Preprint · 2024 · Open access

Scaling text de-identification using locally augmented ensembles

Karthik Murugadoss, Saivikas Killamsetty, Deeksha Doddahonnaiah, Nakul Iyer, Michael J. Pencina, Jeffrey M. Ferranti, John David Halamka, Bradley Malin, Sankar Ardhanari

medRxiv · Published 20 June 2024 · DOI 10.1101/2024.06.20.24308896

Open PDFView at the publisherCite this paper

In brief

“Scaling text de-identification using locally augmented ensembles” is a 2024 preprint by Karthik Murugadoss and 8 co-authors, published in medRxiv. OpenAlex counts 14 citations as of 19 November 2026. It is open access: the full text is free to read at medRxiv.

Citations
14
Most cited in
2026 (12)
References
34
Authors
9

Abstract

The natural language text in electronic health records (EHRs), such as clinical notes, often contains information that is not captured elsewhere (e.g., degree of disease progression and responsiveness to treatment) and, thus, is invaluable for downstream clinical analysis. However, to make such data available for broader research purposes, in the United States, personally identifiable information (PII) is typically removed from the EHR in accordance with the Privacy Rule of the Health Insurance Portability and Accountability Act (HIPAA). Automated de-identification systems that mimic human accuracy in identifier detection can enable access, at scale, to more diverse de-identified data sets thereby fostering robust findings in medical research to advance patient care. The best performing of such systems employ language models that require time and effort for retraining or fine tuning for newer datasets to achieve consistent results and revalidation on older datasets. Hence, there is a need to adapt text de-identification methods to datasets across health institutions. Given the success of foundational large language models (LLMs), such as ChatGPT, in a wide array of natural language processing (NLP) tasks, they seem a natural fit for identifying PII across varied datasets. In this paper, we introduce locally augmented ensembles, which adapt an existing PII detection ensemble method trained at one health institution to others by using institution-specific dictionaries to capture location specific PII and recover medically relevant information that was previously misclassified as PII. We augment an ensemble model created at Mayo Clinic and test it on a dataset of 15,716 clinical notes at Duke University Health System. We further compare the task specific fine tuned ensemble against LLM based prompt engineering solutions on the 2014 i2b2 and 2003 CoNLL NER datasets for prediction accuracy, speed and cost. On the Duke notes, our approach achieves increased recall and precision of 0.996 and 0.982 respectively compared to 0.989 and 0.979 respectively without the augmentation. Our results indicate that LLMs may require significant prompt engineering effort to reach the levels attained by ensemble approaches. Further, given the current state of technology, they are at least 3 times slower and 5 times more expensive to operate than the ensemble approach.

Cite this paper

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

APA 7

Murugadoss, K., Killamsetty, S., Doddahonnaiah, D., Iyer, N., Pencina, M. J., Ferranti, J. M., Halamka, J. D., Malin, B., & Ardhanari, S. (2024). Scaling text de-identification using locally augmented ensembles. medRxiv. https://doi.org/10.1101/2024.06.20.24308896

MLA 9

Murugadoss, Karthik, et al. “Scaling text de-identification using locally augmented ensembles.” medRxiv, 2024. https://doi.org/10.1101/2024.06.20.24308896.

Chicago

Murugadoss, Karthik, Saivikas Killamsetty, Deeksha Doddahonnaiah, Nakul Iyer, Michael J. Pencina, Jeffrey M. Ferranti, John David Halamka, Bradley Malin, and Sankar Ardhanari. 2024. “Scaling text de-identification using locally augmented ensembles.” medRxiv. https://doi.org/10.1101/2024.06.20.24308896.

Harvard

Murugadoss, K. et al. (2024) ‘Scaling text de-identification using locally augmented ensembles’, medRxiv. doi:10.1101/2024.06.20.24308896.

IEEE

K. Murugadoss et al., “Scaling text de-identification using locally augmented ensembles,” medRxiv, 2024, doi: 10.1101/2024.06.20.24308896.

BibTeX

@misc{murugadoss2024scaling,
  title     = {{Scaling text de-identification using locally augmented ensembles}},
  author    = {Murugadoss, Karthik and Killamsetty, Saivikas and Doddahonnaiah, Deeksha and Iyer, Nakul and Pencina, Michael J. and Ferranti, Jeffrey M. and Halamka, John David and Malin, Bradley and Ardhanari, Sankar},
  howpublished = {medRxiv},
  year      = {2024},
  doi       = {10.1101/2024.06.20.24308896},
  url       = {https://doi.org/10.1101/2024.06.20.24308896}
}

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 notes
  • electronic health records
  • large language models
  • prompt engineering
  • natural language processing
  • HIPAA Privacy Rule
  • i2b2

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?

Murugadoss, K., Killamsetty, S., Doddahonnaiah, D., Iyer, N., Pencina, M. J., Ferranti, J. M., Halamka, J. D., Malin, B., & Ardhanari, S. (2024). Scaling text de-identification using locally augmented ensembles. medRxiv. https://doi.org/10.1101/2024.06.20.24308896

How many times has this paper been cited?

14 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 medRxiv: sign in and open the PDF from this page.

Who wrote this paper?

Karthik Murugadoss, Saivikas Killamsetty, Deeksha Doddahonnaiah, Nakul Iyer, Michael J. Pencina, Jeffrey M. Ferranti, John David Halamka, Bradley Malin, Sankar Ardhanari.

What is the DOI of this paper?

10.1101/2024.06.20.24308896, permanently at https://doi.org/10.1101/2024.06.20.24308896. 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.