Risks and benefits of speech recognition for clinical documentation: a systematic review
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Objective To review literature assessing the impact of speech recognition (SR) on clinical documentation. Methods Studies published prior to December 2014 reporting clinical documentation using SR were identified by searching Scopus, Compendex and Inspect, PubMed, and Google Scholar. Outcome variables analyzed included dictation and editing time, document turnaround time (TAT), SR accuracy, error rates per document, and economic benefit. Twenty-three articles met inclusion criteria from a pool of 441. Results Most studies compared SR to dictation and transcription (DT) in radiology, and heterogeneity across studies was high. Document editing time increased using SR compared to DT in four of six studies (+1876.47% to –16.50%). Dictation time similarly increased in three of five studies (+91.60% to –25.00%). TAT consistently improved using SR compared to DT (16.41% to 82.34%); across all studies the improvement was 0.90% per year. SR accuracy was reported in ten studies (88.90% to 96.00%) and appears to improve 0.03% per year as the technology matured. Mean number of errors per report increased using SR (0.05 to 6.66) compared to DT (0.02 to 0.40). Economic benefits were poorly reported. Conclusions SR is steadily maturing and offers some advantages for clinical documentation. However, evidence supporting the use of SR is weak, and further investigation is required to assess the impact of SR on documentation error types, rates, and clinical outcomes.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Weighted kappa: nominal scale agreement provision for scaled disagreement or partial credit
Cohen, J. (1968) · Psychological Bulletin · doi:10.1037/h0026256 · Cited by 8,736 · cited 1×
“Inter-rater agreement was calculated using Cohen’s j.(13) The observed agreement was statistically significant at 95.”
MethodA systematic review of speech recognition technology in health care
Johnson, M., Lapkin, S., Long, V., Sanchez, P., Suominen, H., Basilakis, J., & Dawson, L. (2014) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-14-94 · Cited by 141 · cited 1×
“INTRODUCTION Speech recognition (SR) systems for medical reporting have been available commercially for over two decades.(1) SR is an input mechanism available to assist with clinical documentation by translating speech into text, or verbally controlling user interface functions.”
Method
Research works printed but not linked: 37
- Herman, 2004, Speech recognition and the creation of radiology reports, Appl Radiol., 33, 23, 10.37549/AR1246 · doi:10.37549/ar1246
- Neustein, 2013, Mobile Speech and Advanced Natural Language Solutions, 10.1007/978-1-4614-6018-3 · DOI
- Bliss, 2005, Speech Recognition for the Health Professions: (using Dragon NaturallySpeaking)
- Madisetti, 2009, Video, Speech, and Audio Signal Processing and Associated Standards, 10.1201/9781420046090 · doi:10.1201/9781420046090
- Paulett, 2009, Improving language models for radiology speech recognition, J Biomed Inform., 42, 53, 10.1016/j.jbi.2008.08.001 · DOI
- Gales, 2008, The application of hidden Markov models in speech recognition, Found Trends Signal Process., 1, 195, 10.1561/2000000004 · DOI · Paper page
- Eddy, 2004, What is a hidden Markov model?, Nat Biotech, 22, 1315, 10.1038/nbt1004-1315 · DOI · Paper page
- Indurkhya, 2012, Handbook of Natural Language Processing
- Lafferty, 2001, Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- Moher, 2009, Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement, Ann Int Med., 151, 264, 10.7326/0003-4819-151-4-200908180-00135 · DOI · Paper page
- Hundt, 1999, Speech processing in radiology, Eur Radiol., 9, 1451, 10.1007/s003300050869 · doi:10.1007/s003300050869
- Pezzullo, 2008, Voice recognition dictation: Radiologist as transcriptionist, J Digital Imag., 21, 384, 10.1007/s10278-007-9039-2 · DOI
- Mohr, 2003, Speech recognition as a transcription aid: a randomized comparison with standard transcription, JAMIA., 10, 85
- Vorbeck, 2000, Report generation using digital speech recognition in radiology, Eur Radiol., 10, 1976, 10.1007/s003300000459 · DOI
- Al-Aynati, 2003, Comparison of voice-automated transcription and human transcription in generating pathology reports, Arch Pathol Lab Med., 127, 721, 10.5858/2003-127-721-COVTAH · DOI · Paper page
- Bhan, 2008, Effect of voice recognition on radiologist reporting time, Can Assoc Radiol J., 59, 203
- Rosenthal, 1998, Computers in radiology: computer-based speech recognition as a replacement for medical transcription, Am J Roentgenol., 170, 23, 10.2214/ajr.170.1.9423591 · DOI
