用AI实时辅助心理治疗督导，自动识别风险并分级预警。
Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage
- 三路分析框架：追踪治疗关系、预测潜在风险、动态分级干预
- 95%准确率识别治疗技术，风险预警延迟从72小时缩短至10秒
- 适合心理治疗培训与高危患者实时监控场景
现代心理健康服务面临资深督导资源严重不足，导致新手治疗师在高风险情境下缺乏及时反馈。本文提出一种基于微调Mistral-7B-instruct模型的自动化“督导在环”系统，利用DAIC-WOZ数据集中的106个会话进行三路分析：(1) 基于语义一致性追踪治疗联盟，(2) 通过注意力加权分析实现潜在风险预测，(3) 采用动态临床紧急指数（D-CUI）完成督导分诊。多模态VAL（视觉-语音-语言）框架达到95%的技术识别准确率（95% CI: 75.1%-99.9%），联盟评估平均绝对误差为0.105（5分制，95% CI: 0.059-0.151），治疗保真度alpha=0.423，D-CUI均值为0.370（95% CI: 0.322-0.419）。训练在单张Tesla T4 GPU上仅需105步，损失下降85.2%。系统将督导分诊延迟从72小时压缩至实时（每会话约10秒），支持高风险案例主动干预。通过贝叶斯先验缓解冷启动问题，并采用时间戳对齐实现鲁棒的多模态融合。
原文摘要 · Abstract (English)
Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a "supervision gap" where novice therapists manage high-stakes risks with delayed professional feedback. This paper proposes a new framework utilizing a fine-tuned Mistral-7B-instruct model as an automated "Supervisor-in-the-Loop" system. By leveraging 106 sessions from the DAIC-WOZ dataset, the model performs a tri-stream analysis: (1) Therapeutic Alliance tracking via semantic adherence, (2) Latent risk prediction using attention-weighted analytics, and (3) Supervisory Triage via a Dynamic Clinical Urgency Index (D-CUI). Our multi-modal VAL (Visual-Acoustic-Linguistic) framework achieves 95% technique identification accuracy [95% CI: 75.1%-99.9%], alliance assessment MAE of 0.105 on a 5-point scale [95% CI: 0.059-0.151], therapeutic fidelity alpha = 0.423, and mean D-CUI of 0.370 [95% CI: 0.322-0.419]. Training converged in 105 steps with 85.2% loss reduction on a single Tesla T4 GPU. The system reduces supervisory triage latency from 72 hours to real time (~10 seconds per session), enabling proactive intervention in high-risk cases. The system addresses the cold-start problem through Bayesian priors and implements timestamp-based modality synchronization for robust multi-modal fusion.
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。