CoChat
Sign Up
Cited by 152Electronic Health Records SystemsMachine Learning in HealthcareArtificial Intelligence in Healthcare and Education

The digital scribe in clinical practice: a scoping review and research agenda

Open access
van Buchem, Marieke M., Boosman, Hileen, Bauer, Martijn P., Kant, Ilse M. J., Cammel, Simone A., Steyerberg, Ewout W.·2021·npj Digital Medicine
DOI 10.1038/s41746-021-00432-5PMC PMC7997964
Open this paper in CoChat — free accountOpen PDF

Abstract

The number of clinician burnouts is increasing and has been linked to a high administrative burden. Automatic speech recognition (ASR) and natural language processing (NLP) techniques may address this issue by creating the possibility of automating clinical documentation with a “digital scribe”. We reviewed the current status of the digital scribe in development towards clinical practice and present a scope for future research. We performed a literature search of four scientific databases (Medline, Web of Science, ACL, and Arxiv) and requested several companies that offer digital scribes to provide performance data. We included articles that described the use of models on clinical conversational data, either automatically or manually transcribed, to automate clinical documentation. Of 20 included articles, three described ASR models for clinical conversations. The other 17 articles presented models for entity extraction, classification, or summarization of clinical conversations. Two studies examined the system’s clinical validity and usability, while the other 18 studies only assessed their model’s technical validity on the specific NLP task. One company provided performance data. The most promising models use context-sensitive word embeddings in combination with attention-based neural networks. However, the studies on digital scribes only focus on technical validity, while companies offering digital scribes do not publish information on any of the research phases. Future research should focus on more extensive reporting, iteratively studying technical validity and clinical validity and usability, and investigating the clinical utility of digital scribes.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-021-00432-5

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Poor data organization, suboptimal information presentation, and complex interfaces often make it challenging for physicians to identify clinically salient information, while extensive documentation requirements demand continuous attention.

    “Poor data organization, suboptimal information presentation, and complex interfaces often make it challenging for physicians to identify clinically salient information, while extensive documentation requirements demand continuous attention8–10.”

    From When better data meets better design: How EHR data usability and system usability shape physicians' cognitive load (2026) · cites this paper as [10]

    The Introduction reports that administrative tasks take approximately half of a clinician’s workday, supporting the claim of a substantial documentation burden. It does not say that poor data organization, information presentation, or complex interfaces make clinically salient information difficult for physicians to identify, nor does it establish that documentation demands continuous attention. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 57 · Cited by 152

