# Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss

arXiv: https://arxiv.org/abs/2509.14464 · HTML: https://mlsanity.com/paper/2509.14464/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [string2string: A Modern Python Library for String-to-String Algorithms](https://mlsanity.com/paper/2304.14395/) (2023)
- [Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records](https://mlsanity.com/paper/2001.05714/) (2020)
- [Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study](https://mlsanity.com/paper/2406.00062/) (2024)
- [LLMs-in-the-Loop Part 2: Expert Small AI Models for Anonymization and De-identification of PHI Across Multiple Languages](https://mlsanity.com/paper/2412.10918/) (2024)

## Built on by (most cited first, 4 of 4)

- [Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches](https://mlsanity.com/paper/2602.15869/) (2026)
- [Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives](https://mlsanity.com/paper/2601.13503/) (2026)
- [Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss](https://mlsanity.com/paper/2608.17051/) (2026)
- [MedDeID enables locally governed clinical-text de-identification from real or synthetic training data](https://mlsanity.com/paper/2609.10049/) (2026)

## Abstract (arXiv)

De-identification in the healthcare setting is an application of NLP where automated algorithms are used to remove personally identifying information of patients (and, sometimes, providers). With the recent rise of generative large language models (LLMs), there has been a corresponding rise in the number of papers that apply LLMs to de-identification. Although these approaches often report near-perfect results, significant challenges concerning reproducibility and utility of the research papers persist. This paper identifies three key limitations in the current literature: inconsistent reporting metrics hindering direct comparisons, the inadequacy of traditional classification metrics in capturing errors which LLMs may be more prone to (i.e., altering clinically relevant information), and lack of manual validation of automated metrics which aim to quantify these errors. To address these issues, we first present a survey of LLM-based de-identification research, highlighting the heterogeneity in reporting standards. Second, we evaluated a diverse set of models to quantify the extent of inappropriate removal of clinical information. Next, we conduct a manual validation of an existing evaluation metric to measure the removal of clinical information, employing clinical experts to assess their efficacy. We highlight poor performance and describe the inherent limitations of such metrics in identifying clinically significant changes. Lastly, we propose a novel methodology for the detection of clinically relevant information removal.