Predicting treatment non-response for anxiety and depression is challenging, in part because of sparse symptom assessments in real-world care. We examined whether passively captured, fine-grained emotions serve as linguistic markers of treatment outcomes by analyzing 12 weeks of de-identified teletherapy transcripts from 12,043 U.S. patients with moderate-to-severe anxiety and depression symptoms. A transformer-based small language model extracted patients' emotions at the talk-turn level; a state-space model (VISTA-SSM) clustered subgroups based on emotion dynamics over time and produced temporal networks. Two groups emerged: an improving group (n=8,230) and a non-response group (n=3,813) showing increased odds of symptom deterioration, and lower likelihood of clinically significant improvement. Temporal networks indicated that sadness and fear exerted most influence on emotion dynamics in non-responders, whereas improving patients showed balanced joy, sadness, and neutral expressions. Findings suggest that linguistic markers of emotional inflexibility can serve as scalable, interpretable, and theoretically grounded indicators for treatment risk stratification.

翻译：预测焦虑与抑郁治疗无应答具有挑战性，部分原因在于真实世界诊疗中症状评估数据稀疏。通过分析12,043名中重度焦虑抑郁症状美国患者为期12周的去标识化远程治疗转录文本，我们检验了被动采集的细粒度情绪是否可作为治疗结果的语言标记物。基于Transformer的小型语言模型在对话轮次层面提取患者情绪；状态空间模型（VISTA-SSM）根据情绪动态变化对亚组进行聚类并生成时序网络。研究识别出两组患者：改善组（n=8,230）与无应答组（n=3,813），后者症状恶化几率更高，且获得临床显著改善的可能性更低。时序网络显示，悲伤与恐惧情绪对无应答者的情绪动态影响最大，而改善组患者则表现出喜悦、悲伤及中性表达的平衡状态。研究结果表明，情绪僵化性的语言标记物可作为可扩展、可解释且具有理论依据的治疗风险分层指标。