Automatic detection of Mild Cognitive Impairment using high-dimensional acoustic features in spontaneous speech

TL;DR

This paper explores machine learning methods to detect Mild Cognitive Impairment from spontaneous speech using high-dimensional acoustic features, demonstrating the effectiveness of certain models across multiple experiments.

Contribution

It introduces a comprehensive comparison of five machine learning methods for MCI detection using high-dimensional acoustic features, including language-agnostic and language-specific models.

Findings

Random Forest and Sparse Logistic Regression performed best.

Models maintained robustness across different languages and out-of-sample data.

High-dimensional acoustic features are effective for MCI classification.

Abstract

This study addresses the TAUKADIAL challenge, focusing on the classification of speech from people with Mild Cognitive Impairment (MCI) and neurotypical controls. We conducted three experiments comparing five machine-learning methods: Random Forests, Sparse Logistic Regression, k-Nearest Neighbors, Sparse Support Vector Machine, and Decision Tree, utilizing 1076 acoustic features automatically extracted using openSMILE. In Experiment 1, the entire dataset was used to train a language-agnostic model. Experiment 2 introduced a language detection step, leading to separate model training for each language. Experiment 3 further enhanced the language-agnostic model from Experiment 1, with a specific focus on evaluating the robustness of the models using out-of-sample test data. Across all three experiments, results consistently favored models capable of handling high-dimensional data, such as Random Forest and Sparse Logistic Regression, in classifying speech from MCI and controls.