Key Takeaways
- Chase Markel, a University of Wyoming Ph.D. student, is developing an AI model to predict the risk of congestive heart failure in cattle based on images of a cow’s heart.
- The model has been trained on nearly 7,000 images and can assign the correct score 92% of the time.
- Markel hopes that this tool can help alleviate financial losses associated with congestive heart failure in the cattle industry.
- The AI model has the potential to revolutionize the field of animal science and improve the bottom line for producers.
- Markel is also developing a similar model to evaluate liver images for the presence and severity of liver abscesses in feedlot cattle.
Introduction to Chase Markel’s Research
Chase Markel, a University of Wyoming Ph.D. student from Wheatland, is harnessing artificial intelligence to transform how animal scientists study risk factors for congestive heart failure in cattle. His AI model, the first of its kind, has been trained to predict the risk of congestive heart failure based on images of a cow’s heart. Markel, who grew up in the cattle industry, hopes that this new tool can ultimately help alleviate financial losses associated with the condition. As he explains, "I’m not a computer scientist, I’m not an AI guy, I’m someone who is studying heart failure [in cattle] and just happened to have the right conversation and made the connection in order to build something that I think can be useful."
Background and Motivation
Markel completed both his undergraduate and master’s degrees in the UW Department of Animal Science. He is currently pursuing a doctorate in the same department under the guidance of faculty advisers Hannah Cunningham-Hollinger and Cody Gifford. As a master’s student, Markel studied pulmonary hypertension, also known as high-altitude disease or brisket disease, in cattle. He didn’t anticipate that this animal science research would eventually lead to a fellowship in the UW School of Computing and the development of a "computer vision" model with the potential to revolutionize his field. Markel’s master’s research indicated that subclinical cases of pulmonary hypertension, in which an animal is affected by high-altitude disease but survives, may have larger economic impacts than direct profit losses incurred when an animal dies before harvest.
The AI Model and Its Potential
The size and shape of a cow’s right ventricle are key risk indicators for both pulmonary hypertension and congestive heart failure. As pressure builds in the right ventricle, the heart becomes thick and misshapen, increasing the severity of pulmonary hypertension and risk of congestive heart failure. Markel knew that detecting these abnormalities, especially in subclinical cases of congestive heart failure, could potentially provide valuable data for plants and producers. As a School of Computing fellow, Markel developed an image classification model calibrated with thousands of heart images taken in commercial processing plants in Nebraska and Colorado. He used a 1-5 scoring system developed by Tim Holt, a close collaborator and professor at Colorado State University, to train the model to correctly categorize images by score.
Accuracy and Future Developments
To date, Markel’s dataset includes nearly 7,000 images, each of them scored by hand, then used to train the model. The new tool has already achieved a startling degree of accuracy. Given an image it’s never encountered before, the AI model assigns the correct score 92% of the time. Although he continues to refine the model, Markel has provided proof of concept for a novel approach to identifying economically relevant risk factors in individual animals. In fact, he’s currently developing a similar model to evaluate liver images for the presence and severity of liver abscesses, another common affliction in feedlot cattle. As Markel explains, "As researchers, we need to start incorporating these tools into our research and…build that technology so producers and people out in the industry can actually utilize those tools and help improve their bottom line."
Impact and Future Plans
While Markel’s current models are best suited for application in processing plants, he hopes that future iterations will benefit Wyoming producers more directly. As Kelly Crane, Farm Credit Services of America dean in the College of Agriculture, Life Sciences and Natural Resources, comments, "Chase Markel’s research exemplifies our college’s commitment to conducting Wyoming-relevant research, which integrates emerging technologies, producer experiences and UW faculty expertise to address some of Wyoming agriculture’s most vexing challenges." Markel submitted a provisional patent application to the U.S. Patent and Trademark Office (USPTO) through UW in 2025. He hopes to obtain full patent protection in 2026. For questions about Markel’s research, contact him at protected email. As Markel continues to develop and refine his AI model, he remains committed to using technology to improve the cattle industry and alleviate financial losses associated with congestive heart failure.
UW Student Develops Artificial Intelligence Model to Study Heart Failure in Cattle