Automated Extraction of Spatio-Semantic Graphs for Identifying Cognitive Impairment

TL;DR

This paper introduces an automated method to extract spatio-semantic graphs from picture descriptions, enabling efficient analysis of cognitive impairment without manual tagging, and demonstrating comparable or better differentiation between impaired and unimpaired speakers.

Contribution

The paper presents a novel automated approach for extracting spatio-semantic graphs from transcripts, eliminating manual content tagging and improving clinical assessment capabilities.

Findings

Automated graphs effectively differentiate cognitive impairment levels.

Features from automated graphs match or surpass manual methods in group differentiation.

The approach facilitates scalable, non-invasive cognitive-linguistic analysis.

Abstract

Existing methods for analyzing linguistic content from picture descriptions for assessment of cognitive-linguistic impairment often overlook the participant's visual narrative path, which typically requires eye tracking to assess. Spatio-semantic graphs are a useful tool for analyzing this narrative path from transcripts alone, however they are limited by the need for manual tagging of content information units (CIUs). In this paper, we propose an automated approach for estimation of spatio-semantic graphs (via automated extraction of CIUs) from the Cookie Theft picture commonly used in cognitive-linguistic analyses. The method enables the automatic characterization of the visual semantic path during picture description. Experiments demonstrate that the automatic spatio-semantic graphs effectively differentiate between cognitively impaired and unimpaired speakers. Statistical analyses reveal that the features derived by the automated method produce comparable results to the manual method, with even greater group differences between clinical groups of interest. These results highlight the potential of the automated approach for extracting spatio-semantic features in developing clinical speech models for cognitive impairment assessment.