- Chapman, 2000, Contribution of a speech recognition system to a computerized pneumonia guideline in the emergency department, Proc/AMIA Ann Symp AMIA Symp, 131
- Ramaswamy, 2000, Continuous speech recognition in MR imaging reporting: advantages, disadvantages, and impact, Am J Roentgenol., 174, 617, 10.2214/ajr.174.3.1740617 · DOI · Paper page
- Ilgner, 2006, Free-text data entry by speech recognition software and its impact on clinical routine, Ear, Nose Throat J., 85, 523, 10.1177/014556130608500816 · DOI
- Koivikko, 2008, Improvement of report workflow and productivity using speech recognition—a follow-up study, J Digit Imaging., 21, 378, 10.1007/s10278-008-9121-4 · DOI
- Krishnaraj, 2010, Voice recognition software: effect on radiology report turnaround time at an academic medical center, Am J Roentgenol., 195, 194, 10.2214/AJR.09.3169 · DOI
- Kanal, 2001, Initial evaluation of a continuous speech recognition program for radiology, J Digit Imaging., 14, 30, 10.1007/s10278-001-0022-z · DOI
- Smith, 1990, Recognition accuracy with a voice-recognition system designed for anesthesia record keeping, J Clin Monitor., 6, 299, 10.1007/BF02842489 · DOI
- Zemmel, 1996, Status of voicetype dictation for windows for the emergency physician, J Emerg Med., 14, 511, 10.1016/0736-4679(96)00092-3 · DOI
- McGurk, 2008, The effect of voice recognition software on comparative error rates in radiology reports, Brit J Radiol., 81, 767, 10.1259/bjr/20698753 · DOI · Paper page
- Basma, 2011, Error rates in breast imaging reports: comparison of automatic speech recognition and dictation transcription, Am J Roentgenol., 197, 923, 10.2214/AJR.11.6691 · DOI · Paper page
- David, 2014, Error rates in physician dictation: quality assurance and medical record production, Int J Health Care Qual Assur., 27, 99, 10.1108/IJHCQA-06-2012-0056 · DOI
- Quint, 2008, Frequency and spectrum of errors in final radiology reports generated with automatic speech recognition technology, J Am Coll Radiol., 5, 1196, 10.1016/j.jacr.2008.07.005 · DOI
- Chang, 2011, Non-clinical errors using voice recognition dictation software for radiology reports: a retrospective audit, J Digit Imaging., 24, 724, 10.1007/s10278-010-9344-z · DOI
- Belton, 1991, Voice-recognition technology: key to the computer-based patient record, J Am Med Record Assoc., 62, 27
- Clark, 1994, Implementation of voice recognition technology at provenant health partners, J Am Health Inform Manag Assoc., 65, 34, 36, 38
- Nuance Communications, 2014, Dragon NaturallySpeaking 13 Premium Data Sheet - Nuance Communications
- Coiera, 2015, Guide to Health Informatics, 10.1201/b13617 · DOI · Paper page
- Coiera, 2015, Technology, cognition and error, BMJ Qual Saf, 24, 417, 10.1136/bmjqs-2014-003484 · DOI · Paper page
- Coiera, 2012, The dangerous decade, JAMIA., 19, 2
- Chleborad, 2013, Evaluation of voice-based data entry to an electronic health record system for dentistry, Biocybernetics Biomed Eng., 33, 204, 10.1016/j.bbe.2013.09.003 · DOI
Cited by
Introducing artificial intelligence training in medical education
Paranjape, K., Schinkel, M., Nannan Panday, R., Car, J., & Nanayakkara, P. (2019) · JMIR Medical Education · doi:10.2196/16048 · Cited by 634
Coiera, E., Kocaballi, B., Halamka, J., & Laranjo, L. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0066-9 · Cited by 132
Self-citationThe unintended consequences of health information technology revisited
Ash, J., Berg, M., & Coiera, E. (2016) · Yearbook of Medical Informatics · doi:10.15265/iy-2016-014 · Cited by 101
“…have described unintended consequences in different settings such as residential aged care homes [10], and with different HIT beyond EHRs such as bar code medication administration [11, 12], health information exchange [13], hands free communication devices [14], and speech recognition [15].”
Self-citationSpeech recognition for clinical documentation from 1990 to 2018: a systematic review
Blackley, S. V., Huynh, J., Wang, L., Korach, Z., & Zhou, L. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy179 · Cited by 97
Zhou, L., Blackley, S. V., Kowalski, L., Doan, R., Acker, W. W., Landman, A. B., Kontrient, E., Mack, D., Meteer, M., Bates, D. W., et al. (2018) · JAMA Network Open · doi:10.1001/jamanetworkopen.2018.0530 · Cited by 94
Metadata
- Authors
- Hodgson, T., & Coiera, E.
- Venue
- Journal of the American Medical Informatics Association
- Publisher
- Oxford University Press (OUP)
- Published
- 2015-11-17
- Volume
- 23
- Issue
- e1
- Pages
- e169-e179
- ISSN
- 1067-5027 (ISSN-L)
- 1527-974X
- OpenAlex
- W2198918681
- Cited by
- 102
- References
- 2
- FWCI
- 2.05
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.