Voiceprints of cognitive impairment: analyzing digital voice for early detection of Alzheimer’s and related dementias

Early detection of Alzheimer's disease (AD) is critical yet challenging, particularly in younger individuals. This study leverages artificial intelligence to analyze digital voice recordings from the Craft Story Recall task within the Longitudinal Early-onset AD Study (LEADS) to (1) detect cognitive impairment and (2) differentiate early-onset AD (EOAD) from early onset non-AD cognitive impairment (EOnonAD). Using speech samples from 120 patients and 68 cognitively unimpaired controls, we employed two classification approaches: feature-engineered machine learning and end-to-end deep learning incorporating a Large Language Model. To detect mild cognitive impairment, the feature-engineered model, using acoustic and linguistic features, achieved an AUC of 0.945 on the holdout test set, while the end-to-end model yielded an AUC of 0.988. For differentiating EOAD from EOnonAD, the feature-engineered model achieved an AUC of 0.804, and the end-to-end model yielded an AUC of 0.904 on the holdout set. Explainability analyses revealed reduced linguistic informativeness as a key AD indicator.

Authors

Institutions

Publication Details

Journal
npj Dementia
Published
2025-11-03
DOI
https://doi.org/10.1038/s44400-025-00040-0
Citations
1
Primary Topic
Dementia and Cognitive Impairment Research
Type
article
Field-Weighted Citation Impact
1.47

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Voiceprints of cognitive impairment: analyzing digital voice for early detection of Alzheimer’s and related dementias

Alexandra Touroutoglou, Lea T. Grinberg, Clifford R. Jack, Alireza Atri et al.
1 citations
npj Dementia
Dementia and Cognitive Impairment Research
1.47
article

Voiceprints of cognitive impairment: analyzing digital voice for early detection of Alzheimer’s and related dementias

Alexandra Touroutoglou, Lea T. Grinberg, Clifford R. Jack, Alireza Atri, Angelina J. Polsinelli, Arthur W. Toga, Renaud La Joie, Alexander Taurone, S. J. Wolk, Joel H. Kramer, Joseph C. Masdeu, Erik S. Musiek, Ian Grant, Liana G. Apostolova, Sharon Sha, Erik C. B. Johnson, Jeffrey L. Dage, Prashanthi Vemuri, Melissa E. Murray, Chiadi U. Onyike, Robert Koeppe, Gil Dan Rabinovici, Dustin B. Hammers, Kyle Womack, Laurel Beckett, Emily Rogalskı, Walter A. Kukull, Neguine Rezaii, Malia Rumbaugh, Gregory Scott Day, Kathy L. Newell, Rema Raman, Kelly Nudelman, Bonnie Wong, Ganna Blazhenets, Mario F. Mendez, Ani Eloyan, Bradford Clark Dickerson, Raymond Scott Turner, Neill R. Graff‐Radford, David Jones, David Clark, Thomas S. Wingo, Marı́a C. Carrillo, Tatiana M. Foroud, Paul Aisen, Ranjan Duara, Steven Salloway, Lawrence S. Honig, Kala Kirby, Bernardino Ghetti, Maryanne Thangarajah, Meghan Riddle
article en
1 citations

Abstract

Early detection of Alzheimer's disease (AD) is critical yet challenging, particularly in younger individuals. This study leverages artificial intelligence to analyze digital voice recordings from the Craft Story Recall task within the Longitudinal Early-onset AD Study (LEADS) to (1) detect cognitive impairment and (2) differentiate early-onset AD (EOAD) from early onset non-AD cognitive impairment (EOnonAD). Using speech samples from 120 patients and 68 cognitively unimpaired controls, we employed two classification approaches: feature-engineered machine learning and end-to-end deep learning incorporating a Large Language Model. To detect mild cognitive impairment, the feature-engineered model, using acoustic and linguistic features, achieved an AUC of 0.945 on the holdout test set, while the end-to-end model yielded an AUC of 0.988. For differentiating EOAD from EOnonAD, the feature-engineered model achieved an AUC of 0.804, and the end-to-end model yielded an AUC of 0.904 on the holdout set. Explainability analyses revealed reduced linguistic informativeness as a key AD indicator.

npj DementiaVol. 1(1)
Northwestern University (US), University of Southern California (US), Alzheimer's Association (US), Mayo Clinic (US), Harvard University (US), Johns Hopkins University (US), Emory University (US), University of California, Los Angeles (US), Palo Alto University (US), University of California, San Francisco (US), Georgetown University (US), University of Washington (US), Washington University in St. Louis (US), Cornell University (US), Brown University (US), University of Michigan (US), Columbia University Irving Medical Center (US), Johns Hopkins Medicine (US), Keck Hospital of USC (US), Jacksonville College (US), WinnMed (US), University of Chicago (US), Massachusetts General Hospital (US), Mount Sinai Medical Center (US), Methodist Hospital (US), Mayo Clinic in Arizona (US), Banner Sun Health Research Institute (US), Mayo Clinic in Florida (US), Indiana University School of Medicine, Indiana University – Purdue University Indianapolis (US), University of Pennsylvania (US), University of California, Davis (US), Stanford University (US)
Alzheimer's Association
Openalex Percentile: Top 14%
Dementia and Cognitive Impairment Research
1.47
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.