Research works printed but not linked: 37

  1. [2]National Academies of Sciences, Engineering, and Medicine. Taking Action Against Clinician Burnout: A Systems Approach to Professional Well-Being (The National Academies Press, 2019). 31940160
  2. [6]Rao SK The impact of administrative burden on academic physicians Acad. Med. 2017 92 237 243 10.1097/ACM.0000000000001461 28121687 · DOI · Paper page
  3. [7]Pelland KD Baier RR Gardner RL “It’s like texting at the dinner table”: a qualitative analysis of the impact of electronic health records on patient-physician interaction in hospitals J. Innov. Health Inform. 2017 24 216 223 10.14236/jhi.v24i2.894 28749316 · DOI
  4. [8]Robertson SL Robinson MD Reid A Electronic health record effects on work-life balance and burnout within the I3 population collaborative J. Grad. Med. Educ. 2017 9 479 484 10.4300/JGME-D-16-00123.1 28824762 PMC5559244 · DOI · Paper page
  5. [9]Gardner RL Physician stress and burnout: the impact of health information technology J. Am. Med. Inform. Assoc. 2019 26 106 114 10.1093/jamia/ocy145 30517663 PMC7647171 · DOI · Paper page
  6. [11]Mishra P Kiang JC Grant RW Association of medical scribes in primary care with physician workflow and patient experience JAMA Intern. Med. 2018 178 1467 10.1001/jamainternmed.2018.3956 30242380 PMC6248201 · DOI · Paper page
  7. [17]Lin SY Shanafelt TD Asch SM Reimagining clinical documentation with artificial intelligence Mayo Clin. Proc. 2018 93 563 565 10.1016/j.mayocp.2018.02.016 29631808 · DOI
  8. [19]Chiu C-C Speech recognition for medical conversations Proc. Interspeech 2018 2018 2972 2976 10.21437/Interspeech.2018-40 · DOI
  9. [20]Du, N., Wang, M., Tran, L., Li, G. & Shafran, I. Learning to infer entities, properties and their relations from clinical conversations. In Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 4979–4990 (Association for Computational Linguistics, 2019).
  10. [22]Jeblee, S., Khattak, F. K., Crampton, N., Mamdani, M. & Rudzicz, F. Extracting relevant information from physician-patient dialogues for automated clinical note taking. In Proc. of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI), 65–74 (Association for Computational Linguistics, 2019).
  11. [23]Kodish-Wachs, J., Agassi, E., Kenny, P. & Overhage, J. M. A systematic comparison of contemporary automatic speech recognition engines for conversational clinical speech. In Proc. of the Annual AMIA Symposium, 683–689 (American Medical Informatics Association, 2018). PMC6371385 30815110
  12. [25]Rajkomar A Automatically charting symptoms from patient-physician conversations using machine learning JAMA Intern. Med. 2019 179 836 10.1001/jamainternmed.2018.8558 30907920 PMC6547250 · DOI
  13. [26]Selvaraj, S. P. & Konam, S. Medication regimen extraction from medical conversations. In Proc. of International Workshop on Health Intelligence of the 34th AAAI Conference on Artificial Intelligence (Association for Computational Linguistics, 2020).
  14. [27]Shafran, I. et al. The medical scribe: corpus development and model performance analyses. In Proc. of the 12th Language Resources and Evaluation Conference (European Language Resources Association, 2020).
  15. [28]Joshi, A., Katariya, N., Amatriain, X. & Kannan, A. Dr. summarize: global summarization of medical dialogue by exploiting local structures. In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3755–3763 (Association for Computational Linguistics, 2020).
  16. [29]Liu, Z., Ng, A., Lee, S., Aw, A. T. & Chen, N. F. Topic-aware pointer-generator networks for summarizing spoken conversations. In Proc. IEEE Automatic Speech Recognition Understanding Workshop 2019, 814–821 (IEEE, 2019).
  17. [30]Krishna, K., Pavel, A., Schloss, B., Bigham, J. P. & Lipton, Z. C. Extracting Structured Data from Physician-Patient Conversations by Predicting Noteworthy Utterances. in Shaban-Nejad A., Michalowski M., Buckeridge D.L. (eds) Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, vol 914 (Springer International Publishing, 2021).
  18. [31]Krishna, K., Khosla, S., Bigham, J. P. & Lipton, Z. C. Generating SOAP notes from doctor-patient conversations. Preprint at arXiv (2020).
  19. [32]Khosla, S., Vashishth, S., Lehman, J. F. & Rose, C. MedFilter: improving extraction of task-relevant utterances through integration of discourse structure and ontological knowledge. In Proc. of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 7781–7797 (Association for Computational Linguistics, 2020).
  20. [33]Schloss, B. & Konam, S. Towards an automated SOAP note: classifying utterances from medical conversations. Preprint at arXiv (2020).
