# Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies

arXiv: https://arxiv.org/abs/2509.10882 · HTML: https://mlsanity.com/paper/2509.10882/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 13 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [Unlocking High-Accuracy Differentially Private Image Classification through Scale](https://mlsanity.com/paper/2204.13650/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning](https://mlsanity.com/paper/2102.12677/) (2021)
- [Differentially Private Synthetic Data via Foundation Model APIs 2: Text](https://mlsanity.com/paper/2403.01749/) (2024)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [Differentially Private Optimization on Large Model at Small Cost](https://mlsanity.com/paper/2210.00038/) (2022)
- [Harnessing large-language models to generate private synthetic text](https://mlsanity.com/paper/2306.01684/) (2023)
- [Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes](https://mlsanity.com/paper/2309.00237/) (2023)
- [Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping](https://mlsanity.com/paper/2009.03106/) (2020)
- [A Comparative Study of Pretrained Language Models for Long Clinical Text](https://mlsanity.com/paper/2301.11847/) (2023)
- [EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries](https://mlsanity.com/paper/2402.16040/) (2024)
- [Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models](https://mlsanity.com/paper/2208.08408/) (2022)
- [MIRA: Medical Time Series Foundation Model for Real-World Health Data](https://mlsanity.com/paper/2506.07584/) (2025)
- [BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling](https://mlsanity.com/paper/2503.02445/) (2025)
- [Differentially Private Knowledge Distillation via Synthetic Text Generation](https://mlsanity.com/paper/2403.00932/) (2024)
- [The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text](https://mlsanity.com/paper/2502.14921/) (2025)
- [Can GPT-3.5 Generate and Code Discharge Summaries?](https://mlsanity.com/paper/2401.13512/) (2024)
- [Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains](https://mlsanity.com/paper/2410.08327/) (2024)
- [PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records](https://mlsanity.com/paper/2307.02006/) (2023)
- [Evaluating Differentially Private Generation of Domain-Specific Text](https://mlsanity.com/paper/2508.20452/) (2025)
- [Controllable Synthetic Clinical Note Generation with Privacy Guarantees](https://mlsanity.com/paper/2409.07809/) (2024)

## Built on by (most cited first, 1 of 1)

- [ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?](https://mlsanity.com/paper/2606.01849/) (2026)

## Abstract (arXiv)

In high-stakes domains such as healthcare, privacy concerns severely limit the use of real-world training data. Differentially private (DP) synthetic data offers a promising alternative with formal privacy guarantees, but achieving strong utility remains challenging for clinical note generation due to domain specificity and long-form text complexity. We present Term2Note, a method for synthesising full-length clinical notes under DP constraints. By structurally separating content and form, Term2Note generates section-wise note content conditioned on medical terms, with terms and notes privatised under separate DP constraints, and applies a DP quality maximiser to improve outputs. Experiments demonstrate that Term2Note produces synthetic notes with statistical properties closely aligned with real clinical notes, and that downstream models trained on these notes achieve performance comparable to those trained on real clinical data. Compared to existing DP text generation baselines, Term2Note substantially improves both fidelity and utility, without relying on label distribution assumptions, highlighting its effectiveness as a practical privacy-preserving alternative to real clinical notes.