Spoken Language Biomarkers for Detecting Cognitive Impairment

TL;DR

This study presents an automated speech analysis system that combines audio and text features to effectively detect cognitive impairment, outperforming demographic models with high accuracy.

Contribution

The paper introduces a novel combined audio-text feature system for cognitive impairment detection, demonstrating superior performance over demographic models.

Findings

Combined audio and text features achieved 0.92 AUC.

Decreased pitch and jitter linked to impairment.

Shorter speech segments and question responses associated with impairment.

Abstract

In this study we developed an automated system that evaluates speech and language features from audio recordings of neuropsychological examinations of 92 subjects in the Framingham Heart Study. A total of 265 features were used in an elastic-net regularized binomial logistic regression model to classify the presence of cognitive impairment, and to select the most predictive features. We compared performance with a demographic model from 6,258 subjects in the greater study cohort (0.79 AUC), and found that a system that incorporated both audio and text features performed the best (0.92 AUC), with a True Positive Rate of 29% (at 0% False Positive Rate) and a good model fit (Hosmer-Lemeshow test > 0.05). We also found that decreasing pitch and jitter, shorter segments of speech, and responses phrased as questions were positively associated with cognitive impairment.