By Scout Nelson
Bovine Respiratory Disease (BRD) has long been a challenge for cattle feeders, becoming the costliest affliction within fed cattle production due to stress from transportation and co-mingling of cattle. Lilli Heinen, a graduate student at Kansas State University’s Beef Cattle Institute, is leading research that may change how the industry approaches BRD using machine learning.
Machine learning is a form of artificial intelligence in which machines, such as computers, learn and improve from data fed into the system. Heinen's doctoral research focuses on how predictive models and machine learning can help cattle producers manage feedlot datasets to mitigate the effects of BRD.
“The main objective of my doctorate program is to get a better idea of how producers can use machine learning and predictive devices with feedlot datasets, which can be diverse and messy,” Heinen explained.
In 2023, Heinen and the Beef Cattle Institute set out to apply machine learning, a tool commonly used in crop production, to feedlot cattle treatment outcomes for BRD. By using Microsoft Azure and feedlot data, Heinen’s team developed five algorithms to predict BRD treatment results.
“Our research evaluation compared all five of them against each other,” Heinen said. “We took the true outcomes for those cattle, and then set those side by side with what the models said would happen, and then calculated the accuracy of each of them.”
Although the models demonstrated moderate accuracy, Heinen noted that improvements are needed for practical use. The research also found that algorithms worked better when customized for individual feedyards rather than using data from multiple locations.
Heinen believes these predictive tools could help reduce labor shortages in feedlots by supporting decision-making in cattle treatment. “I am not saying that computers can replace a human decision, yet we do not have the needed number of people in feedyards to make treatment decisions all the time,” she said.
Heinen’s ongoing research is now focused on developing models for groups of cattle to help reduce antibiotic use by detecting morbidity rates and optimizing treatment plans.
“Hopefully, these machine learning tools can help us lower the use of antibiotics and resistance to them,” Heinen concluded.
Photo Credit:gettyimages-digitalvision
Categories: Kansas, General, Livestock, Dairy Cattle