Medizinische Spracherkennung im stationären und ambulanten Einsatz – Eine systematische Übersicht

Zusammenfassung

Einleitung Die medizinische Dokumentation dient neben der Sicherung einer ordnungsgemäßen Behandlung auch der umfänglichen Aufklärung des Patienten. Gleichsam nimmt sie einen großen Anteil der Arbeitszeit von Gesundheitsprofessionen in Anspruch. Häufig ist die zeitnahe Fertigstellung der Dokumentation durch den zunehmenden Zeitdruck im klinischen Alltag zusätzlich erschwert. Um den Zeitaufwand für die medizinische Dokumentation zu reduzieren, werden auch im ärztlichen Dienst immer häufiger Spracherkennungstechnologien in Einsatz gebracht. Dennoch sind die Auswirkungen dieser medizinischen Spracherkennung auf Bearbeitungszeit und Qualität der Dokumentation zum aktuellen Zeitpunkt noch wenig erforscht. Die bestehende Literatur erfasst bis dato nicht in ausreichendem Maße alle Möglichkeiten des aktuellen technologischen Standes. Ziel dieser Übersichtsarbeit ist daher, den aktuellen Forschungsstand zu den Auswirkungen und Folgen des Einsatzes von digitaler Spracherkennung auf Arbeitsprozesse der Gesundheitsprofessionen zu analysieren. Dazu wurden alle seit dem Jahr 2000 veröffentlichten Studien der jeweiligen medizinischen Fachbereiche berücksichtigt.

Methode Die Autoren führten eine Literaturrecherche unter Verwendung der Datenbanken Medline via PubMed und Google Scholar durch. Die Datenbanken wurden nach den folgenden Stichwörtern durchsucht: „speech recognition“, „voice recognition“, „medical“ und „healthcare“. Unter der Annahme, dass sich erst die ab dem Jahr 2000 entwickelten Spracherkennungstechnologien bezüglich ihrer Genauigkeit für den medizinischen Bereich eignen, wurden Studien erst ab diesem Zeitpunkt in der vorliegenden Übersichtsarbeit berücksichtigt.

Ergebnisse Insgesamt lieferten die 29 für diese Analyse herangezogenen Studien sehr differente Ergebnisse. Im Vergleich zu alternativen Diktatserviceleistungen, konnte sich die Spracherkennungstechnologie als zeit- und kosteneffizienter erweisen. Im Vergleich zur Texteingabe zeigte sich die Spracherkennung in den betrachteten Studien jedoch nicht überlegen, was mehrheitlich an der geringeren beobachteten Genauigkeit der Spracherkennung lag.

Schlussfolgerung Der Einsatz von digitaler Spracherkennung im klinischen Betrieb bietet einige Vorteile bezüglich der reinen Dokumentationszeit. Die vorhandenen qualitativen Probleme in der genauen semantischen Umsetzung führen jedoch in den vorliegenden Studien noch nicht zu einer eindeutigen Evidenz der Vorteilhaftigkeit dieser Technologie. Aus diesem Grund besteht darüber hinaus Bedarf an weiteren Untersuchungen auf diesem Forschungsfeld.

Abstract

Introduction The medical documentation serves to ensure proper treatment and comprehensive information for the patient. At the same time, medical documentation takes up a large proportion of the working time of health professionals, and the increasing time pressure in everyday clinical life makes it more difficult to complete documentation promptly. With the aim of reducing the time required for medical documentation, speech recognition technologies are increasingly being used in the medical field. Nevertheless, the effect of medical speech recognition on the processing time and the quality of medical documentation appears to have been little researched to date and the existing literature does not capture the features of the current state of technology. The aim of this review is to analyse the current state of research on the effects of the use of digital speech recognition on the medical work processes, taking into account all since the year 2000 published studies of the medical disciplines.

Methods The literature search was carried out using the databases Medline via PubMed and Google Scholar. The databases were searched for keywords “speech recognition”, “voice recognition”, “medical” and “healthcare”. Under the assumption that the speech recognition technologies developed from the year 2000 onwards would be suitable for the medical-clinical field in terms of their accuracy, only the studies from 2000 or older were taken into account in this review.

Results In total, the 29 studies used for this analysis yielded very different results. Compared to the alternative “dictation service”, speech recognition technology proved to be more time and cost efficient. However, speech recognition was not superior to text input, mainly due to the lower observed accuracy of speech recognition.

Conclusion The use of speech recognition in clinical applications shows some advantages in terms of documentation time. However, the results of these studies do not yet provide clear evidence of the benefits of this technology. For this reason, there is still a need for further extensive investigations in this field of research.

