Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study.
6 affiliations
- 1Mass General Brigham University of Health Professions, Charlestown, MA, United States.
- 2Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, United States.
- 3Speech and Hearing Bioscience and Technology, Harvard University, Boston, MA, United States.
- 4Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.
- 5Neuroimaging Research for Veterans Center, VA Boston Healthcare System, Jamaica Plain, MA, United States.
- 6Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.
Abstract
Background
Apolipoprotein E ε4 (APOE-ε4), the strongest genetic risk factor for late-onset Alzheimer disease (AD), is associated with early neuromotor vulnerability that may precede measurable cognitive decline. Because speech integrates fine neuromotor processes, acoustic analysis could offer a sensitive, noninvasive marker of preclinical effects.Objective
This study aims to determine if speech acoustics distinguish cognitively normal APOE-ε4 carriers from noncarriers, and to assess which speech tasks provide optimal classification performance.Methods
In this cross-sectional observational study, 80 cognitively normal adults aged 41 to 89 years (22 APOE-ε4 carriers and 58 noncarriers) completed sustained phonation, oral diadochokinetic syllable repetition, passage reading, and spontaneous-speech tasks. Speech samples were collected remotely using participants' personal devices and processed to extract 88 acoustic features from the extended Geneva Minimalistic Acoustic Parameter Set. Task-specific random forest classifiers were developed to distinguish APOE-ε4 carriers from noncarriers. A genetic algorithm was used to select informative features, and model performance was evaluated using leave-one-participant-out cross-validation. Performance metrics included balanced accuracy, accuracy, precision, sensitivity, specificity, F₁-score, and receiver operating characteristic area under the curve (ROC-AUC).Results
Spontaneous speech produced the strongest classification performance, with balanced accuracy of 0.84, accuracy of 0.89, sensitivity of 0.73, specificity of 0.95, F₁-score of 0.78, and ROC-AUC of 0.75. Performance was lower for sustained phonation (F₁-score=0.69), diadochokinetic syllable repetition (F₁-score =0.70 for /ba/ and 0.64 for /pa/), and passage reading (F₁-score=0.61). Combining recordings across tasks reduced performance (F₁-score=0.53), indicating that task-specific acoustic patterns were more informative than pooled data.Conclusions
Automated analysis of task-specific acoustic speech features, particularly spontaneous speech, internally distinguished cognitively normal APOE-ε4 carriers from noncarriers. These findings support further validation of speech acoustics as a low-burden digital biomarker of preclinical AD risk and suggest that spontaneous-speech tasks may be especially well suited for future remote and longitudinal assessment.
Related
- Practice Effects on Repeated Self-Administered Digital Cognitive Assessments in Cognitively Intact Older Adults from the Framingham Heart Study: Longitudinal Observational Study.
- Cognitively engaging sedentary activities are associated with better cognitive function in middle-aged adults: a cross-sectional study using the 1970 British Cohort Study.
- Identification and operative vs. conservative vs. no treatment trial of breastfeeding-impeding lingual frenulum in newborn infants (LINNE): protocol for a randomized controlled trial (RCT) embedded in a prospective observational cohort study in Northern Finland
- Knowledge, Attitudes, Religiosity, and Reproductive Genetic Carrier Screening: A Cross-Sectional Study.
- Promoting the Mediterranean Diet in the Workplace: An Observational Cross-Sectional Study
BibTeX
@article{tavakoli2026remote,
title = {{Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study.}},
author = {Maryam Tavakoli and Mehrdad Dadgostar and Jordan R Green and David H Salat and Steven E Arnold and Kathryn P Connaghan and Brian Richburg and Nelson V Barnett and Mariam Tkeshelashvili and Marziye Eshghi},
journal = {JMIR formative research},
year = {2026},
month = oct,
doi = {10.2196/89830},
url = {https://europepmc.org/article/MED/42849896},
note = {CC BY},
}
RIS
TY - JOUR
TI - Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study.
AU - Maryam Tavakoli
AU - Mehrdad Dadgostar
AU - Jordan R Green
AU - David H Salat
AU - Steven E Arnold
AU - Kathryn P Connaghan
AU - Brian Richburg
AU - Nelson V Barnett
AU - Mariam Tkeshelashvili
AU - Marziye Eshghi
PY - 2026
DA - 2026/10/08
JO - JMIR formative research
DO - 10.2196/89830
UR - https://europepmc.org/article/MED/42849896
AB - Background Apolipoprotein E ε4 (APOE-ε4), the strongest genetic risk factor for late-onset Alzheimer disease (AD), is associated with early neuromotor vulnerability that may precede measurable cognitive decline. Because speech integrates fine neuromotor processes, acoustic analysis could offer a sensitive, noninvasive marker of preclinical effects.Objective This study aims to determine if speech acoustics distinguish cognitively normal APOE-ε4 carriers from noncarriers, and to assess which speech tasks provide optimal classification performance.Methods In this cross-sectional observational study, 80 cognitively normal adults aged 41 to 89 years (22 APOE-ε4 carriers and 58 noncarriers) completed sustained phonation, oral diadochokinetic syllable repetition, passage reading, and spontaneous-speech tasks. Speech samples were collected remotely using participants' personal devices and processed to extract 88 acoustic features from the extended Geneva Minimalistic Acoustic Parameter Set. Task-specific random forest classifiers were developed to distinguish APOE-ε4 carriers from noncarriers. A genetic algorithm was used to select informative features, and model performance was evaluated using leave-one-participant-out cross-validation. Performance metrics included balanced accuracy, accuracy, precision, sensitivity, specificity, F₁-score, and receiver operating characteristic area under the curve (ROC-AUC).Results Spontaneous speech produced the strongest classification performance, with balanced accuracy of 0.84, accuracy of 0.89, sensitivity of 0.73, specificity of 0.95, F₁-score of 0.78, and ROC-AUC of 0.75. Performance was lower for sustained phonation (F₁-score=0.69), diadochokinetic syllable repetition (F₁-score =0.70 for /ba/ and 0.64 for /pa/), and passage reading (F₁-score=0.61). Combining recordings across tasks reduced performance (F₁-score=0.53), indicating that task-specific acoustic patterns were more informative than pooled data.Conclusions Automated analysis of task-specific acoustic speech features, particularly spontaneous speech, internally distinguished cognitively normal APOE-ε4 carriers from noncarriers. These findings support further validation of speech acoustics as a low-burden digital biomarker of preclinical AD risk and suggest that spontaneous-speech tasks may be especially well suited for future remote and longitudinal assessment.
SN - 2561-326X
ER -