CoChat

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

Open access
de la Fuente Garcia, Sofia, Ritchie, Craig W., Luz, Saturnino · 2020 · Journal of Alzheimer's Disease

The DOI matches its Crossref record; 125 of the 127 references it cites were found in a registry or an index; 5 of the 167 sources its claims cite were checked for support.

Abstract

Background: Language is a valuable source of clinical information in Alzheimer’s disease, as it declines concurrently with neurodegeneration. Consequently, speech and language data have been extensively studied in connection with its diagnosis. Objective: Firstly, to summarize the existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease. Secondly, to detail current research procedures, highlight their limitations, and suggest strategies to address them. Methods: Systematic review of original research between 2000 and 2019, registered in PROSPERO (reference CRD42018116606). An interdisciplinary search covered six databases on engineering (ACM and IEEE), psychology (PsycINFO), medicine (PubMed and Embase), and Web of Science. Bibliographies of relevant papers were screened until December 2019. Results: From 3,654 search results, 51 articles were selected against the eligibility criteria. Four tables summarize their findings: study details (aim, population, interventions, comparisons, methods, and outcomes), data details (size, type, modalities, annotation, balance, availability, and language of study), methodology (pre-processing, feature generation, machine learning, evaluation, and results), and clinical applicability (research implications, clinical potential, risk of bias, and strengths/limitations). Conclusion: Promising results are reported across nearly all 51 studies, but very few have been implemented in clinical research or practice. The main limitations of the field are poor standardization, limited comparability of results, and a degree of disconnect between study aims and clinical applications. Active attempts to close these gaps will support translation of future research into clinical practice.

Overview

CoChat Summary

## TL;DR

This systematic review synthesized 51 studies on AI, speech, and language processing for Alzheimer’s disease (AD) monitoring from 2000–2019 and found promising performance but very limited clinical translation. The authors argue the field is held back by poor standardization, small and imbalanced datasets, and weak comparability across studies.

## Key findings

  • The search yielded 3,654 records in total, and 51 articles met eligibility criteria for the review.
  • Across the reviewed literature, 41 of 51 papers focused on distinguishing cognitive impairment categories, while only 7 attempted three-way or four-way classification, 2 examined longitudinal cognitive change, and 1 used cluster analysis to describe discourse patterns.
  • The review reports that 31% of studies trained on fewer than 50 participants, only 27% had 100 or more participants, and just 6 studies had 100+ participants/speech samples in each experimental group; all six used the Pitt Corpus.
  • Reported performance ranged widely: some classifiers were 50% or lower, while others exceeded 90% accuracy; examples highlighted include 60% to 93.79% accuracy in one small, imbalanced study, 78.7% accuracy in a larger balanced dataset, 85.4% accuracy on the same dataset using text features, and 86.6% as the state-of-the-art accuracy for dialogue data.

## Methods

  • Systematic review of original research from 2000–2019, registered in PROSPERO (CRD42018116606).
  • Searched six databases: ACM, IEEE, PsycINFO, PubMed, Embase, and Web of Science, plus bibliographies and citation tracking through December 2019.
  • Two reviewers independently screened records and extracted data using four tables covering study details, data details, methodology, and clinical applicability; synthesis was narrative, with no meta-analysis.

## Limitations

  • The paper’s stated limitations of the field are poor standardization, limited comparability of results, and a disconnect between study aims and clinical applications.
  • The review itself notes that most studies use relatively small datasets, class imbalance is common, and many studies lack held-out testing or external validation, which limits generalizability; this is stated in the paper and is also evident from the reporting.
  • A further limitation evident from the text is that many studies report incomplete pre-processing and feature-generation details, making replication difficult; the authors explicitly say these procedures are often not fully described.

Model-written summary of a shortened version of the paper’s full text (it is longer than we read). Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3233/jad-200888

Cites

125 of 125 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig.1 Number of relevant records per year (2000–2019).
Fig.1 Number of relevant records per year (2000–2019).CC BY-NC · PubMed Central
Fig.2 Screening and selection procedure, following guidelines provided by PRISMA [19].
Fig.2 Screening and selection procedure, following guidelines provided by PRISMA [19].CC BY-NC · PubMed Central

Verification

Claims the paper makes

5 Valid · 2 Not valid · 70 Not checked · 122 Own results and interpretations

108 more claims

Create a free account to see all 199 claims and to verify the 162 references still open.

See all claims — free account
  • It may state two separate claims as one. 57
  • Probably not a substantial claim. 39
  • The quote only partly states this claim. 1

Create a free account to see these claims.

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?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

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

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Research works printed but not linked: 4

  1. World Health Organization, 2013, Mental health action plan 2013-2020, WHO Library Cataloguing-in-Publication Data, 1
  2. Joanette, 1995, Évaluation neuropsychologique et profils cognitifs des démences de type Alzheimer: dissociations transversales et longitudinales, Neuropsychologie Clinique des Démences, 91
  3. Bayles, 1993, ABCD: Arizona battery for communication disorders of dementia
  4. Darley, 1975, Motor speech disorders

Cited by

See all 271

Metadata

Authors
de la Fuente Garcia, S., Ritchie, C. W., & Luz, S.
Affiliations
  • Usher Institute, Edinburgh Medical School, The University of Edinburgh, Scotland, UK
  • University of Edinburgh (GB)
Venue
Journal of Alzheimer's Disease
Published
2020-12-08
Volume
78
Issue
4
Pages
1547-1574
ISSN
  • 1387-2877 (ISSN-L)
  • 1875-8908
OpenAlex
W3093156670
Cited by
5
References
127
Citations by year
2025: 1 · 2023: 1 · 2022: 1 · 2021: 2
FWCI
0.17
Type
journal article
Language
en
Open access
Locations
  • Journal of Alzheimer s Disease (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
Keywords
Alzheimer's disease, speech analysis
MeSH terms
Machine Learning, Alzheimer Disease, Artificial Intelligence, Humans, Natural Language Processing, Speech, Disease Progression, Cognitive Dysfunction

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).

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

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.