融合语言特征与预训练时序嵌入，提升阿尔茨海默病早期识别准确率
Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification
- 结合可解释语言特征与预训练模型提取的时序嵌入进行多模态融合
- 分类任务F1得分0.649，回归任务RMSE为2.628，排名竞赛第一
- 适合关注早期认知衰退检测的临床与算法研究者
通过自发性言语进行认知障碍检测是阿尔茨海默病（AD）和轻度认知障碍（MCI）早期诊断的有前景方向，及时干预可显著改善患者预后。ICASSP 2025的PROCESS大挑战推动了认知衰退检测的分类与回归方法创新。本文提出一种多模态融合策略，将可解释的语言特征与预训练模型提取的时序嵌入相结合。该方法在分类任务（区分健康、MCI、痴呆）中取得F1-score 0.649，回归任务（MMSE评分预测）中达到RMSE 2.628，获得竞赛总分第一。
原文摘要 · Abstract (English)
Cognitive impairment detection through spontaneous speech is a promising avenue for early diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI), where timely intervention can significantly improve patient outcomes. The PROCESS Grand Challenge at ICASSP 2025 addresses these tasks by promoting innovative classification and regression methods for detecting cognitive decline. In this paper, we propose a multimodal fusion strategy that combines interpretable linguistic features with temporal embeddings extracted from pre-trained models. Our approach achieves an F1-score of 0.649 for the classification task (predicting healthy, MCI, dementia) and an RMSE of 2.628 for the regression task (MMSE score prediction), securing the top overall ranking in the competition.
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。