用AI筛查心理疾病需兼顾隐私，这篇论文给出实用解决方案。
Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities
- 结合匿名化与合成数据，降低患者信息泄露风险
- 提出隐私-效用权衡框架，平衡保护与诊断精度
- 适合关注医疗AI伦理与落地的研究者和开发者
心理疾病带来深远的个人与社会负担，但传统诊断方式成本高、可及性差。人工智能，尤其是自然语言处理与多模态方法的进步，为心理障碍的检测与干预提供了新可能，但也引发严重隐私风险。本文系统分析这些挑战，提出包括匿名化、合成数据生成和隐私保护训练在内的解决方案，并构建隐私-效用权衡框架，旨在推动可靠、具备隐私意识的AI工具发展，支持临床决策并改善心理健康结果。
原文摘要 · Abstract (English)
Mental health disorders create profound personal and societal burdens, yet conventional diagnostics are resource-intensive and limit accessibility. Advances in artificial intelligence, particularly natural language processing and multimodal methods, offer promise for detecting and addressing mental disorders, but raise critical privacy risks. This paper examines these challenges and proposes solutions, including anonymization, synthetic data, and privacy-preserving training, while outlining frameworks for privacy-utility trade-offs, aiming to advance reliable, privacy-aware AI tools that support clinical decision-making and improve mental health outcomes.
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。