EUVIMEDOdkrijte EUVIMED
BeobachtungsstudieQuerschnittstudieOpen access

Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study

Maryam Tavakoli iD, Mehrdad Dadgostar iD, Jordan R Green iD, David H Salat iD, Steven E Arnold iD, Kathryn P Connaghan iD, Brian Richburg iD, Nelson V Barnett iD, Mariam Tkeshelashvili iD, Marziye Eshghi iD

JMIR Formative Research · 2026

DOI: 10.2196/89830 ↗

At a glance

Beobachtungsstudie in JMIR Formative Research, 2026. Written by Maryam Tavakoli and 9 co-authors. Institution: Mass General Brigham University of Health Professions, Charlestown, MA, United States. Major MEDLINE topics: Apolipoprotein E4, Heterozygote, Speech Acoustics, Cognition. 48 references. The full text is freely available in PubMed Central.

PovzetekSubjectsBibliografski podatkiCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

Apolipoprotein E4HeterozygoteSpeech AcousticsCognitionHumansCross-Sectional StudiesAgedFemaleMaleAdultMiddle AgedAged, 80 and overSpeech

Author keywords

APOE-ε4 genotypeAlzheimer diseaseapolipoprotein E ε4eGeMAPSextended Geneva Minimalistic Acoustic Parameter Setgenetic risk factorspeech acousticsspeech biomarkers

Substances

Apolipoprotein E4

Authors and institutions

  • Mass General Brigham University of Health Professions, Charlestown, MA, United States.
  • Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, United States.
  • Speech and Hearing Bioscience and Technology, Harvard University, Boston, MA, United States.
  • Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.
  • Neuroimaging Research for Veterans Center, VA Boston Healthcare System, Jamaica Plain, MA, United States.
  • Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.

ORCID profiles: Maryam Tavakoli, Mehrdad Dadgostar, Jordan R Green, David H Salat, Steven E Arnold, Kathryn P Connaghan, Brian Richburg, Nelson V Barnett, Mariam Tkeshelashvili, Marziye Eshghi

Cite

APA

Tavakoli, M., Dadgostar, M., Green, J. R., Salat, D. H., Arnold, S. E., Connaghan, K. P., Richburg, B., Barnett, N. V., Tkeshelashvili, M., & Eshghi, M. (2026). Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study. JMIR Formative Research. https://doi.org/10.2196/89830

Vancouver

Tavakoli M, Dadgostar M, Green JR, Salat DH, Arnold SE, Connaghan KP, et al. Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study. JMIR Formative Research. 2026. doi:10.2196/89830

BibTeX
@article{Tavakoli2026,
  author = {Tavakoli, Maryam and Dadgostar, Mehrdad and Green, Jordan R and Salat, David H and Arnold, Steven E and Connaghan, Kathryn P and Richburg, Brian and Barnett, Nelson V and Tkeshelashvili, Mariam and Eshghi, Marziye},
  title = {Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study},
  journal = {JMIR Formative Research},
  year = {2026},
  doi = {10.2196/89830}
}
Start for free →