Detecting Alzheimer's Disease Using Natural Language Processing of Referential Communication Task Transcripts

Ziming Liu; Eun Jin Paek; Si On Yoon; Devin Casenhiser; Wenjun Zhou; Xiaopeng Zhao

doi:10.3233/JAD-215137

Back

Detecting Alzheimer's Disease Using Natural Language Processing of Referential Communication Task Transcripts

Journal article

Peer reviewed

Detecting Alzheimer's Disease Using Natural Language Processing of Referential Communication Task Transcripts

Ziming Liu, Eun Jin Paek, Si On Yoon, Devin Casenhiser, Wenjun Zhou and Xiaopeng Zhao

Journal of Alzheimer's disease, Vol.86(3), pp.1385-1398

2022

DOI: 10.3233/JAD-215137

PMID: 35213368

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/12233998View

Open Access

Abstract

People with Alzheimer's disease (AD) often demonstrate difficulties in discourse production. Referential communication tasks (RCTs) are used to examine a speaker's capability to select and verbally code the characteristics of an object in interactive conversation. In this study, we used contextualized word representations from Natural language processing (NLP) to evaluate how well RCTs are able to distinguish between people with AD and cognitively healthy older adults. We adapted machine learning techniques to analyze manually transcribed speech transcripts in an RCT from 28 older adults, including 12 with AD and 16 cognitively healthy older adults. Two approaches were applied to classify these speech transcript samples: 1) using clinically relevant linguistic features, 2) using machine learned representations derived by a state-of-art pretrained NLP transfer learning model, Bidirectional Encoder Representation from Transformer (BERT) based classification model. The results demonstrated the superior performance of AD detection using a designed transfer learning NLP algorithm. Moreover, the analysis showed that transcripts of a single image yielded high accuracies in AD detection. The results indicated that RCT may be useful as a diagnostic tool for AD, and that the task can be simplified to a subset of images without significant sacrifice to diagnostic accuracy, which can make RCT an easier and more practical tool for AD diagnosis. The results also demonstrate the potential of RCT as a tool to better understand cognitive deficits from the perspective of discourse production in people with AD.

Aged

Alzheimer Disease - diagnosis

Alzheimer Disease - psychology

Cognitive Dysfunction - diagnosis

Communication

Humans

Natural Language Processing

Speech

Details

Title: Subtitle: Detecting Alzheimer's Disease Using Natural Language Processing of Referential Communication Task Transcripts
Creators: Ziming Liu - University of Tennessee at Knoxville
Eun Jin Paek - University of Tennessee Health Science Center
Si On Yoon - University of Iowa
Devin Casenhiser - University of Tennessee Health Science Center
Wenjun Zhou - Department of Business Analytics and Statistics, University of Tennessee, Knoxville, TN, USA.
Xiaopeng Zhao - University of Tennessee at Knoxville
Resource Type: Journal article
Publication Details: Journal of Alzheimer's disease, Vol.86(3), pp.1385-1398
DOI: 10.3233/JAD-215137
PMID: 35213368
NLM abbreviation: J Alzheimers Dis
ISSN: 1387-2877
eISSN: 1875-8908
Language: English
Date published: 2022
Academic Unit: Communication Sciences and Disorders
Record Identifier: 9984258743002771

Metrics

23 Record Views

10 Times Cited - Web of Science