From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultations

TL;DR

This paper introduces SafeShare, a real-time privacy protection tool for online health consultations that uses localized LLMs to redact sensitive information, enhancing user privacy without sacrificing utility.

Contribution

The paper presents SafeShare, a novel interaction technique leveraging localized LLMs for real-time privacy redaction in online health consultations.

Findings

SafeShare achieves 89.64% accuracy in PII detection.

User interviews reveal a disconnect between privacy desires and platform practices.

SafeShare effectively balances privacy and utility in health consultations.

Abstract

Online medical consultation platforms, while convenient, are undermined by significant privacy risks that erode user trust. We first conducted in-depth semi-structured interviews with 12 users to understand their perceptions of security and privacy landscapes on online medical consultation platforms, as well as their practices, challenges and expectation. Our analysis reveals a critical disconnect between users' desires for anonymity and control, and platform realities that offload the responsibility of ``privacy labor''. To bridge this gap, we present SafeShare, an interaction technique that leverages localized LLM to redact consultations in real-time. SafeShare balances utility and privacy through selectively anonymize private information. A technical evaluation of SafeShare's core PII detection module on 3 dataset demonstrates high efficacy, achieving 89.64\% accuracy with Qwen3-4B on IMCS21 dataset.