语音识别技术在放射诊断中的应用

封面图片

如何引用文章

全文:

详细

能够进行语音识别的设备是保健系统的一个有前途的工具。语音识别技术在西方医疗系统中有相当长的使用历史（自20世纪70年代以来），但它在21世纪初才得到了广泛推广，取代了医疗抄写员。对于国内的医疗保健来说，该技术是相对较新的。它的积极开发是在2010年代初才开始，并2010年代末才在保健事业广泛采用的。这种延迟是由于俄语的特点和21世纪初计算能力的限制而导致的。

语音识别的设备和软件包现在被用于通过语言输入填写病历，此外，与传统（用键盘）文本输入相比，减少了准备X射线学协议所需的时间。

本文献综述简要介绍了语音识别技术在放射诊断中的发展和应用的历史。介绍了证实其在西方医疗系统中使用的有效性的主要科学研究。展示了国内使用语音识别技术的经验，并对其有效性进行了评估。描述了该技术在俄罗斯保健事业进一步发展的前景。

作者简介

Nikita D. Kudryavtsev

Moscow Center for Diagnostics and Telemedicine

Email: KudryavtsevND@zdrav.mos.ru
ORCID iD: 0000-0003-4203-0630
SPIN 代码: 1125-8637
俄罗斯联邦, Moscow

Kristina A. Bardasova

Ural State Medical University

Email: bardasovakris@mail.ru
ORCID iD: 0009-0002-4310-1357
SPIN 代码: 1156-7627
俄罗斯联邦, Ekaterinburg

Anna N. Khoruzhaya

Moscow Center for Diagnostics and Telemedicine

编辑信件的主要联系方式.
Email: KhoruzhayaAN@zdrav.mos.ru
ORCID iD: 0000-0003-4857-5404
SPIN 代码: 7948-6427
俄罗斯联邦, Moscow

