Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug;20(8):5262-5270.
doi: 10.1002/alz.13886. Epub 2024 Jun 25.

Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models

Samad Amini  1 , Boran Hao  1 , Jingmei Yang  1 , Cody Karjadi  2 , Vijaya B Kolachalama  3   4   5 , Rhoda Au  2   6 , Ioannis C Paschalidis  1   4
Affiliations

Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models

Samad Amini et al. Alzheimers Dement. 2024 Aug.

Abstract

Introduction: Identification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials.

Methods: We applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews of n = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases.

Results: Our best models, which used features generated from speech data, as well as age, sex, and education level, achieved an accuracy of 78.5% and a sensitivity of 81.1% to predict MCI-to-AD progression within 6 years.

Discussion: The proposed method offers a fully automated procedure, providing an opportunity to develop an inexpensive, broadly accessible, and easy-to-administer screening tool for MCI-to-AD progression prediction, facilitating development of remote assessment.

Highlights: Voice recordings from neuropsychological exams coupled with basic demographics can lead to strong predictive models of progression to dementia from mild cognitive impairment. The study leveraged AI methods for speech recognition and processed the resulting text using language models. The developed AI-powered pipeline can lead to fully automated assessment that could enable remote and cost-effective screening and prognosis for Alzehimer's disease.

Keywords: Alzheimer's disease prognosis; Framingham Heart Study; natural language processing; neuropsychological test.

PubMed Disclaimer

Conflict of interest statement

Rhoda Au is a scientific advisor to Signant Health and NovoNordisk and consultant to Biogen and the Davos Alzheimer's Collaborative. She receives funding from the National Institute on Aging (AG072654, AG062109, AG068753) and has also been supported through awards from the American Heart Association, the Alzheimer's Drug Discovery Foundation, Alzheimer's Disease Data Initiative, and Gates Ventures. Vijaya B. Kolachalama has received support from the Karen Toffler Charitable Trust; Johnson & Johnson (through the Boston University Lung Cancer Alliance); the NIH under grants RF1‐AG062109, R01‐HL159620, R43‐DK134273, and R21‐CA253498; the American Heart Association under grant 20SFRN35460031; and serves as a consultant to AstraZeneca. Both R. Au and V. B. Kolachalama state no conflicts of interest with the present work. There is no declaration from other authors. Author disclosures are available in the supporting information.

Figures

FIGURE 1
FIGURE 1
Number of MCI patients transitioning to AD annually over 6 years. AD, Alzheimer's disease; MCI, mild cognitive impairment.
FIGURE 2
FIGURE 2
Automated pipeline for converting raw speech into structured data (as an example, the box on the right side contains a short note from each subtest highlighted in blue ink).
FIGURE 3
FIGURE 3
Automated pipeline for Alzheimer's disease prediction from a neuropsychological test interview.
FIGURE 4
FIGURE 4
Performance error analysis for health factors. A, Performance error (1‐AUC) after removing each feature at a time. B, Results of AUC for an arbitrary number of most important features. AUC, area under the receiver operating characteristic curve; BMI, body mass index; LDL, low‐density lipoprotein.
FIGURE 5
FIGURE 5
Logistic regression coefficients of the text features and demographics used in the proposed method. Demographics includes age, sex, and education. BNT, Boston Naming Test; CDT, Clock Drawing Test; DEMO, part of the interview related to demographic information; OTHER, similarity tests; TAS, transcript average score; WAIS, Wechsler Adult Intelligence Scale.
See this image and copyright information in PMC

References

    1. Mitchell AJ, Shiri‐Feshki M. Rate of progression of mild cognitive impairment to dementia–meta‐analysis of 41 robust inception cohort studies. Acta Psychiatr Scand. 2009;119:252‐265. - PubMed
    1. Liu S, Cao Y, Liu J, Ding X, Coyle D, Initiative ADN. A novelty detection approach to effectively predict conversion from mild cognitive impairment to Alzheimer's disease. Int J Mach Learn Cybern. 2023;14:213‐228.
    1. Pereira T, Ferreira FL, Cardoso S, et al. Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer's disease: a feature selection ensemble combining stability and predictability. BMC Med Inform Decis Mak. 2018;18:1‐20. - PMC - PubMed
    1. Scheltens P, Blennow K, Breteler M, et al. Alzheimer's disease. Lancet (Lond Engl). 2016;388:505‐517. - PubMed
    1. Turner RS, Stubbs T, Davies DA, Albensi BC. Potential new approaches for diagnosis of alzheimer's disease and related dementias. Front Neurol. 2020;11:496. - PMC - PubMed

Publication types