arXiv cs.CL· Sankalp Vaish, Sumukh Veeramalla, Rishank Singh, Caroline Summerour, John A. Batsis, Xiaohui Liang·· 2 天前AI 评分23
CogDrift-4D：面向 MCI 检测的时间行为衰退分层多模态建模
CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection
AI 导读
CogDrift-4D 是一个分层 4D Transformer 框架，用于轻度认知障碍（MCI）检测，在结构化言语与语言交互评测中取得 0.733±0.13 的分类准确率和 0.716±0.14 的 F1 分数，优于先进基线。
正文 · 原文
Abstract:Early detection of mild cognitive impairment remains a critical bottleneck in dementia care, demanding scalable tools capable of capturing subtle behavioral decay. To capture the subtle temporal changes of cognitive decline, we introduce a behavioral dataset collected across seven unscripted multimodal interactions over an 18-month horizon. This dataset formalizes continuous, multi-session interactions into a dense 4D tensor (Batch * Session * Time * Feature) that explicitly preserves concurrent local dynamics alongside long-term changes. To effectively process these complex behavioral patterns, we propose CogDrift-4D: a novel, hierarchical 4D Transformer framework. To capture the complex trajectory of cognitive decline, CogDrift-4D implements a dual-level behavioral fatigue and drift modeling architecture. At the intra-session level, the model computes localized least-squares regression slopes to quantify the acute ``fading'' of frame-level facial action units and acoustic energy. At the inter-session level, a recursive cross-attention feedback encoder acts as a cumulative fatigue accumulator, mapping the patient's continuous behavioral drift across successive sessions. To mitigate environmental noise and track failures across sessions, a localized Quality Gate dynamically filters low-integrity features before final fusion, also an early fusion that integrates semantic insights with raw physical dynamics. Evaluated on structured verbal and linguistic interactions, our architecture successfully detects MCI with a classification accuracy of 0.733 +- 0.13 and an F1-score of 0.716 +- 0.14, outperforming advanced baselines. The framework provides a mathematically rigorous, scalable, and robust foundation for home-based, real-time dementia screening.
| Comments: | Accepted for publication at the 2026 IEEE International Conference on E-health Networking, Application & Services (Healthcom) |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20877 [cs.LG] |
| (or arXiv:2610.20877v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20877 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sankalp Vaish [view email]
[v1]
Wed, 14 Oct 2026 20:08:01 UTC (408 KB)
来源：arXiv cs.CL · arxiv.org