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

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.

FIGURE 1

Number of MCI patients transitioning to AD annually over 6 years. AD, Alzheimer's disease; MCI, mild cognitive impairment.

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

Automated pipeline for Alzheimer's disease prediction from a neuropsychological test interview.

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

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.