参考

  1. Vechorko VI. Distribution of working time at an outpatient appointment of a district therapist with a nurse in a polyclinic in Moscow (photochronometric observation). Social Aspects Public Health. 2016;(6):4. (In Russ).
  2. Kaplieva OV, Marega LA, Vorobyeva LP. Timekeeping of working hours of doctors of the children’s consultative and diagnostic department. Far Eastern Med J. 2018;(4):72–76. (In Russ).
  3. Ryabchikov IV, Zagafarov RR, Mukhina VV, et al. Distribution of the traumatologist-orthopaedician’s working time with outpatients. Моscоw Sur J. 2018;(6):38–43. (In Russ). doi: 10.17238/issn2072-3180.2018.6.38-43
  4. Kudryavtsev ND, Sergunova KA, Ivanova GV, et al. Evaluation of the effectiveness of the implementation of speech recognition technology for the preparation of radiological protocols. VIT. 2020;6(S1):58–64. (In Russ). doi: 10.37690/1811-0193-2020-S1-58-64
  5. Blackley SV, Huynh J, Wang L, et al. Speech recognition for clinical documentation from 1990 to 2018: A systematic review. J Am Med Inf Association. 2019;26(4):324–338. doi: 10.1093/jamia/ocy179
  6. Motyer RE, Liddy S, Torreggiani WC, Buckley O. Frequency and analysis of non-clinical errors made in radiology reports using the National Integrated Medical Imaging System voice recognition dictation software. Ir J Med Sci. 2016;185(4):921–927. doi: 10.1007/s11845-016-1507-6
  7. Hodgson T, Coiera E. Risks and benefits of speech recognition for clinical documentation: A systematic review. J Am Med Inf Association. 2016;23(e1):e169–e179. doi: 10.1093/jamia/ocv152
  8. Itakura F. Minimum prediction residual principle applied to speech recognition. IEEE Trans Acoust Speech Signal Process. 1975;23(1):67–72. doi: 10.1109/TASSP.1975.1162641
  9. Leeming W, Porter D, Jackson JD, et al. Computerized radiologic reporting with voice data-entry. Radiology. 1981;138(3):585–588. doi: 10.1148/radiology.138.3.7465833
  10. Simon M, Leeming BW, Bleich HL, et al. Computerized radiology reporting using coded language. Radiology. 1974;113(2):343–349. doi: 10.1148/113.2.343
  11. Vogel M, Kaisers W, Wassmuth R, Mayatepek E. Analysis of documentation speed using web-based medical speech recognition technology: Randomized controlled trial. J Med Internet Res. 2015;17(11):e247. doi: 10.2196/jmir.5072
  12. Ramaswamy MR, Chaljub G, Esch O, et al. Continuous speech recognition in MR imaging reporting. Am J Roentgenol. 2000;174(3):617–622. doi: 10.2214/ajr.174.3.1740617
  13. Poder TG, Fisette JF, Déry V. Speech recognition for medical dictation: Overview in quebec and systematic review. J Med Systems. 2018;42(5):89. doi: 10.1007/s10916-018-0947-0
  14. Sankaranarayanan B, David G, Vishwanath KR, et al. Would technology obliterate medical transcription? In: Proceedings of the 2017 ACM SIGMIS Conference on Computers and People Research. New York, NY, USA: ACM; 2017. P. 97–104. doi: 10.1145/3084381.3084414
  15. Houston JD, Rupp FW. Experience with implementation of a radiology speech recognition system. J Digital Imaging. 2000;13(3):124–128. doi: 10.1007/BF03168385
  16. Saxena K, Diamond R, Conant RF, et al. Provider adoption of speech recognition and its impact on satisfaction, documentation quality, efficiency, and cost in an inpatient EHR. AMIA Jt Summits Transl Sci Proc. 2018;2017:186–195.
  17. Schwartz LH, Kijewski P, Hertogen H, et al. Voice recognition in radiology reporting. Am J Roentgenol. 1997;169(1):27–29. doi: 10.2214/ajr.169.1.9207496
  18. Vogel M, Kaisers W, Wassmuth R, Mayatepek E. Analysis of documentation speed using web-based medical speech recognition technology: Randomized controlled trial. J Med Int Research. 2015;17(11):e247. doi: 10.2196/jmir.5072
  19. Hammana I, Lepanto L, Poder T, et al. Speech recognition in the radiology department: A systematic review. Health Inf Manag. 2015;44(2):4–10. doi: 10.1177/183335831504400201
  20. Mohr DN, Turner DW, Pond GR, et al. speech recognition as a transcription aid: A randomized comparison with standard transcription. J Am Med Inf Association. 2003;10(1):85–93. doi: 10.1197/jamia.m1130
  21. Singh M, Pal TR. Voice recognition technology implementation in surgical pathology: Advantages and limitations. Arch Pathol Laboratory Med. 2011;135(11):1476–1481. doi: 10.5858/arpa.2010-0714-OA
  22. Goss FR, Blackley SV, Ortega CA, et al. A clinician survey of using speech recognition for clinical documentation in the electronic health record. Int J Med Inf. 2019;(130):103938. doi: 10.1016/j.ijmedinf.2019.07.017
  23. Blackley SV, Schubert VD, Goss FR, et al. Physician use of speech recognition versus typing in clinical documentation: A controlled observational study. Int J Med Inform. 2020;(141):104178. doi: 10.1016/j.ijmedinf.2020.104178
