Understanding dry mouth in adults using AI to read electronic records
Official title: Clinical Informatics of Xerostomia: Characterizing Comorbidities, Social Risk Factors, and Predicting Oral Health Outcomes Using Structured and Unstructured EHR Data
Funded at University of California, San Francisco · NIH-11437326 · Data updated 2026-11-12
A new project uses AI to find adults with xerostomia in medical records and predict who will have worse oral health outcomes.
Quick facts
| Grant type | R03 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 28, 2026 |
| Project end | August 27, 2028 |
| Funding year | 2026 |
| Award (this year) | $328,000 |
| NIH project number | 1R03DE036394-01 |
| Project ID | NIH-11437326 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults 21 years and older with xerostomia or at risk of xerostomia who have comprehensive electronic health records available for NLP analysis.
✕Less likely to help
Individuals without xerostomia or without access to detailed EHR data may not directly benefit.
What this research studies
This project aims to use both structured data like ICD codes and unstructured text from electronic health records to better identify people with xerostomia (dry mouth) and understand how comorbidities and social factors affect their oral health. By applying natural language processing to clinical notes, the study hopes to uncover patterns that traditional data miss and forecast future oral health needs. The goal is to improve early identification and tailor interventions to reduce dental caries, infections, and related quality-of-life impacts for affected adults. The work is led by UC San Francisco and focuses on AI-assisted analysis of patient records to inform care.
Why it matters
Potential benefit: If successful, this work could help clinicians pinpoint patients at highest risk for severe dry-mouth complications and guide personalized prevention and treatment strategies.
How similar studies have gone: Previous work shows NLP can improve identification of patient symptoms in records; this study proposes applying it specifically to xerostomia for risk prediction.
Where this research is happening
-
University of California, San Francisco
San Francisco, United States Active
Researchers
- Principal investigator: Banava, Sepideh — University of California, San Francisco
- Study coordinator: Banava, Sepideh
Related research
Other NIH-funded projects on the same topics.
-
IOP and CSF Pressure in Glaucoma Risk
This grant studies how eye pressure and cerebrospinal fluid pressure together influence glaucoma risk and vision loss.
-
ALS risk factors in a long-term ALS study
A long-term ALS study is looking at which factors may influence disease risk and progression in people living with ALS.
-
Understanding how work exposures and genes influence ALS risk
A study is building a long-term group of people at higher risk for ALS to see how their jobs, exposures at work, and genes together affect if and when the disease might develop.
-
Coordinated Oral Health Promotion for Chicago Kids
A long-running study in Chicago is following children and their caregivers to find ways to reduce tooth decay and improve daily life for families.
-
P-CARRS-BRAIN: Predicting Alzheimer’s risk in South Asians in India using genetic, behavior, and vascular data
Aims to predict Alzheimer’s disease risk in middle-aged South Asians by combining genetic, lifestyle, and vascular information to catch early changes before dementia develops.
-
P-CARRS-BRAIN: Predicting Alzheimer’s risk in South Asians in India using genetics, behavior, and vascular data
Aimed at people 21 and older, this project looks at how biology, behavior, and blood vessel health together may signal the early risk of Alzheimer’s disease and related dementias in South Asians.
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.