Schlüsselwörter

Spracherkennung - medizinische Dokumentation - Digitalisierung - Spracheingabe - Systematische Übersichtsarbeit

Key words

Speech recognition - Medical documentation - Digitalization - Voice typing - Systematic review

Publication History

Article published online:
26 February 2020

• Literatur

• 1 Clynch N, Kellett J. Medical documentation: Part of the solution, or part of the problem?. A narrative review of the literature on the time spent on and value of medical documentation. Int J Med Inform 2015; 84: 221-228 https://doi.org/10.1016/j.ijmedinf.2014.12.001
• 2 King J, Patel V, Jamoom EW. et al. Clinical Benefits of Electronic Health Record Use: National Findings. Health Serv Res 2014; 49: 392-404 https://doi.org/10.1111/1475-6773.12135
• 3 Poissant L, Pereira J, Tamblyn R. et al. The impact of electronic health records on time efficiency of physicians and nurses: a systematic review. J Am Med Inform Assoc 2005; 12: 505-16 https://doi.org/10.1197/jamia.M1700
• 4 Johnson M, Lapkin S, Long V. et al. A systematic review of speech recognition technology in health care. BMC Med Inform Decis Mak 2014; 14: 94 https://doi.org/10.1186/1472-6947-14-94
• 5 Hodgson T, Coiera E. Risks and benefits of speech recognition for clinical documentation: a systematic review. J Am Med Informatics Assoc 2016; 23: e169-e179 https://doi.org/10.1093/jamia/ocv152
• 6 Moher D, Liberati A, Tetzlaff J. et al. Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Med 2009; 6: e1000097 https://doi.org/10.1371/journal.pmed.1000097
• 7 Koivikko MP, Kauppinen T, Ahovuo J. Improvement of Report Workflow and Productivity Using Speech Recognition—A Follow-up Study. J Digit Imaging 2008; 21: 378-382 https://doi.org/10.1007/s10278-008-9121-4
• 8 Zick RG, Olsen J. Voice recognition software versus a traditional transcription service for physician charting in the ED. Am J Emerg Med 2001; 19: 295-298 https://doi.org/10.1053/AJEM.2001.24487
• 9 Callaway EC, Sweet CF, Siegel E. et al. Speech recognition interface to a hospital information system using a self-designed visual basic program: initial experience. J Digit Imaging 2002; 15: 43-53 https://doi.org/10.1007/bf03191902
• 10 Chapman WW, Aronsky D, Fiszman M. et al. Contribution of a speech recognition system to a computerized pneumonia guideline in the emergency department. Proc/AMIA Ann Symp AMIA Symp 2000; 131-135
• 11 Prevedello LM, Ledbetter S, Farkas C. et al. Implementation of Speech Recognition in a Community-based Radiology Practice: Effect on Report Turnaround Times. J Am Coll Radiol 2014; 11: 402-406 https://doi.org/10.1016/J.JACR.2013.07.008
• 12 Hart JL, McBride A, Blunt D. et al. Immediate and sustained benefits of a & quot;total & quot; implementation of speech recognition reporting. Br J Radiol 2010; 83: 424-7 https://doi.org/10.1259/bjr/58137761
• 13 Krishnaraj A, Lee JKT, Laws SA. et al. Voice Recognition Software: Effect on Radiology Report Turnaround Time at an Academic Medical Center. Am J Roentgenol 2010; 195: 194-197 https://doi.org/10.2214/AJR.09.3169
• 14 Trumm CG, Morhard D, Ertl-Wagner B. et al. Impact of RIS/PACS integrated speech recognition on report availability. Radiol Manage 2008; 30: 16-23 quiz 24–6
• 15 Vorbeck F, Ba-Ssalamah A, Kettenbach J. et al. Report generation using digital speech recognition in radiology. Eur Radiol 200 (10) 1976-1982 https://doi.org/10.1007/s003300000459
• 16 Rosenthal DI, Chew FS, Dupuy DE. et al. Computer-based speech recognition as a replacement for medical transcription. Am J Roentgenol 1998; 170: 23-25 https://doi.org/10.2214/ajr.170.1.9423591
• 17 Henricks WH, Roumina K, Skilton BE. et al. The Utility and Cost Effectiveness of Voice Recognition Technology in Surgical Pathology. Mod Pathol 2002; 15: 565-571 https://doi.org/10.1038/modpathol.3880564
