Classifying Dementia in the Presence of Depression: A Cross-Corpus Study

TL;DR

This study develops and evaluates speech-based classifiers to distinguish between healthy controls, MCI, and dementia, accounting for depression, across different datasets and recording conditions to improve early diagnosis accuracy.

Contribution

It introduces a multi-class classification approach using speech, text, and emotion features on cross-corpus German datasets, addressing generalization and depression effects.

Findings

Effective discrimination between HC, MCI, and DEM using speech features.

Cross-corpus models show promising generalization across datasets.

Depression influences classification, highlighting the need for nuanced models.

Abstract

Automated dementia screening enables early detection and intervention, reducing costs to healthcare systems and increasing quality of life for those affected. Depression has shared symptoms with dementia, adding complexity to diagnoses. The research focus so far has been on binary classification of dementia (DEM) and healthy controls (HC) using speech from picture description tests from a single dataset. In this work, we apply established baseline systems to discriminate cognitive impairment in speech from the semantic Verbal Fluency Test and the Boston Naming Test using text, audio and emotion embeddings in a 3-class classification problem (HC vs. MCI vs. DEM). We perform cross-corpus and mixed-corpus experiments on two independently recorded German datasets to investigate generalization to larger populations and different recording conditions. In a detailed error analysis, we look at depression as a secondary diagnosis to understand what our classifiers actually learn.