UTHealth Houston researchers developing app to help clinicians assess thoracic aortic aneurysm risk and dissections

From left, David Murdock, MD, Siddharth Prakash, MD, PhD, and Krishi Manem. (Photo by UTHealth Houston)

A $100,000 grant awarded to researchers at UTHealth Houston from the John Ritter Foundation will fund an app that will help clinicians recognize, access, and manage thoracic aortic disease.

Heritable thoracic aortic diseases such as Marfan syndrome, Loeys-Dietz syndrome, and vascular Ehlers-Danlos syndrome are conditions that lead to fragility of the aorta and other blood vessels. Currently, genetic data on patients with these disorders can be complex and time-consuming to review, making it difficult for doctors to identify and treat patients appropriately to prevent life-threatening complications such as aortic dissections.

The app, AortaGPT, was developed by David Murdock, MD, assistant professor of medical genetics, and Siddharth Prakash, MD, PhD, professor of medical genetics and cardiovascular medicine, both in the Department of Internal Medicine atMcGovern Medical School at UTHealth Houston. AortaGPT is an AI-driven point-of-care tool that physicians can use to translate complex genetics concepts into clear, actionable care recommendations.

AortaGPT uses a large language model to gather a patient’s genetic data and medical history to offer treatment guidance. Trained on public genetic databases, aortic disease registry data, and established care guidelines curated by Prakash and his team, the model can generate a tailored treatment plan complete with risk curves. This will guide clinicians on the appropriate next steps in patient care, for example, additional imaging or medication recommendations. 

The AortaGPT team also developed and trained a facial recognition algorithm capable of detecting subtle differences in facial appearance associated with genetic conditions that affect the aorta, such as Marfan syndrome and vascular Ehlers-Danlos syndrome. Using just a photograph, the AI identifies facial features suggestive of these disorders and alerts clinicians that the patient may warrant further evaluation or specialized management. This tool could be particularly valuable in acute care settings like emergency departments, as well as in locations without access to genetic specialists or testing. 

“Many genetic conditions that predispose to aortic and arterial aneurysms and dissections have some kind of characteristic or unique facial features,” Murdock said. “You probably notice with your phone how it can very quickly say who is who in a photo or an image. With AortaGPT, a medical provider could use this technology to screen for these conditions just using facial image analysis.”

The next phase of AortaGPT is moving the tools into a working app for clinicians. 

“By the end of the award period, we expect to develop fully operational prototypes of AortaGPT and the facial recognition component that are ready for external validation and clinical implementation,” Prakash said.

“This grant will allow us to get the app where it needs to be, to be testable,” said Krishi Manem, a second-year medical student at McGovern Medical School. “We want to validate this model and give it out to clinicians and see if it’s adding anything clinically and what we may need to improve.” 

Co-investigators include: Dianna Milewicz, MD, PhD, professor, President George Bush Chair in Cardiovascular Medicine, and director of the Division of Medical Genetics in the Department of Internal Medicine atMcGovern Medical School, and Shaine Morris, MD, MPH, associate professor in the Division of Pediatric Cardiology at Baylor College of Medicine and a pediatric cardiologist at Texas Children’s Hospital.