Preprint · 2026 · Open access
De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint)
Published 18 July 2026 · DOI 10.2196/preprints.107369
In brief
“De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint)” is a 2026 preprint by Murat Koçak and 2 co-authors. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read.
- Citations
- 0
- Authors
- 3
Abstract
BACKGROUND Electronic health records (EHRs) contain Protected Health Information (PHI) that poses significant privacy and regulatory risks. Cloud-based large language model (LLM) solutions require data to leave institutional boundaries, raising legal and ethical concerns. OBJECTIVE This study aimed to develop and validate a fully local de-identification pipeline based on HIPAA Safe Harbor criteria, comparatively evaluating 11 open-source local LLMs on Turkish clinical text. METHODS Clinical documents from Turkish healthcare institutions (n=221, 488 pages) were digitized from PDF to Markdown via a vision-language model OCR pipeline and processed through a zero-shot de-identification prompt. A manually annotated gold standard of 11,768 PHI spans across 18 HIPAA entity categories was constructed and used for evaluation. Model performance was assessed using precision, recall, F1 score, and Matthews Correlation Coefficient (MCC). RESULTS Binary PHI F1 scores ranged from 0.56 to 0.96. Qwen3.5-27B-NonThinking achieved the highest performance (Binary F1=0.96, Macro F1=0.917, MCC=0.876), establishing itself as the Pareto-dominant model without extended chain-of-thought reasoning. Four models met the Excellent MCC threshold (>0.75) required for HIPAA-regulated deployment. Structurally regular entities (EMAIL, IP, SSN, URL) were detected consistently across models, while contextually dependent categories (DEVICE, HEALTHPLANID, OTHERID) showed high inter-model variance. The domain-specific MedGemma-27B ranked last (F1=0.56, MCC=0.12), indicating that clinical pre-training does not inherently confer advantages in structured PHI detection. A "Performance Cliff" below rank 8 revealed that MCC collapsed while F1 remained superficially acceptable, underscoring F1's insufficiency as a sole evaluation criterion. CONCLUSIONS The developed prototype demonstrates the feasibility of privacy-preserving de-identification of Turkish clinical records using local large language models, offering a practical solution for institutions seeking to comply with data protection requirements while leveraging AI-assisted clinical research. The comparative evaluation of 11 models revealed significant differences in performance across identifier categories, highlighting the importance of model selection and language-specific post-processing in non-English clinical contexts. Future work should focus on fine-tuning models on annotated Turkish EHRs and expanding validation across diverse hospital settings. CLINICALTRIAL N/A
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Koçak, M., İsmayılov, R., & Akçalı, Z. (2026). De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint). https://doi.org/10.2196/preprints.107369
MLA 9
Koçak, Murat, et al. “De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint).” 2026. https://doi.org/10.2196/preprints.107369.
Chicago
Koçak, Murat, Rashad İsmayılov, and Zafer Akçalı. 2026. “De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint).” https://doi.org/10.2196/preprints.107369.
Harvard
Koçak, M., İsmayılov, R. and Akçalı, Z. (2026) ‘De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint)’. doi:10.2196/preprints.107369.
IEEE
M. Koçak, R. İsmayılov, and Z. Akçalı, “De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint),” 2026, doi: 10.2196/preprints.107369.
BibTeX
@misc{kocak2026identification,
title = {{De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint)}},
author = {Koçak, Murat and İsmayılov, Rashad and Akçalı, Zafer},
year = {2026},
doi = {10.2196/preprints.107369},
url = {https://doi.org/10.2196/preprints.107369}
}
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
- de-identification
- electronic health records
- local large language models
- protected health information
- open-source LLMs
- model evaluation
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Koçak, M., İsmayılov, R., & Akçalı, Z. (2026). De-identification of Turkish Electronic Health Records Using Local Large Language Models: A Privacy-Focused and Open-Source Prototype Development Study (Preprint). https://doi.org/10.2196/preprints.107369
How many times has this paper been cited?
0 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: sign in and open the full text from this page.
Who wrote this paper?
Murat Koçak, Rashad İsmayılov, Zafer Akçalı.
What is the DOI of this paper?
10.2196/preprints.107369, permanently at https://doi.org/10.2196/preprints.107369. 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.