• 18 Parente R, Kock N, Sonsini J. An analysis of the implementation and impact of speech-recognition technology in the healthcare sector. Perspect Heal Inf Manag 2004; 1: 5
• 19 Issenman RM, Jaffer IH. Use of voice recognition software in an outpatient pediatric specialty practice. Pediatrics 2004; 114: e290-3 https://doi.org/10.1542/peds.2003-0724-L
• 20 Vogel M, Kaisers W, Wassmuth R. et al. Analysis of Documentation Speed Using Web-Based Medical Speech Recognition Technology: Randomized Controlled Trial. J Med Internet Res 2015; 17: e247 https://doi.org/10.2196/jmir.5072
• 21 Mohr DN, Turner DW, Pond GR. et al. Speech recognition as a transcription aid: a randomized comparison with standard transcription. J Am Med Inform Assoc 2003; 10: 85-93 https://doi.org/10.1197/jamia.m1130
• 22 Derman YD, Arenovich T, Strauss J. Speech recognition software and electronic psychiatric progress notes: physicians’ ratings and preferences. BMC Med Inform Decis Mak 2010; 10: 44 https://doi.org/10.1186/1472-6947-10-44
• 23 Strahan RH, Schneider-Kolsky ME. Voice recognition versus transcriptionist: Error rates and productivity in MRI reporting. J Med Imaging Radiat Oncol 2010; 54: 411-414 https://doi.org/10.1111/j.1754-9485.2010.02193.x
• 24 Goss FR, Zhou L, Weiner SG. Incidence of speech recognition errors in the emergency department. Int J Med Inform 2016; 93: 70-73 https://doi.org/10.1016/j.ijmedinf.2016.05.005
• 25 Zhou L, Blackley SV, Kowalski L. et al. Analysis of Errors in Dictated Clinical Documents Assisted by Speech Recognition Software and Professional Transcriptionists. JAMA Netw open 2018; 1 DOI: 10.1001/jamanetworkopen.2018.0530.
• 26 Hodgson T, Magrabi F, Coiera E. Efficiency and safety of speech recognition for documentation in the electronic health record. J Am Med Informatics Assoc 2017; 24: 1127-1133 https://doi.org/10.1093/jamia/ocx073
• 27 McGurk S, Brauer K, Macfarlane TV. et al. The effect of voice recognition software on comparative error rates in radiology reports. Br J Radiol 2008; 81: 767-770 https://doi.org/10.1259/bjr/20698753
• 28 Basma S, Lord B, Jacks LM. et al. Error Rates in Breast Imaging Reports: Comparison of Automatic Speech Recognition and Dictation Transcription. Am J Roentgenol 2011; 197: 923-927 https://doi.org/10.2214/AJR.11.6691
• 29 Ilgner J, Düwel P, Westhofen M. Free-text data entry by speech recognition software and its impact on clinical routine. Ear Nose Throat J 2006; 85: 523-7
• 30 Motyer RE, Liddy S, Torreggiani WC. et al. Frequency and analysis of non-clinical errors made in radiology reports using the National Integrated Medical Imaging System voice recognition dictation software. Irish J Med Sci (1971 -) 2016; 185: 921-927 https://doi.org/10.1007/s11845-016-1507-6
• 31 Singh M, Pal TR. Voice Recognition Technology Implementation in Surgical Pathology: Advantages and Limitations. Arch Pathol Lab Med 2011; 135: 1476-1481 https://doi.org/10.5858/arpa.2010-0714-OA
• 32 Lyons JP, Sanders SA, Fredrick Cesene D. et al. Speech recognition acceptance by physicians: A temporal replication of a survey of expectations and experiences. Health Informatics J 2016; 22: 768-778 https://doi.org/10.1177/1460458215589600
• 33 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 proceedings AMIA Jt Summits Transl Sci 2018; 2017: 186-195
• 34 Alapetite A, Boje Andersen H, Hertzum M. Acceptance of speech recognition by physicians: A survey of expectations, experiences, and social influence. Int J Hum Comput Stud 2009; 67: 36-49 https://doi.org/10.1016/J.IJHCS.2008.08.004
• 35 Hodgson T, Magrabi F, Coiera E. Evaluating the usability of speech recognition to create clinical documentation using a commercial electronic health record. Int J Med Inform 2018; 113: 38-42 https://doi.org/10.1016/j.ijmedinf.2018.02.011
• 36 Dugdale DC, Epstein R, Pantilat SZ. Time and the patient-physician relationship. J Gen Intern Med 1999; 14 Suppl 1 S34-40 https://doi.org/10.1046/j.1525-1497.1999.00263.x