用概率模型预测抑郁程度，还能看清信心变化过程。
Probabilistic Textual Time Series Depression Detection
- 结合注意力与概率输出，从对话序列中预测抑郁分数。
- 在E-DAIC和DAIC-WOZ数据集上MAE低于4.0，结果可信度高。
- 适合临床辅助决策，尤其关注预测不确定性的场景。
准确且可解释的抑郁严重程度预测对临床决策支持至关重要，但现有模型常缺乏不确定性估计和时间可解释性。本文提出PTTSD，一种基于临床访谈语句序列的抑郁检测概率框架，不仅能预测PHQ-8评分，还可建模校准后的不确定性。该框架包含序列到序列和序列到单值两种变体，均融合LSTM、自注意力与残差连接，并采用高斯或学生t分布输出头，通过负对数似然进行训练。序列到序列变体虽目标为单次会话评分，但仍能实现对预测置信度随时间演变的分析。在E-DAIC和DAIC-WOZ数据集上，PTTSD在纯文本系统中表现优异（如E-DAIC上MAE=3.85，DAIC-WOZ上MAE=3.55），且生成了校准良好的预测区间。消融实验验证了注意力机制与概率建模的有效性；三部分校准分析与定性案例研究进一步凸显了不确定性感知预测的临床价值。
原文摘要 · Abstract (English)
Accurate and interpretable predictions of depression severity are essential for clinical decision support, yet existing models often lack uncertainty estimates and temporal interpretability. We propose PTTSD, a Probabilistic framework for Depression Detection from clinical interview utterance sequences that predicts PHQ-8 scores while modeling calibrated uncertainty. PTTSD includes sequence-to-sequence and sequence-to-one variants, both combining LSTMs, self-attention, and residual connections with Gaussian or Student's-t output heads trained via negative log-likelihood. The sequence-to-sequence variant enables temporal analysis of how predictive confidence evolves over an interview, despite the target being a single session-level score. Evaluated on E-DAIC and DAIC-WOZ, PTTSD achieves competitive performance among text-only systems (e.g., MAE = 3.85 on E-DAIC, 3.55 on DAIC) and produces well-calibrated prediction intervals. Ablations confirm the value of attention and probabilistic modeling, while a three-part calibration analysis and qualitative case studies highlight the clinical relevance of uncertainty-aware prediction.
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。