During psychiatric assessment, clinicians observe not only what patients report, but important nonverbal signs such as tone, speech rate, fluency, responsiveness, and body language. Weighing and integrating these different information sources is a challenging task and a good candidate for support by intelligence-driven tools - however this is yet to be realized in the clinic. Here, we argue that several important barriers to adoption can be addressed using Bayesian network modelling. To demonstrate this, we evaluate a model for depression and anxiety symptom prediction from voice and speech features in large-scale datasets (30,135 unique speakers). Alongside performance for conditions and symptoms (for depression, anxiety ROC-AUC=0.842,0.831 ECE=0.018,0.015; core individual symptom ROC-AUC>0.74), we assess demographic fairness and investigate integration across and redundancy between different input modality types. Clinical usefulness metrics and acceptability to mental health service users are explored. When provided with sufficiently rich and large-scale multimodal data streams and specified to represent common mental conditions at the symptom rather than disorder level, such models are a principled approach for building robust assessment support tools: providing clinically-relevant outputs in a transparent and explainable format that is directly amenable to expert clinical supervision.

翻译：在精神科评估过程中，临床医生不仅关注患者主诉内容，还观察重要的非言语体征，如语调、语速、流畅度、应答反应及肢体语言。权衡并整合这些不同信息源是一项具有挑战性的任务，也是智能驱动工具辅助应用的理想场景——然而该目标尚未在临床实践中实现。本文提出，采用贝叶斯网络建模可有效解决临床应用中的若干关键障碍。为验证此观点，我们基于大规模数据集（30,135名独立说话者）评估了通过语音与言语特征预测抑郁和焦虑症状的模型性能。除针对疾病整体与核心症状的预测效能（抑郁与焦虑的ROC-AUC分别为0.842与0.831，预期校准误差ECE为0.018与0.015；核心个体症状ROC-AUC均大于0.74）外，我们还评估了模型的人口统计学公平性，并探究了不同输入模态类型间的整合效应与冗余关系。同时，本文探讨了临床实用性指标及心理健康服务使用者的接受度。研究表明，当获得足够丰富的大规模多模态数据流，并将模型设定为在症状层面（而非疾病层面）表征常见精神状况时，此类模型可成为构建稳健评估支持工具的规范化方法：其以透明、可解释的形式提供临床相关输出，并能直接接受临床专家的监督指导。