Speech and language tools to detect Alzheimer's and frontotemporal dementia in Spanish and English speakers
Official title: An automated machine learning approach to language changes in Alzheimer’s disease and frontotemporal dementia across Latino and English-speaking populations
Funded at University of California, San Francisco · NIH-11404657 · Data updated 2026-11-12
Using short natural speech recordings, researchers will look for sound and language patterns that can help detect Alzheimer's disease and frontotemporal dementia in Spanish-speaking Latinos and English-speaking adults.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Francisco NIH-funded |
| Lab location | 1 site (San Francisco, United States) |
| Project start | August 15, 2023 |
| Project end | June 30, 2028 |
| Funding year | 2025 |
| Award (this year) | $279,559 |
| NIH project number | 3R01AG075775-03S3 |
| Project ID | NIH-11404657 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are Spanish-speaking Latinos and English-speaking adults with diagnosed or suspected Alzheimer's disease or frontotemporal dementia, as well as healthy control volunteers willing to provide speech samples.
✕Less likely to help
People without cognitive concerns or those with neurological conditions not related to Alzheimer's disease or frontotemporal dementia may not receive direct benefit from this project.
What this research studies
You would be asked to produce natural speech (conversation, storytelling, or similar tasks) while being recorded so acoustic and word-level features can be extracted. Those digital features will be analyzed with automated speech and language methods and machine learning to find patterns that distinguish Alzheimer's disease from frontotemporal dementia and from healthy aging. The project includes large groups of Spanish speakers from five Latin American countries and English speakers in the US and will account for factors like bilingualism, sex, and brain profile. Researchers will also compare speech markers with standard clinical measures to test how well speech-based signals match established evaluations.
Why it matters
Potential benefit: Could enable low-cost, scalable speech-based screening and monitoring tools that make earlier and more accessible detection of AD and FTD possible for Spanish- and English-speaking patients.
How similar studies have gone: Previous automated speech and language studies have shown promising signals for detecting dementia but have typically been small and focused on English, so this multilingual, large-scale effort builds on encouraging but not yet definitive evidence.
Where this research is happening
-
University of California, San Francisco
San Francisco, United States Active
Researchers
- Principal investigator: Gorno Tempini, Maria Luisa — University of California, San Francisco
- Study coordinator: Gorno Tempini, Maria Luisa
Related research
Other NIH-funded projects on the same topics.
-
Automated language analysis for Alzheimer’s disease and frontotemporal dementia in Latino and English speakers
A low-cost, automated speech and language analysis tool is being developed to help identify Alzheimer’s disease or frontotemporal dementia in Latino and English-speaking people.
-
Automated language analysis for Alzheimer’s and frontotemporal dementia across Latino and English-speaking groups
A low-cost, automated language study aims to help diagnose and understand Alzheimer’s and FTD in diverse Spanish- and English-speaking communities.
-
Automated language analysis to help diagnose Alzheimer’s and frontotemporal dementia in Latino and English speakers
A low-cost, computer-based method analyzes speech and language to help identify Alzheimer’s disease or frontotemporal dementia in Latino and English-speaking people.
-
Automated language analysis for Alzheimer's and frontotemporal dementia in Latino and English-speaking communities
A low-cost, computer-based language analysis method is being developed to help identify Alzheimer’s disease and frontotemporal dementia in Latino and English-speaking people.
-
Automated language analysis to detect Alzheimer’s and frontotemporal dementia in Latino and English-speaking adults
A low-cost, computer-based language and speech analysis tool will help identify Alzheimer’s disease and frontotemporal dementia in Latino and English-speaking adults.
-
Automated language analysis for Alzheimer’s disease and frontotemporal dementia in Latino and English speakers
A machine learning approach analyzes speech and language from Latino and English-speaking people to help detect Alzheimer’s disease and related dementias.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.