《柳叶刀·数字健康》发表多模态AI模型，可预测TAVI术后长期死亡风险
Multimodal artificial intelligence-based long-term mortality prediction after transcatheter aortic valve implantation: a multicentre development, validation, and testing study
柳叶刀子刊的多中心研究：多模态AI预测TAVI术后长期死亡率，比传统风险评分准，能帮医生给病人分层。
《柳叶刀·数字健康》刊发一项多中心研究，开发并验证了一个用于预测TAVI（经导管主动脉瓣植入术）术后长期死亡风险的多模态AI模型。
论文称该模型采用可解释设计，在预测TAVI人群长期结局上显著优于传统风险评分。模型在不同TAVI人群和临床环境中均保持稳健的泛化能力，可通过准确的风险分层来指导患者管理。
Multimodal artificial intelligence-based long-term mortality prediction after transcatheter aortic valve implantation: a multicentre development, validation, and testing study
Our explainable, multimodal AI-based model for predicting long-term outcomes in the TAVI population substantially outperformed conventional risk scores. The model showed robust generalisability across diverse TAVI populations and clinical settings, supporting accurate risk stratification that could potentially guide patient management.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括：TAVI、The Lancet Digital Health、多模态、医疗AI，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「Lancet Digital Health」（@Isaac Shiri, Daijiro Tomii, Giovanni Baj, Pooya Mohammadi Kazaj, Toshiya Yoshida, Wen Xie, Taishi Okuno, Masaaki Nakase, Daryoush Samim, Waldo Valenzuela, Stefan Stortecky, David Reineke, Jonas Lanz, George C M Siontis, Yoshihiro J Akashi, Thomas Pilgrim, Stephan Windecker, Christoph Gräni），经 AITOP 多维评分管线结构化提炼。
