CoChat

Predicting dementia from spontaneous speech using large language models

Open access
Agbavor, Felix, Liang, Hualou · 2022 · PLOS Digital Health

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pdig.0000168

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Schematic showing two different feature representations that are derived from speech. A. The acoustic features are engineered to capture the acoustic characteristics of speech and therefore the pathological speech behavior. B. The linguistic features, represented as text embeddings, are derived from the transcribed text. Central to our proposed approach is the GPT-3 based text embeddings (shaded), which entail meaningful vector representations that can capture lexical, syntactic, and semantic properties for dementia classification.
Fig 1 Schematic showing two different feature representations that are derived from speech. A. The acoustic features are engineered to capture the acoustic characteristics of speech and therefore the pathological speech behavior. B. The linguistic features, represented as text embeddings, are derived from the transcribed text. Central to our proposed approach is the GPT-3 based text embeddings (shaded), which entail meaningful vector representations that can capture lexical, syntactic, and semantic properties for dementia classification.CC BY · PubMed Central
Fig 2 ROC curves, along with the averaged AUC scores and standard deviations, obtained by the 10-fold CV for the best acoustic, Ada and Babbage embedding models.
Fig 2 ROC curves, along with the averaged AUC scores and standard deviations, obtained by the 10-fold CV for the best acoustic, Ada and Babbage embedding models.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 39 references

Research works printed but not linked: 9

  1. H Goodglass, 2001, BDAE: The Boston Diagnostic Aphasia Examination.
  2. S Luz, 2020, Alzheimer’s Dementia Recognition through Spontaneous Speech: The ADReSS Challenge [Internet]., arXiv
  3. SO Orimaye, 2015, Learning Linguistic Biomarkers for Predicting Mild Cognitive Impairment using Compound Skip-grams [Internet]., arXiv
  4. Y Aytar, 2016, SoundNet: Learning Sound Representations from Unlabeled Video. In: Advances in Neural Information Processing Systems [Internet].
  5. A Balagopalan, 2020, To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer’s Disease Detection [Internet]., arXiv
  6. J Devlin, 2019, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [Internet]., arXiv
  7. A Radford, 2018, Improving language understanding by generative pre-training
  8. T Brown, 2020, Language Models are Few-Shot Learners. In: Advances in Neural Information Processing Systems [Internet]., 1877
  9. ME Peters, 2018, Deep contextualized word representations [Internet]., arXiv

Cited by

See all 151

Metadata

Authors
Agbavor, F., & Liang, H.
Affiliations
Drexel University (US)
Corresponding author
Liang, Hualou
Venue
PLOS Digital Health
Published
2022-12-22
Volume
1
Issue
12
Pages
e0000168
ISSN
2767-3170 (ISSN-L)
OpenAlex
W4312091558
Cited by
147
References
34
Citations by year
2026: 39 · 2025: 47 · 2024: 42 · 2023: 17 · 2022: 2
FWCI
17.60
Type
journal article
Language
en
Open access
Locations
  • PLOS Digital Health (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • Drexel University
  • National Institutes of Health (AG05133)
  • National Institute on Aging (P50AG005133)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
dementia prediction, Alzheimer's disease, spontaneous speech, GPT-3, text embeddings, language impairment, early diagnosis, speech biomarkers, natural language processing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Predicting dementia from spontaneous speech using large language models. https://app.cochat.ai/papers/10.1371/journal.pdig.0000168
The paper
Agbavor, F., & Liang, H. (2022). Predicting dementia from spontaneous speech using large language models. PLOS Digital Health. https://doi.org/10.1371/journal.pdig.0000168

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.