Preprint · 2026 · Open access

Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes

Byron De John, Nico Enslin, Joshua Fieggen, Linda Camara, Bruce A. Bassett, Graham Fieggen

Research Square · Published 15 April 2026 · DOI 10.21203/rs.3.rs-9139641/v1

Free PDFView at the publisherCite this paper

In brief

“Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes” is a 2026 preprint by Byron De John and 5 co-authors, published in Research Square. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.

Citations
0
References
1
Authors
6

Abstract

In a prospective real-world evaluation at Groote Schuur Hospital, South Africa, a large-language-model ambient scribe was compared with contemporaneous handwritten clinical notes. The system generated notes from raw audio without diarisation, transcript editing, or clinician review. Across 49 encounters, documentation quality was independently assessed using a SOAP-aligned rubric (0–5 per domain) and a symmetric severity-graded error taxonomy. AI-generated notes outperformed handwritten notes in 48 encounters and tied in one, with higher mean overall SOAP scores (4.9 vs 2.9) and a 97.1% posterior probability (95% credible interval, 91.0%–99.8%) of superior documentation quality. Posterior rates of moderate-to-severe hallucinations, distortions, omissions, and clinically significant errors were at least fivefold higher in handwritten notes. Hallucinations were not confined to AI outputs, challenging their framing as an AI-specific risk. In LMIC settings, ambient AI scribes could complement existing documentation workflows and may form part of a broader pathway toward scalable digital health infrastructure.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

De John, B., Enslin, N., Fieggen, J., Camara, L., Bassett, B. A., & Fieggen, G. (2026). Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes. Research Square. https://doi.org/10.21203/rs.3.rs-9139641/v1

MLA 9

De John, Byron, et al. “Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-9139641/v1.

Chicago

De John, Byron, Nico Enslin, Joshua Fieggen, Linda Camara, Bruce A. Bassett, and Graham Fieggen. 2026. “Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes.” Research Square. https://doi.org/10.21203/rs.3.rs-9139641/v1.

Harvard

De John, B. et al. (2026) ‘Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes’, Research Square. doi:10.21203/rs.3.rs-9139641/v1.

IEEE

B. De John, N. Enslin, J. Fieggen, L. Camara, B. A. Bassett, and G. Fieggen, “Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes,” Research Square, 2026, doi: 10.21203/rs.3.rs-9139641/v1.

BibTeX

@misc{dejohn2026accuracy,
  title     = {{Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes}},
  author    = {De John, Byron and Enslin, Nico and Fieggen, Joshua and Camara, Linda and Bassett, Bruce A. and Fieggen, Graham},
  howpublished = {Research Square},
  year      = {2026},
  doi       = {10.21203/rs.3.rs-9139641/v1},
  url       = {https://doi.org/10.21203/rs.3.rs-9139641/v1}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • large language models
  • clinical documentation quality
  • SOAP notes
  • hallucinations
  • medical errors
  • low- and middle-income countries
  • digital health infrastructure

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

De John, B., Enslin, N., Fieggen, J., Camara, L., Bassett, B. A., & Fieggen, G. (2026). Accuracy and Safety of an AI Ambient Scribe Compared with Handwritten Clinical Notes. Research Square. https://doi.org/10.21203/rs.3.rs-9139641/v1

How many times has this paper been cited?

0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Research Square.

Who wrote this paper?

Byron De John, Nico Enslin, Joshua Fieggen, Linda Camara, Bruce A. Bassett, Graham Fieggen.

What is the DOI of this paper?

10.21203/rs.3.rs-9139641/v1. The permanent link is https://doi.org/10.21203/rs.3.rs-9139641/v1.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.