Award
NIH Reporter #1R03DE036394-01
Clinical Informatics of Xerostomia: Characterizing Comorbidities, Social Risk Factors, and Predicting Oral Health Outcomes Using Structured and Unstructured EHR Data
Recipient
University of California, San Francisco
Award Amount
$328,000.00
Ceiling
$328,000.00
Awarded
August 28, 2026
Identifier
1R03DE036394-01
Award to University of California, San Francisco to develop an AI-driven model predicting oral health outcomes related to xerostomia using EHR data.
Description
This project aims to develop and validate a novel Electronic Health Record (EHR)-based phenotype of xerostomia (dry mouth) and to build a preliminary AI-driven risk prediction model of oral health complications. The study will analyze a large dataset from UCSF’s De-Identified Clinical Data Warehouse, containing over 4.5 million patients and 198 million clinical notes. The project will utilize AI-enabled multimodal phenotyping that integrates structured data, clinical notes, and social factors, and will develop a risk prediction model using logistic regression and machine learning methods.