将心理诊疗大模型部署在设备端，确保患者数据全程不外泄。
Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
- 采用轻量级大模型在本地运行，实现零数据外泄。
- 三模型协同推理，诊断准确率与云端相当。
- 适合军营、监狱等高隐私要求的医疗场景使用。
隐私是人工智能在心理健康领域应用中最关键却长期被忽视的障碍，尤其在军事、监狱及偏远医疗等敏感环境中，患者数据泄露风险可能完全抑制求助行为。现有精神科决策支持系统多依赖云端推理，需将敏感数据传输至外部服务器，带来不可接受的隐私与安全风险。本文提出一种零外泄、设备端部署的心理健康辅助AI平台，作为跨平台移动应用运行。该系统通过重构推理流程，实现全本地执行，确保患者数据在任何阶段均不离开设备、不被外部服务器处理或存储。平台集成三个轻量化、微调并量化的开源大模型（Gemma、Phi-3.5-mini、Qwen2），基于其紧凑架构与在资源受限移动硬件上的高效表现进行选型。设备端编排层协调模型集成推理与共识式诊断分析，生成符合DSM-5标准的评估结果。系统旨在协助临床医生进行鉴别诊断与症状映射，同时支持患者自助筛查，并配备相应临床安全机制。初步评估表明，该零外泄部署在通用移动设备上实现了与云端版本相当的诊断准确率，且保持实时推理延迟。
原文摘要 · Abstract (English)
Privacy represents one of the most critical yet underaddressed barriers to AI adoption in mental healthcare -- particularly in high-sensitivity operational environments such as military, correctional, and remote healthcare settings, where the risk of patient data exposure can deter help-seeking behavior entirely. Existing AI-enabled psychiatric decision support systems predominantly rely on cloud-based inference pipelines, requiring sensitive patient data to leave the device and traverse external servers, creating unacceptable privacy and security risks in these contexts. In this paper, we propose a zero-egress, on-device AI platform for privacy-preserving psychiatric decision support, deployed as a cross-platform mobile application. The proposed system extends our prior work on fine-tuned LLM consortiums for psychiatric diagnosis standardization by fundamentally re-architecting the inference pipeline for fully local execution -- ensuring that no patient data is transmitted to, processed by, or stored on any external server at any stage. The platform integrates a consortium of three lightweight, fine-tuned, and quantized open-source LLMs -- Gemma, Phi-3.5-mini, and Qwen2 -- selected for their compact architectures and proven efficiency on resource-constrained mobile hardware. An on-device orchestration layer coordinates ensemble inference and consensus-based diagnostic reasoning, producing DSM-5-aligned assessments for conditions. The platform is designed to assist clinicians with differential diagnosis and evidence-linked symptom mapping, as well as to support patient-facing self-screening with appropriate clinical safeguards. Initial evaluation demonstrates that the proposed zero-egress deployment achieves diagnostic accuracy comparable to its server-side predecessor while sustaining real-time inference latency on commodity mobile hardware.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。