Preprint · 2023 · Open access

Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets

Veysel Kocaman, Hasham Ul Haq, David Talby

arXiv (Cornell University) · Published 13 December 2023 · DOI 10.48550/arxiv.2312.08495

Open PDFView at the publisherCite this paper

In brief

“Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets” is a 2023 preprint by Veysel Kocaman and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2026 (6)
References
19
Authors
3

Abstract

Recent research advances achieve human-level accuracy for de-identifying free-text clinical notes on research datasets, but gaps remain in reproducing this in large real-world settings. This paper summarizes lessons learned from building a system used to de-identify over one billion real clinical notes, in a fully automated way, that was independently certified by multiple organizations for production use. A fully automated solution requires a very high level of accuracy that does not require manual review. A hybrid context-based model architecture is described, which outperforms a Named Entity Recogniton (NER) - only model by 10% on the i2b2-2014 benchmark. The proposed system makes 50%, 475%, and 575% fewer errors than the comparable AWS, Azure, and GCP services respectively while also outperforming ChatGPT by 33%. It exceeds 98% coverage of sensitive data across 7 European languages, without a need for fine tuning. A second set of described models enable data obfuscation -- replacing sensitive data with random surrogates -- while retaining name, date, gender, clinical, and format consistency. Both the practical need and the solution architecture that provides for reliable & linked anonymized documents are described.

Cite this paper

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

APA 7

Kocaman, V., Haq, H. U., & Talby, D. (2023). Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2312.08495

MLA 9

Kocaman, Veysel, et al. “Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2312.08495.

Chicago

Kocaman, Veysel, Hasham Ul Haq, and David Talby. 2023. “Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2312.08495.

Harvard

Kocaman, V., Haq, H. U. and Talby, D. (2023) ‘Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets’, arXiv (Cornell University). doi:10.48550/arxiv.2312.08495.

IEEE

V. Kocaman, H. U. Haq, and D. Talby, “Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2312.08495.

BibTeX

@misc{kocaman2023beyond,
  title     = {{Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets}},
  author    = {Kocaman, Veysel and Haq, Hasham Ul and Talby, David},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2312.08495},
  url       = {https://doi.org/10.48550/arxiv.2312.08495}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • clinical text
  • named entity recognition
  • data obfuscation
  • production deployment

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Kocaman, V., Haq, H. U., & Talby, D. (2023). Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2312.08495

How many times has this paper been cited?

7 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Veysel Kocaman, Hasham Ul Haq, David Talby.

What is the DOI of this paper?

10.48550/arxiv.2312.08495, permanently at https://doi.org/10.48550/arxiv.2312.08495. 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.