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

TL;DR

This study evaluates explainable machine learning models using speech biomarkers to screen for cognitive impairment and Alzheimer's disease, demonstrating promising accuracy and potential for at-home monitoring and early intervention.

Contribution

It introduces a validated, interpretable ML approach for cognitive impairment screening using linguistic features from speech, with generalisability to real-world data and clinical utility for triage.

Findings

Random Forest achieves 69.4% sensitivity and 83.3% specificity on benchmark data.

Model sensitivity is 70.0% with 52.5% specificity on pilot in-residence data.

Linguistic features include pronoun use, disfluency, and lexical diversity, associated with ADRD.

Abstract

Timely and accurate assessment of cognitive impairment remains a major unmet need. Speech biomarkers offer a scalable, non-invasive, cost-effective solution for automated screening. However, the clinical utility of machine learning (ML) remains limited by interpretability and generalisability to real-world speech datasets. We evaluate explainable ML for screening of Alzheimer's disease and related dementias (ADRD) and severity prediction using benchmark DementiaBank speech (N = 291, 64% female, 69.8 (SD = 8.6) years). We validate generalisability on pilot data collected in-residence (N = 22, 59% female, 76.2 (SD = 8.0) years). To enhance clinical utility, we stratify risk for actionable triage and assess linguistic feature importance. We show that a Random Forest trained on linguistic features for ADRD detection achieves a mean sensitivity of 69.4% (95% confidence interval (CI) = 66.4-72.5) and specificity of 83.3% (78.0-88.7). On pilot data, this model yields a mean sensitivity of 70.0% (58.0-82.0) and specificity of 52.5% (39.3-65.7). For prediction of Mini-Mental State Examination (MMSE) scores, a Random Forest Regressor achieves 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. Risk stratification improves specificity by 13% on the test set, offering a pathway for clinical triage. Linguistic features associated with ADRD include increased use of pronouns and adverbs, greater disfluency, reduced analytical thinking, lower lexical diversity, and fewer words that reflect a psychological state of completion. Our predictive modelling shows promise for integration with conversational technology at home to monitor cognitive health and triage higher-risk individuals, enabling early screening and intervention.