  24. Yang L, Ene IC, Belaghi RA, et al. Stakeholders’ perspectives on the future of artificial intelligence in radiology: A scoping review. Eur Radiol. 2022;32(3):1477–1495. doi: 10.1007/s00330-021-08214-z
  25. European Society of Radiology (ESR). Impact of artificial intelligence on radiology: A EuroAIM survey among members of the European Society of Radiology. Insights Imaging. 2019;10(1):105. doi: 10.1186/s13244-019-0798-3
  26. Szymański P, Żelasko P, Morzyet M, et al. WER we are and WER we think we are. arXiv. arXiv:2010.03432.2020. doi: 10.48550/arXiv.2010.03432
  27. Li J. Recent advances in end-to-end automatic speech recognition. arXiv. arXiv:2111.01690.2022. doi: 10.48550/arXiv.2111.01690
  28. Juang BH, Rabiner LR. Hidden markov models for speech recognition. Technometrics. 1991;33(3):251–272.
  29. Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, BC, Canada: IEEE; 2013. P. 6645–6649. doi: 10.48550/arXiv.1303.5778
  30. Deng L, Li X. Machine learning paradigms for speech recognition: An overview. IEEE Trans Audio Speech Lang Process. 2013;21(5):1060–1089.
  31. Kazachkin AE. Speech recognition methods, modern speech technologies. Young Scientist. 2019;(39):6–8. (In Russ).
  32. Kamath U, Liu J, Whitaker J. Deep learning for NLP and speech recognition. Cham: Springer International Publishing; 2019. 621 р.
  33. Wang D, Wang X, Lv S. An overview of end-to-end automatic speech recognition. Symmetry. 2019;11(8):1018. doi: 10.3390/sym11081018
  34. Zhozhikashvili VA, Farkhadov MP, Petukhova NV, Zhozhikashvili AV. The first voice recognition applications in Russian language for use in The Interactive Information Systems. In: Speech and Computer. Saint-Petersburg, SPECOM; 2004. Р. 304–307. (In Russ).
  35. Karpov AA, Ronzhin AA, Li IV. SIRIUS system of dictoron-independent recognition of the merged Russian speech. Izvestia Southern Federal University. Technical Sci. 2005;54(10):44–54. (In Russ).
  36. Irzaev MG. The use of voice input of information in medical institutions to fill in electronic charts and patient medical histories. New technologies and techniques in medicine, biology and ecology: Collection of scientific papers. 2013;(3):149–154. (In Russ).
  37. Vazhenina D, Markov K, Karpov A, et al. State-of-the-art speech recognition technologies for Russian language. In: Proceedings of the 2012 Joint International Conference on Human-Centered Computer Environments. Aizu-Wakamatsu Japan: ACM; 2012. P. 59–63. doi: 10.1145/2160749.2160763
  38. Kamvar M, Chelba C. Optimal size, freshness and time-frame for voice search vocabulary. arXiv. arXiv:1210.8436.2012.
  39. Kipyatkova IS, Karpov AA. An analytical survey of large vocabulary Russian speech recognition systems. SPIIRAS Proceedings. 2014;1(12):7. (In Russ). doi: 10.15622/sp.12.1
  40. Kudryavtsev ND, Semenov DS, Kozhikhina DD, Vladzymyrskyy AV. Speech recognition technology: Results of a survey of radiologists at the Moscow reference center for diagnostic radiology. Healthcare Management. 2022;8(3):95–104. (In Russ). doi: 10.33029/2411-8621-2022-8-3-95-104
  41. Sinitsyn VE, Komarova MA, Mershina EA. Protocol of radiological description: Past, present, future. Bulletin Radiology Radiology. 2014;(3):35–40. (In Russ).
  42. Sobez LM, Kim SH, Angstwurm M, et al. Creating high-quality radiology reports in foreign languages through multilingual structured reporting. Eur Radiol. 2019;29(11):6038–6048. doi: 10.1007/s00330-019-06206-8
  43. Ganeshan D, Duong PA, Probyn L, et al. Structured reporting in radiology. Academic Radiology. 2018;25(1):66–73. doi: 10.1016/j.acra.2017.08.005
  44. Dos Santos PD, Hempel JM, Mildenberger P, et al. Structured reporting in clinical routine. Rofo. 2019. Vol. 191, N 01. P. 33–39. doi: 10.1055/a-0636-3851
  45. Andrianova MG, Kudryavtsev ND, Petryaykin AV. Development of a thesaurus of radiological terms for voice filling of diagnostic research protocols. Digital Diagnostics. 2022;3(S1):21–22. (In Russ). doi: 10.17816/DD105703

补充文件

附件文件
动作
1. JATS XML
下载
2. Fig. 1. A simplified scheme of the operation of a classical speech recognition system. An algorithm for recognizing the “signs of osteochondrosis” phrase is presented.

下载 (154KB)
索引源数据
3. Fig. 2. Workplace of a radiologist at the Moscow Reference Center for Radiation Diagnostics, equipped with a speech recognition system. The process of filling medical records.

下载 (129KB)
索引源数据
4. 图1。经典语音识别系统的简化操作方案。图1给出识别短语“骨软骨病的症状”的算法 。 注：ям——来自俄语的языковая модель（语言模型）。

下载 (107KB)
索引源数据
5. 图2。配有语音识别系统的莫斯科放射诊断参考中心放射科医生的工作场所。填写医疗文件的过程。

下载 (129KB)
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。

##common.cookie##