Evaluating Spoken Language as a Biomarker for Automated Screening of Cognitive Impairment

2025-01-30

AI Summary

Early noninvasive screening for Alzheimer’s disease and related dementias (ADRD) remains hampered by low sensitivity, poor model interpretability, and limited suitability for home-based deployment. To address these challenges, we propose an interpretable machine learning framework integrating risk stratification with linguistic feature importance analysis. Leveraging natural speech, the framework extracts linguistically grounded features—including part-of-speech distributions, fluency metrics, and semantic diversity—and employs random forest classifiers and regressors. Cross-domain validation on DementiaBank and prospectively collected clinical data yields 69.4% sensitivity and 83.3% specificity for ADRD binary classification in the primary cohort; in real-world home settings, sensitivity reaches 70.0% and specificity 52.5%. For MMSE score prediction, mean absolute error ranges from 3.3 to 3.7 points. To our knowledge, this is the first framework to translate speech-derived biomarkers into a clinically actionable and home-deployable tool, substantially enhancing both model transparency and practical utility.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Timely and accurate assessment of cognitive impairment is a major unmet need in populations at risk. Alterations in speech and language can be early predictors of Alzheimer's disease and related dementias (ADRD) before clinical signs of neurodegeneration. Voice biomarkers offer a scalable and non-invasive solution for automated screening. However, the clinical applicability of machine learning (ML) remains limited by challenges in generalisability, interpretability, and access to patient data to train clinically applicable predictive models. Using DementiaBank recordings (N=291, 64% female), we evaluated ML techniques for ADRD screening and severity prediction from spoken language. We validated model generalisability with pilot data collected in-residence from older adults (N=22, 59% female). Risk stratification and linguistic feature importance analysis enhanced the interpretability and clinical utility of predictions. For ADRD classification, a Random Forest applied to lexical features achieved a mean sensitivity of 69.4% (95% confidence interval (CI) = 66.4-72.5) and specificity of 83.3% (78.0-88.7). On real-world pilot data, this model achieved a mean sensitivity of 70.0% (58.0-82.0) and specificity of 52.5% (39.3-65.7). For severity prediction using Mini-Mental State Examination (MMSE) scores, a Random Forest Regressor achieved a mean absolute MMSE error of 3.7 (3.7-3.8), with comparable performance of 3.3 (3.1-3.5) on pilot data. Linguistic features associated with higher ADRD risk included increased use of pronouns and adverbs, greater disfluency, reduced analytical thinking, lower lexical diversity and fewer words reflecting a psychological state of completion. Our interpretable predictive modelling offers a novel approach for in-home integration with conversational AI to monitor cognitive health and triage higher-risk individuals, enabling earlier detection and intervention.

Problem

• Cognitive Impairment Detection
• Alzheimer's Disease Diagnosis
• Early Stage Dementia

Innovation

• Machine Learning
• Early Detection of Dementia
• Random Forest Algorithm