MultiConAD: A Unified Multilingual Conversational Dataset for Early Alzheimer's Detection

TL;DR

This paper introduces a multilingual conversational dataset for early Alzheimer's detection, enabling finer classification including MCI, and evaluates cross-language models to improve early diagnosis and generalization.

Contribution

The paper presents a novel multilingual dataset unifying 16 datasets across four languages, and explores multi-class classification including MCI, advancing early AD detection research.

Findings

Multilingual training benefits some languages for AD detection.

Finer-grained classification improves early diagnosis.

Cross-language models show variable performance across languages.

Abstract

Dementia is a progressive cognitive syndrome with Alzheimer's disease (AD) as the leading cause. Conversation-based AD detection offers a cost-effective alternative to clinical methods, as language dysfunction is an early biomarker of AD. However, most prior research has framed AD detection as a binary classification problem, limiting the ability to identify Mild Cognitive Impairment (MCI)-a crucial stage for early intervention. Also, studies primarily rely on single-language datasets, mainly in English, restricting cross-language generalizability. To address this gap, we make three key contributions. First, we introduce a novel, multilingual dataset for AD detection by unifying 16 publicly available dementia-related conversational datasets. This corpus spans English, Spanish, Chinese, and Greek and incorporates both audio and text data derived from a variety of cognitive assessment tasks. Second, we perform finer-grained classification, including MCI, and evaluate various classifiers using sparse and dense text representations. Third, we conduct experiments in monolingual and multilingual settings, finding that some languages benefit from multilingual training while others perform better independently. This study highlights the challenges in multilingual AD detection and enables future research on both language-specific approaches and techniques aimed at improving model generalization and robustness.