Natural language processing-based classification of early Alzheimer's disease from connected speech

IF 11.1 1区医学 Q1 CLINICAL NEUROLOGY Alzheimer's & Dementia Pub Date : 2025-01-27 DOI:10.1002/alz.14530

Helena Balabin, Bastiaan Tamm, Laure Spruyt, Nathalie Dusart, Ines Kabouche, Ella Eycken, Kevin Statz, Steffi De Meyer, Hugo Van Hamme, Patrick Dupont, Marie-Francine Moens, Rik Vandenberghe

{"title":"Natural language processing-based classification of early Alzheimer's disease from connected speech","authors":"Helena Balabin, Bastiaan Tamm, Laure Spruyt, Nathalie Dusart, Ines Kabouche, Ella Eycken, Kevin Statz, Steffi De Meyer, Hugo Van Hamme, Patrick Dupont, Marie-Francine Moens, Rik Vandenberghe","doi":"10.1002/alz.14530","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> INTRODUCTION</h3>\n \n <p>The automated analysis of connected speech using natural language processing (NLP) emerges as a possible biomarker for Alzheimer's disease (AD). However, it remains unclear which types of connected speech are most sensitive and specific for the detection of AD.</p>\n </section>\n \n <section>\n \n <h3> METHODS</h3>\n \n <p>We applied a language model to automatically transcribed connected speech from 114 Flemish-speaking individuals to first distinguish early AD patients from amyloid negative cognitively unimpaired (CU) and then amyloid negative from amyloid positive CU individuals using five different types of connected speech.</p>\n </section>\n \n <section>\n \n <h3> RESULTS</h3>\n \n <p>The language model was able to distinguish between amyloid negative CU subjects and AD patients with up to 81.9% sensitivity and 81.8% specificity. Discrimination between amyloid positive and negative CU individuals was less accurate, with up to 82.7% sensitivity and 74.0% specificity. Moreover, autobiographical interviews consistently outperformed scene descriptions.</p>\n </section>\n \n <section>\n \n <h3> DISCUSSION</h3>\n \n <p>Our findings highlight the value of autobiographical interviews for the automated analysis of connecting speech.</p>\n </section>\n \n <section>\n \n <h3> Highlights</h3>\n \n <div>\n <ul>\n \n <li>This study compared five types of connected speech for the detection of early Alzheimer's disease (AD).</li>\n \n <li>Autobiographical interviews yielded a higher specificity than scene descriptions.</li>\n \n <li>A preceding clinical AD classification task can refine the performance of amyloid status classification in cognitively healthy individuals.</li>\n </ul>\n </div>\n </section>\n </div>","PeriodicalId":7471,"journal":{"name":"Alzheimer's & Dementia","volume":"21 2","pages":""},"PeriodicalIF":11.1000,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/alz.14530","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Alzheimer's & Dementia","FirstCategoryId":"3","ListUrlMain":"https://alz-journals.onlinelibrary.wiley.com/doi/10.1002/alz.14530","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

INTRODUCTION

The automated analysis of connected speech using natural language processing (NLP) emerges as a possible biomarker for Alzheimer's disease (AD). However, it remains unclear which types of connected speech are most sensitive and specific for the detection of AD.

METHODS

We applied a language model to automatically transcribed connected speech from 114 Flemish-speaking individuals to first distinguish early AD patients from amyloid negative cognitively unimpaired (CU) and then amyloid negative from amyloid positive CU individuals using five different types of connected speech.

RESULTS

The language model was able to distinguish between amyloid negative CU subjects and AD patients with up to 81.9% sensitivity and 81.8% specificity. Discrimination between amyloid positive and negative CU individuals was less accurate, with up to 82.7% sensitivity and 74.0% specificity. Moreover, autobiographical interviews consistently outperformed scene descriptions.

DISCUSSION

Our findings highlight the value of autobiographical interviews for the automated analysis of connecting speech.

Highlights

This study compared five types of connected speech for the detection of early Alzheimer's disease (AD).
Autobiographical interviews yielded a higher specificity than scene descriptions.
A preceding clinical AD classification task can refine the performance of amyloid status classification in cognitively healthy individuals.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于自然语言处理的连接言语早期阿尔茨海默病分类

使用自然语言处理（NLP）对连接语音进行自动分析，可能成为阿尔茨海默病（AD）的生物标志物。然而，目前尚不清楚哪种类型的连接语音对AD的检测最敏感和特异性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Alzheimer's & Dementia 医学-临床神经学

CiteScore

14.50

自引率

5.00%

发文量

299

审稿时长

3 months

期刊介绍： Alzheimer's & Dementia is a peer-reviewed journal that aims to bridge knowledge gaps in dementia research by covering the entire spectrum, from basic science to clinical trials to social and behavioral investigations. It provides a platform for rapid communication of new findings and ideas, optimal translation of research into practical applications, increasing knowledge across diverse disciplines for early detection, diagnosis, and intervention, and identifying promising new research directions. In July 2008, Alzheimer's & Dementia was accepted for indexing by MEDLINE, recognizing its scientific merit and contribution to Alzheimer's research.