Files and links (1)
Published, Version of Record (VoR)CC BY V4.0, Open
Journal article
Predicting dementia from spontaneous speech using large language models
PLOS digital health, v 1(12), e0000168
22 Dec 2022
PMID: 36812634
Abstract
Language impairment is an important biomarker of neurodegenerative disorders such as Alzheimer's disease (AD). Artificial intelligence (AI), particularly natural language processing (NLP), has recently been increasingly used for early prediction of AD through speech. Yet, relatively few studies exist on using large language models, especially GPT-3, to aid in the early diagnosis of dementia. In this work, we show for the first time that GPT-3 can be utilized to predict dementia from spontaneous speech. Specifically, we leverage the vast semantic knowledge encoded in the GPT-3 model to generate text embedding, a vector representation of the transcribed text from speech, that captures the semantic meaning of the input. We demonstrate that the text embedding can be reliably used to (1) distinguish individuals with AD from healthy controls, and (2) infer the subject's cognitive testing score, both solely based on speech data. We further show that text embedding considerably outperforms the conventional acoustic feature-based approach and even performs competitively with prevailing fine-tuned models. Together, our results suggest that GPT-3 based text embedding is a viable approach for AD assessment directly from speech and has the potential to improve early diagnosis of dementia.
Metrics
13 Record Views
73 citations in Scopus
Details
- Title
- Predicting dementia from spontaneous speech using large language models
- Creators
- Felix Agbavor - Drexel University, School of Biomedical Engineering, Science, and Health SystemsHualou Liang - Drexel University, School of Biomedical Engineering, Science, and Health Systems
- Publication Details
- PLOS digital health, v 1(12), e0000168
- Publisher
- Public LIbrary of Science (PLOS)
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Scopus ID
- 2-s2.0-85146810243
- Other Identifier
- 991021864310804721