Journal article · 2026 · Open access

Evaluating privacy leakages in LLM-driven ambient clinical documentation

Jenny Chim, Jonathan Pearson, Dan Schofield, Maria Liakata

Frontiers in Digital Health, 8, 1761624 · Published 31 March 2026 · DOI 10.3389/fdgth.2026.1761624

Open PDFView at the publisherCite this paper

In brief

“Evaluating privacy leakages in LLM-driven ambient clinical documentation” is a 2026 journal article by Jenny Chim and 3 co-authors, published in Frontiers in Digital Health. OpenAlex counts 6 citations as of 19 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Frontiers in Digital Health.

Citations
6
Most cited in
2026 (6)
Field-weighted impact
6.01
References
31
Authors
4

Abstract

Introduction: Automated documentation tools are being rapidly adopted in healthcare and clinical workflows. Among these are AI-enabled ambient scribing products, which transcribe conversations between patients and healthcare providers, then produce clinical records using automatic speech recognition (ASR) and generative AI such as Large Language Models (LLMs). While research suggests these technologies can reduce clinical burden, safe and responsible deployment requires that these tools determine what captured information is appropriate to record and under which circumstances. This presents a contextual privacy challenge distinct from PII leakage or data memorization and remains largely untested. Methods: We address this gap by operationalizing privacy leakage as the inappropriate inclusion of third-party personal information in LLM-generated clinical notes. We construct a benchmark of transcripts containing private information with gold standard clinical notes by enriching patient metadata from the aci-bench corpus and injecting third-party personal information across six relationship types and seven information topics. We evaluate open weight LLaMA 3.1 8 and 70 B, Mixtral 8×7B and 8×22B, and proprietary Claude 3.5 Haiku and Sonnet models on note generation using prompts with varied privacy and structural requirements. Results: All examined models leaked third-party information, and privacy instructions helped reduce leakage but proved neither complete nor robust as a solution. Models could generate privacy-infringing notes despite correctly identifying such information as inappropriate to share. Decomposing generation and privacy editing into separate steps could further reduce leakage, but only when privacy was defined with contextual specificity. Discussion: No single mitigation eliminated leakage entirely, but combining approaches yielded the greatest reductions. Results emphasize the need to build privacy-by-design systems and develop evaluation strategies that reflect emerging information synthesis and sharing practices.

Cite this paper

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

APA 7

Chim, J., Pearson, J., Schofield, D., & Liakata, M. (2026). Evaluating privacy leakages in LLM-driven ambient clinical documentation. Frontiers in Digital Health, 8, 1761624. https://doi.org/10.3389/fdgth.2026.1761624

MLA 9

Chim, Jenny, et al. “Evaluating privacy leakages in LLM-driven ambient clinical documentation.” Frontiers in Digital Health, vol. 8, 2026, p. 1761624. https://doi.org/10.3389/fdgth.2026.1761624.

Chicago

Chim, Jenny, Jonathan Pearson, Dan Schofield, and Maria Liakata. 2026. “Evaluating privacy leakages in LLM-driven ambient clinical documentation.” Frontiers in Digital Health 8: 1761624. https://doi.org/10.3389/fdgth.2026.1761624.

Harvard

Chim, J. et al. (2026) ‘Evaluating privacy leakages in LLM-driven ambient clinical documentation’, Frontiers in Digital Health, 8, p. 1761624. doi:10.3389/fdgth.2026.1761624.

IEEE

J. Chim, J. Pearson, D. Schofield, and M. Liakata, “Evaluating privacy leakages in LLM-driven ambient clinical documentation,” Frontiers in Digital Health, vol. 8, p. 1761624, 2026, doi: 10.3389/fdgth.2026.1761624.

BibTeX

@article{chim2026evaluating,
  title     = {{Evaluating privacy leakages in LLM-driven ambient clinical documentation}},
  author    = {Chim, Jenny and Pearson, Jonathan and Schofield, Dan and Liakata, Maria},
  journal   = {Frontiers in Digital Health},
  year      = {2026},
  volume    = {8},
  pages     = {1761624},
  doi       = {10.3389/fdgth.2026.1761624},
  url       = {https://doi.org/10.3389/fdgth.2026.1761624}
}

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

  • privacy leakage
  • large language models
  • clinical note generation
  • privacy by design
  • clinical documentation
  • speech recognition
  • benchmark design
  • Llama 3.1

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?

Chim, J., Pearson, J., Schofield, D., & Liakata, M. (2026). Evaluating privacy leakages in LLM-driven ambient clinical documentation. Frontiers in Digital Health, 8, 1761624. https://doi.org/10.3389/fdgth.2026.1761624

How many times has this paper been cited?

6 times, according to OpenAlex on 19 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 at Frontiers in Digital Health: sign in and open the PDF from this page.

Who wrote this paper?

Jenny Chim, Jonathan Pearson, Dan Schofield, Maria Liakata.

What is the DOI of this paper?

10.3389/fdgth.2026.1761624, permanently at https://doi.org/10.3389/fdgth.2026.1761624. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.