UT Tyler Awarded Nearly $175K by National Science Foundation to Enhance EKG Diagnostics

August 5, 2025 | Hannah Buchanan

The University of Texas at Tyler received $174,740 from the National Science Foundation to create computationally efficient Artificial Intelligence models to better understand electrocardiograms, or EKGs/ECGs. Dr. Sagnik Dakshit, UT Tyler assistant professor of computer science, serves as principal investigator on the two-year project.

EKGs are used extensively by clinicians for the detection and monitoring of cardiac conditions and constitute an essential element of both routine and emergency cardiac care.

“This project seeks to build deep learning systems that can generate synthetic ECG signals for rare cases, enhance diagnostic reliability by identifying instances of model uncertainty, and produce comprehensive explanation reports that reflect the clinical workflow of ECG diagnosis,” said Dakshit, whose research interests include AI in both education and health care informatics. “These explanations are intended to assist clinicians in understanding the reasoning behind deep-learning model decisions, thereby increasing trust and usability in real clinical settings.”

Despite recent advancements in the automatic diagnosis and interpretation of medical conditions from EKG signals, the real-world use of these models in health care remains limited. This is due to several challenges, Dakshit noted, such as the lack of sufficient data for rare/clinically important heart conditions, the difficulty of understanding how the current ‘black box’ models make decisions, and the absence of explanations that align with the diagnostic reasoning from clinical experts.

“The results of this research are expected to improve the quality and transparency of DL-based decision support systems, enrich training for future health care professionals through tools that align with their diagnostic processes, and broaden access to accurate and interpretable diagnostic technologies," he added.

UT Tyler undergraduates will collaborate alongside Dakshit. Dr. Bhavani Suryadevara and Dr. Lindsey Stockton, UT Tyler School of Medicine faculty, will also provide clinical support.

“We are so proud of Dr. Dakshit and this collaborative effort he is leading to develop and test AI models that are clinically aligned to real-world problems,” said Dr. Krist Swimberghe, UT Tyler Soules College of Business dean. “Students involved will work across the business and health care sectors and foster a mindset for solving problems through critical thinking as well as technical skills.”

Dakshit joined the Soules College of Business in 2023. Aside from his research endeavors, he has been instrumental in bringing AI to the forefront of education, leading AI-focused presentations, projects and workshops across the university and East Texas.

He holds a doctorate in computer science from UT Dallas as well as a Bachelor of Technology degree in computer science and engineering from the West Bengal University of Technology in India. Additionally, Dakshit teaches applied deep learning, database design, software development and information management courses at UT Tyler.

With a mission to improve educational and health care outcomes for East Texas and beyond, UT Tyler offers more than 90 undergraduate and graduate programs to more than 10,000 students. Through its alignment with UT Tyler Health Science Center and UT Health East Texas, UT Tyler has unified these entities to serve Texas with quality education, cutting-edge research and excellent patient care. Classified by Carnegie as a doctoral research institution and by U.S. News & World Report as a national university, UT Tyler has campuses in Tyler, Longview, Palestine and Houston.