Automated speech analysis to spot language changes in Alzheimer's and frontotemporal dementia for Spanish- and English-speakers

An automated machine learning approach to language changes in Alzheimer’s disease and frontotemporal dementia across Latino and English-speaking populations

NIH-funded research University of California, San Francisco · NIH-11128685

This project uses automated speech and language analysis with machine learning to find language signs of Alzheimer's and frontotemporal dementia for Spanish- and English-speaking patients, including Latinos.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of California, San Francisco NIH-funded
Lab location1 site (San Francisco, United States)
Project IDNIH-11128685 on NIH RePORTER

What this research studies

You would be asked to speak naturally so researchers can collect recordings of your speech. They will extract sound and language features (like voice patterns and word use) and use machine learning to look for patterns that match Alzheimer's or frontotemporal dementia. The project includes about 2,740 people across five Latin American countries and the United States, comparing people with AD, people with FTD, and healthy controls. The team will account for factors like bilingualism, sex, and brain profiles to make the tools usable across different languages and backgrounds.

Who could benefit from this research

Good fit: Ideal participants include Spanish- or English-speaking people with diagnosed or suspected Alzheimer's disease or frontotemporal dementia, as well as healthy older adults for comparison, including bilingual Latinos.

Not a fit: People who cannot produce natural spoken samples in Spanish or English, have very advanced disease that prevents speech, or are outside the study regions may not benefit directly from participation.

Why it matters

Potential benefit: If successful, this could enable low-cost, language-based tools to help detect and monitor Alzheimer's and frontotemporal dementia earlier and more fairly for Latino and English-speaking patients.

How similar studies have performed: Previous speech-analysis research has shown promising signals for detecting dementia, but few large studies have tested diverse Latino and bilingual groups or directly compared Alzheimer's and frontotemporal dementia, so this work is partly novel.

Where this research is happening

San Francisco, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions Alzheimer disease dementiaAlzheimer syndromeAlzheimer's Disease
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.