  21. [34]Ferracane, E. & Konam, S. Towards fairness in classifying medical conversations into SOAP sections. In To be presented at AAAI 2021 Workshop: Trustworthy AI for Healthcare (AAAI Press, 2020).
  22. [35]Patel, D., Konam, S. & Selvaraj, S. P. Weakly supervised medication regimen extraction from medical conversations. In Proc. of the 3rd Clinical Natural Language Processing Workshop, 178–193 (Association for Computational Linguistics, 2020).
  23. [36]Mani, A., Palaskar, S. & Konam, S. Towards understanding ASR error correction for medical conversations. In Proc. of the First Workshop on Natural Language Processing for Medical Conversations, 7–11 (Association for Computational Linguistics, 2020).
  24. [37]Enarvi, S. et al. Generating medical reports from patient-doctor conversations using sequence-to-sequence models. In Proc. of the First Workshop on Natural Language Processing for Medical Conversations, 22–30 (Association for Computational Linguistics, 2020).
  25. [38]Du, N. et al. Extracting symptoms and their status from clinical conversations. In Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, 915–925 (Association for Computational Linguistics, 2019).
  26. [46]Peddinti, V. et al. Jhu aspire system: robust LVCSR with TDNNs, Ivector adaptation and RNN-LMs. In IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 539–546 (IEEE, 2015).
  27. [47]Hu, K., Sainath, T. N., Pang, R. & Prabhavalkar, R. Deliberation model based two-pass end-to-end speech recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7799–7803 (IEEE 2020).
  28. [48]Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. Preprint at arXiv (2014).
  29. [49]Cho, K. et al. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proc. of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724–1734 (Association for Computational Linguistics, 2014).
  30. [50]Hernandez-Boussard T Bozkurt S Ioannidis JPA Shah NH MINIMAR (MINimum Information for Medical AI Reporting): developing reporting standards for artificial intelligence in health care J. Am. Med. Inform. Assoc. 2020 27 2011 2015 10.1093/jamia/ocaa088 32594179 PMC7727333 · DOI · Paper page
  31. [52]Wiens J Do no harm: a roadmap for responsible machine learning for health care Nat. Med. 2019 25 1337 1340 10.1038/s41591-019-0548-6 31427808 · DOI · Paper page
  32. [53]Kocaballi AB Envisioning an artificial intelligence documentation assistant for future primary care consultations: a co-design study with general practitioners J. Am. Med. Inform. Assoc. 2020 27 1695 1704 10.1093/jamia/ocaa131 32845984 PMC7671614 · DOI · Paper page
  33. [54]Quiroz JC Identifying relevant information in medical conversations to summarize a clinician-patient encounter Health Inform. J. 2020 26 2906 2914 10.1177/1460458220951719 32865113 · DOI
  34. [57]Vasey, B. et al. DECIDE-AI: new reporting guidelines to bridge the development-to-implementation gap in clinical artificial intelligence. Nat. Med.27, 186–187 (2021). 33526932
  35. [58]Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. InProc. of the 27th International Conference on Neural Information Processing Systems (NIPS)2, 3104–3112 (MIT Press, 2014).
  36. [59]See, A., Liu, P. J. & Manning, C. D. Get to the point: summarization with pointer-generator networks. In Proc. of the 55th Annual Meeting of the Association for Computational Linguistics, 1, 1073–1083 (Association for Computational Linguistics, 2017).
  37. [60]Mikolov, T., Sutskever, I., Chen, K., Corrado, G. & Dean, J. Distributed representations of words and phrases and their compositionality. InProc. of the 26th International Conference on Neural Information Processing Systems (NIPS)2, 3111–3119 (Curran Associates Inc., 2013).

Authors
van Buchem, M. M., Boosman, H., Bauer, M. P., Kant, I. M. J., Cammel, S. A., & Steyerberg, E. W.
Affiliations
Leiden University Medical Center (NL)
ORCID
Venue
npj Digital Medicine
Publisher
Springer Science and Business Media LLC
Published
2021-03-26
Volume
4
Issue
1
Pages
57-57
ISSN
2398-6352 (ISSN-L)
DOI
10.1038/s41746-021-00432-5
PMC
PMC7997964
OpenAlex
W3139390182
Cited by
152
References
57
Citations by year
2026: 38 · 2025: 46 · 2024: 30 · 2023: 25 · 2022: 10 · 2021: 3
FWCI
3.02
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Leiden Repository (Leiden University) (submittedVersion, cc-by)
  • Data Archiving and Networked Services (DANS) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
clinical documentation automation, speech recognition, natural language processing, clinical conversation, named entity recognition, clinical summarization, clinical validity, usability, clinician burnout, administrative burden, attention-based neural networks, word embeddings

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