In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages
This work addresses clinician burnout by enabling the creation of HIPAA-friendly synthetic patient portal messages for research and tool development, though it is incremental as it builds on existing text generation techniques.
The study tackled the lack of public patient portal message datasets by introducing an LLM-powered framework for generating realistic synthetic messages, showing through evaluation that it produces higher quality data than comparable methods and existing datasets.
Since the COVID-19 pandemic, clinicians have seen a large and sustained influx in patient portal messages, significantly contributing to clinician burnout. To the best of our knowledge, there are no large-scale public patient portal messages corpora researchers can use to build tools to optimize clinician portal workflows. Informed by our ongoing work with a regional hospital, this study introduces an LLM-powered framework for configurable and realistic patient portal message generation. Our approach leverages few-shot grounded text generation, requiring only a small number of de-identified patient portal messages to help LLMs better match the true style and tone of real data. Clinical experts in our team deem this framework as HIPAA-friendly, unlike existing privacy-preserving approaches to synthetic text generation which cannot guarantee all sensitive attributes will be protected. Through extensive quantitative and human evaluation, we show that our framework produces data of higher quality than comparable generation methods as well as all related datasets. We believe this work provides a path forward for (i) the release of large-scale synthetic patient message datasets that are stylistically similar to ground-truth samples and (ii) HIPAA-friendly data generation which requires minimal human de-identification efforts.