FOR IMMEDIATE RELEASE

Contact: UTREALHealthAI@utsystem.edu

Competitive awards totaling more than $3.6 million support AI innovation in emergency care, patient safety, clinical efficiency, and medical education across eleven UT institutions.

AUSTIN, Texas — The University of Texas Research, Engineering, and Application Laboratory for Healthcare Artificial Intelligence (UT REAL Health AI) today announced funding for 12 pilot projects designed to advance the use of AI in healthcare across the UT System. Selected through a rigorous two-phase review of 120 systemwide submissions, the awards span three categories — AI Innovation, AI Implementation, and AI Collaboration — and involve institutions including UTHealth Houston, UT Southwestern, UT Austin, UT San Antonio, UTMB Galveston, MD Anderson Cancer Center, UT Rio Grande Valley, and UT Tyler.

“These projects represent the UT System’s commitment to deploying AI where it can make the greatest difference — at the bedside, in the clinic, and in the classroom,” said Dr. Nyma Shah, Executive Director of UT REAL AI. “Each award was chosen for its potential to deliver measurable impact for patients, providers, and health systems across Texas and beyond.”

AI Innovation Awards

Three moonshot projects each received up to $500,000 to pursue transformative clinical AI. 

BEACON Bedside Emergency AI for Care Orchestration (UT San Antonio, PI: Dr. Amina Qutub) deploys “Leah,” an AI clinical assistant trained on more than 400,000 trauma cases, across seven UT hospital sites to optimize emergency triage and transfer decisions. The project addresses a critical need, as trauma remains the leading cause of death for Texans under age 46. 

WombWatch Smartphone Detection of Fetal Movements Using Artificial Intelligence: A Novel Approach to Prevent Stillbirth (UT Austin, PI: Dr. Kenneth Moise) is a smartphone app that uses AI-powered acoustic analysis to detect fetal movements with 88% accuracy, compared with 18% for maternal perception alone. The technology could help prevent stillbirths in both high-risk and low-risk pregnancies. 

Reimagining Clinical Registry Abstraction with Uncertainty-Aware, Self-Improving AI (UT Southwestern, PI: Dr. Dylan Owens) aims to automate clinical quality registry abstraction using a registry-agnostic AI platform. The project seeks to reduce the multimillion-dollar manual burden on health systems participating in registries such as STS and AHA GWTG-Stroke.

AI Implementation Awards

Three projects received Implementation Awards to scale proven AI tools within clinical workflows. 

At UTMB Galveston, Dr. Salim Hayek is deploying AI Referral Triage to Reduce Low-Value Care and Improve Patient Access, a referral triage system for Internal Medicine. The tool analyzes EHR documentation, assigns urgency scores, and routes patients to the appropriate level of care. The project aims to reduce wait times for high-acuity patients by 20–40% and divert up to 25% of low-value referrals and create a deployment playbook for other UT institutions. 

At UTHealth Houston, Dr. Aanand Naik is scaling Priorities AI Scaling and Implementation to Achieve Medicare Age-Friendly Healthcare Designation, a conversational agent that identifies older adults’ surgical outcome goals before meeting with their surgeon. 

At UT Dell Medical School, Dr. Salim Saiyed is leading AI Tool for Patient Engagement and Clinical Efficiency Enhancement, which implements six Epic-integrated AI tools to automate lab result messaging, generate patient-facing imaging summaries, and reduce physician documentation burden through ambient voice technology.

AI Collaboration Awards

Six Collaboration Awards support cross-institutional projects addressing a diverse range of high-impact healthcare challenges. 

Expanding AI-Powered No-Show Reduction Across UT System Health Institutions, led by Dr. Xiaoqian Jian, that has already saved more than 6,500 appointments and $900,000 in revenue at UTHealth Houston. The project will now expand to UT Health San Antonio, where it is projected to recover 15,000–20,000 appointments annually. 

Stress-to-Suicide AI (S2S-AI), led by Dr. Ming Huang at UT Dell Medical School will use large language models to analyze free-text clinical notes across more than 7 million patient records. The system will identify suicidal ideation and life stressors, including unemployment and financial strain, to improve suicide risk detection and support prevention across Texas.

Artificial Intelligence (AI)-Powered Early Warning System to Predict Wrong-Tooth Extraction (WTE) in Oral & Maxillofacial Surgery (Predict-WTE) led by Dr. Sayali Tungare at UTHealth Houston, will combine computer vision analysis of dental imaging with natural language processing of surgical documentation to help prevent wrongful tooth extraction. 

On the research front, Scaling Human-in-the-Loop AI Trial Prescreening Across UT System HRIs led by Dr. Michael Dohopolski, expands a clinical trial prescreening platform previously validated on nearly 40,000 patients at UT Southwestern. The project will extend the platform to UT Health San Antonio and UTMB Galveston, helping accelerate clinical trials enrollment across the UT System.

Scaling and Validating AI-Enabled Simulation Assessment Across University of Texas Medical Schools,led by Dr. Andrew Jamieson UT Southwestern, expands an AI grading platform that has been in continuous operational use for more than three years and has supported more than 3,500 simulation encounters across text, audio, and video modalities. The initiative will scale the system across five additional UT institutions, creating the first multi-site validation of AI-assisted simulation assessment in medical education. 

Finally, AI Retina Scanning (AIRS) to Advance Population Health Across the UT System, led by Dr. Andrea Cooley at UT Tyler, uses artificial intelligence to expand access to retinal screening and early disease detecting at scale.