Hand-in-hand: UTSA, UT Health SA, and UT Tyler receive $1M to enhance trauma care using AI

MAY 8, 2024 — Researchers in the UTSA MATRIX AI Consortium for Human Well-Being will collaborate with researchers at UT Health San Antonio and UT Tyler on a newly funded project to develop and apply artificial intelligence (AI) tools to the field of trauma care. The $1 million grant was awarded by the Trauma Research and Combat Casualty Care Collaborative (TRC4), an initiative of The University of Texas System. The research team will develop and deploy AI tools to improve trauma care decision making among clinicians.

According to a paper published in the National Center for Biotechnology Information (NCBI), “Association between the time to definitive care and trauma patent outcomes: every minute in the golden hour matters,” expedient, definitive care is a major determinant of outcomes for trauma patients. Delayed care can result in lower survival rates and longer-lasting effects of trauma, with longer intervals between injury and treatment being “positively associated with the 30-day mortality rate.”

A second article in the NCBI, “History of trauma field triage development and the American College of Surgeons criteria,” notes that the first 60 minutes following a traumatic injury are so critical that they are commonly referred to as “the golden hour” by healthcare practitioners. Researchers across The University of Texas System aim to improve the care of critically injured patients in the Texas trauma system by utilizing AI tools to identify and remediate delays in care.

“UTSA is swiftly gaining momentum in the interdisciplinary field of AI and health.”

“The TRC4 is excited to support this collaboration with The University of Texas Health Science Center at San Antonio, the University of Texas at Tyler and The University of Texas at San Antonio and marks a significant milestone in our mission to advance trauma research,” said James Bynum, professor and vice chair of research in the department of surgery at UT Health San Antonio, and executive director of TRC4. “This partnership means exciting new opportunities in medicine, where innovative approaches and coordination will enhance patient outcomes and shape the future of health care."

The project is called iRemedyACT or Identification and Remediation of Delays to Definitive Care of Critically Injured Patients in the Texas Trauma System with Advances in AI to Improve Care for Trauma. The lead researchers from the collaborating institutions include Amina Qutub (UTSA), Brian Eastridge, MD (UT Health San Antonio) and Alan Cook, MD (UT Tyler). The MATRIX-affiliated co-PIs include Mark Goldberg, Dhireesha Kudithipudi, Joe Houpt and Chris Rathbone.

“This project will accelerate the design of machine learning models that evaluate high-dimensional, multi-modal and imbalanced trauma data, empowering clinicians to make swift, informed decisions on emergency medical interventions and deliver individualized patient care,” Kudithipudi noted. “It is a source of pride for me to see research leaders in MATRIX, such as Dr. Qutub, paving the way for a centralized AI-ready data repository dedicated to trauma care in Texas.”

ACT is an online platform with broadly accessible artificial intelligence (AI) tools and a corresponding training infrastructure for medical professionals. These tools include large-language models, expert-informed clustering and interactive visualization. ACT will be available for researchers and clinicians to analyze data and improve trauma care protocols, policies and decision making.

For ACT to produce valuable insights, the researchers will need to collect a relevant data set for interpretation. The project team will develop a communication network and database infrastructure to collect data on trauma patients from hospitals across the UT System, significantly bolstering the amount of data available to trauma professionals. The data will initially be available across Texas but may become available nationwide as the project progresses. Data on trauma care in the pre-hospital setting have historically been less robust and therefore less helpful in decision-making than data on treatment in the hospital, according to the NCBI paper, “A meta-analysis of prehospital care times for trauma.”

“For the last 25 years, we have gathered detailed data on injured patients from the moment of emergency department arrival to discharge from the hospital,” Cook said. “These data have informed volumes of prospective research. Ultimately, outcomes for patients have improved as a result. With this project, we turn our attention to the pre-hospital setting with the aim of realizing similar improvements in patient care and outcomes.”

Cook explained that the team will analyze time elapsed between patients’ injuries and their arrival at trauma centers. They will map geographic locations of injury scenes to identify injury hotspots. Once identified, these data could inform injury prevention initiatives and interventions. For example, additional resources could be deployed near injury hotspots to improve response time or transit time, potentially improving overall patient outcomes.

The research team expects that AI-informed decision-making will lead to improved survival rates of trauma patients, reduce the long-term effects of trauma and enhance the overall efficiency of the Texas Trauma system.

“There is great potential for AI to positively impact healthcare,” said Amina Qutub, associate professor of biomedical and chemical engineering. “Last month, the FDA approved the first AI software for hemorrhage triage of combat casualties. At the same time, a new rapid biomarker test to assess traumatic brain injury from blood was approved. Through the introduction of new AI methods and integrated databases to the field of trauma, iRemedyACT will accelerate these types of breakthrough translational applications that will save lives and improve quality of life for trauma survivors.”

This project aligns with a larger university-wide initiative at UTSA to foster research and scholarship at the intersection of AI and medicine. Last fall, UTSA and UT Health San Antonio jointly launched the nation’s first dual degree program in medicine and AI. Around the same time, MATRIX established a center to combat health disparities powered by AI and machine learning called M-POWER. The center received funding from the National Institutes of Health (NIH)’s AIM AHEAD program, which is dedicated to advancing health equity and research diversity through technology.

“UTSA is swiftly gaining momentum in the interdisciplinary field of AI and health,” noted JoAnn Browning, UTSA interim vice president for research. “This grant represents an incredible opportunity to conduct valuable research that bridges disciplines and, most importantly, improves patient outcomes.”

Bringing together over 70 scientists and AI experts from UTSA, UT Health San Antonio, the Southwest Research Institute and the wider San Antonio region, MATRIX AI is at the forefront of pioneering transdisciplinary AI solutions. Focused on four key research thrusts — machine learning and deployment, augmenting human capabilities, neuro-inspired AI and trustworthy AI — and strategically partnering with industry leaders and federal research labs, MATRIX AI is tackling significant AI challenges while addressing the nation’s growing need for interdisciplinary AI research talent. With multiple dedicated research centers and a plethora of collaborative projects, MATRIX AI is the primary hub for advancing AI research at UTSA and in San Antonio. M-POWER, one of three newly launched MATRIX research centers, focuses specifically on addressing health care disparities.

The iRemedyACT team is one of four recipients of a direct grant from TRC4. The $1 million award will fund the initial 16 months of the project, through July 31, 2025. Additional funding could be awarded for further development.

— Audrey Gray