）和冠状动脉钙化（用橙线勾勒）；此外，算法显示了心外膜脂肪体积增加（用黄色填充，该病变在研究中没有考虑）；b——矢状切片：医生和算法正确地发现了Th6和Th9椎体的压缩性骨折，Genant 3（3列用红线标记），但医生没有在协议书中指出Th5和Th12椎体的畸形，Genant 2（3列用黄线标记）。

下载 (236KB)
索引源数据
17. 图8。考虑到使用人工智能的成本，医疗机构由于没有使用复合人工智能进行胸部CT检查而导致的未提供医疗服务的费用可行性。

下载 (236KB)
索引源数据

版权所有 © Eco-Vector, 2023

Creative Commons License
此作品已接受知识共享署名-非商业性使用-禁止演绎 4.0国际许可协议的许可。

Согласие на обработку персональных данных с помощью сервиса «Яндекс.Метрика»

1. Я (далее – «Пользователь» или «Субъект персональных данных»), осуществляя использование сайта https://journals.rcsi.science/ (далее – «Сайт»), подтверждая свою полную дееспособность даю согласие на обработку персональных данных с использованием средств автоматизации Оператору - федеральному государственному бюджетному учреждению «Российский центр научной информации» (РЦНИ), далее – «Оператор», расположенному по адресу: 119991, г. Москва, Ленинский просп., д.32А, со следующими условиями.

2. Категории обрабатываемых данных: файлы «cookies» (куки-файлы). Файлы «cookie» – это небольшой текстовый файл, который веб-сервер может хранить в браузере Пользователя. Данные файлы веб-сервер загружает на устройство Пользователя при посещении им Сайта. При каждом следующем посещении Пользователем Сайта «cookie» файлы отправляются на Сайт Оператора. Данные файлы позволяют Сайту распознавать устройство Пользователя. Содержимое такого файла может как относиться, так и не относиться к персональным данным, в зависимости от того, содержит ли такой файл персональные данные или содержит обезличенные технические данные.

3. Цель обработки персональных данных: анализ пользовательской активности с помощью сервиса «Яндекс.Метрика».

4. Категории субъектов персональных данных: все Пользователи Сайта, которые дали согласие на обработку файлов «cookie».

5. Способы обработки: сбор, запись, систематизация, накопление, хранение, уточнение (обновление, изменение), извлечение, использование, передача (доступ, предоставление), блокирование, удаление, уничтожение персональных данных.

6. Срок обработки и хранения: до получения от Субъекта персональных данных требования о прекращении обработки/отзыва согласия.

7. Способ отзыва: заявление об отзыве в письменном виде путём его направления на адрес электронной почты Оператора: info@rcsi.science или путем письменного обращения по юридическому адресу: 119991, г. Москва, Ленинский просп., д.32А

8. Субъект персональных данных вправе запретить своему оборудованию прием этих данных или ограничить прием этих данных. При отказе от получения таких данных или при ограничении приема данных некоторые функции Сайта могут работать некорректно. Субъект персональных данных обязуется сам настроить свое оборудование таким способом, чтобы оно обеспечивало адекватный его желаниям режим работы и уровень защиты данных файлов «cookie», Оператор не предоставляет технологических и правовых консультаций на темы подобного характера.

9. Порядок уничтожения персональных данных при достижении цели их обработки или при наступлении иных законных оснований определяется Оператором в соответствии с законодательством Российской Федерации.

10. Я согласен/согласна квалифицировать в качестве своей простой электронной подписи под настоящим Согласием и под Политикой обработки персональных данных выполнение мною следующего действия на сайте: https://journals.rcsi.science/ нажатие мною на интерфейсе с текстом: «Сайт использует сервис «Яндекс.Метрика» (который использует файлы «cookie») на элемент с текстом «Принять и продолжить».