# De-identification of clinical free text using natural language processing: A systematic review of current approaches

arXiv: https://arxiv.org/abs/2312.03736 · HTML: https://mlsanity.com/paper/2312.03736/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 96 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 7 of 7)

- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [De-identification of medical records using conditional random fields and long short-term memory networks](https://mlsanity.com/paper/1709.06901/) (2017)
- [De-identifying Australian Hospital Discharge Summaries: An End-to-End Framework using Ensemble of Deep Learning Models](https://mlsanity.com/paper/2101.00146/) (2021)
- [A Context-Enhanced De-identification System](https://mlsanity.com/paper/2102.08513/) (2021)
- [De-identification of Unstructured Clinical Texts from Sequence to Sequence Perspective](https://mlsanity.com/paper/2108.07971/) (2021)

## Built on by (most cited first, 13 of 13)

- [CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering](https://mlsanity.com/paper/2506.08584/) (2025)
- [RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification](https://mlsanity.com/paper/2505.18380/) (2025)
- [A Survey on Current Trends and Recent Advances in Text Anonymization](https://mlsanity.com/paper/2508.21587/) (2025)
- [Conversational Disease Diagnosis via External Planner-Controlled Large Language Models](https://mlsanity.com/paper/2404.04292/) (2024)
- [Synthetic4Health: Generating Annotated Synthetic Clinical Letters](https://mlsanity.com/paper/2409.09501/) (2024)
- [Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration](https://mlsanity.com/paper/2510.16194/) (2025)
- [Synthesis and Evaluation of Long-term History-aware Medical Dialogue](https://mlsanity.com/paper/2605.19766/) (2026)
- [DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment](https://mlsanity.com/paper/2410.01648/) (2024)
- [SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification](https://mlsanity.com/paper/2605.03301/) (2026)
- [Leveraging Large Language Models for Rare Disease Named Entity Recognition](https://mlsanity.com/paper/2508.09323/) (2025)
- [Stronger Re-identification Attacks through Reasoning and Aggregation](https://mlsanity.com/paper/2510.09184/) (2025)
- [Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives](https://mlsanity.com/paper/2601.13503/) (2026)
- [Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification](https://mlsanity.com/paper/2606.18372/) (2026)

## Abstract (arXiv)

Background: Electronic health records (EHRs) are a valuable resource for data-driven medical research. However, the presence of protected health information (PHI) makes EHRs unsuitable to be shared for research purposes. De-identification, i.e. the process of removing PHI is a critical step in making EHR data accessible. Natural language processing has repeatedly demonstrated its feasibility in automating the de-identification process. Objectives: Our study aims to provide systematic evidence on how the de-identification of clinical free text has evolved in the last thirteen years, and to report on the performances and limitations of the current state-of-the-art systems. In addition, we aim to identify challenges and potential research opportunities in this field. Methods: A systematic search in PubMed, Web of Science and the DBLP was conducted for studies published between January 2010 and February 2023. Titles and abstracts were examined to identify the relevant studies. Selected studies were then analysed in-depth, and information was collected on de-identification methodologies, data sources, and measured performance. Results: A total of 2125 publications were identified for the title and abstract screening. 69 studies were found to be relevant. Machine learning (37 studies) and hybrid (26 studies) approaches are predominant, while six studies relied only on rules. Majority of the approaches were trained and evaluated on public corpora. The 2014 i2b2/UTHealth corpus is the most frequently used (36 studies), followed by the 2006 i2b2 (18 studies) and 2016 CEGS N-GRID (10 studies) corpora.