For the first time in Bangladesh, researchers at the University of Agriculture (BAU) claim that they have successfully utilized machine learning, a form of artificial intelligence, to identify, diagnose and propose effective preventive measures for brucellosis, a fatal animal bone disease that affects both animals and humans.
This study was conducted under the Faculty of Veterinary Md. It was conducted with Dr. SiddiqurRahman and Doctoral Researcher Colonel (RETD) SM Azizul Karim Hussaini.
They argue that this AI-driven approach could revolutionize the control and prevention of brucellosis in the country.
“Brucellosis is a globally significant infectious disease that affects livestock, wildlife, and even marine mammals. It causes significant economic losses for farmers due to reduced milk production, abortion and reduced reproductive performance,” Dr. Rahman said.
“And as a zoonotic disease, it can easily be transmitted from animals to humans, poses a serious public health risk.”
This study was recently published in the Asian Journal of Agriculture and Biology, a Scopus-indexed journal with an impact coefficient of 1.6. Dr. Rahman was the lead investigator of the study, co-supervisor Dr. Heinrich Neubauer of the Friedrich Loeffler Institute in Germany. The project also received technical support from King Faisal University in Saudi Arabia.
Addressing the media, Dr. Rahman explained: “There is currently no effective treatment for this disease, and farmers have long suffered due to its widespread impact. By applying five machine learning algorithms, including MLP, Deep Learning 4J, Adaboost MI and J48 Tree, we have identified the major risk factors associated with brucellosis.
He said, “While machine learning is already being used around the world to detect heart disease, kidney disorders, diabetes and human breathing conditions, applications for animal health are still emerging in Bangladesh.
In this study, out of 12 species of Brucella, B. abortus, B. suis, B. melitensis, and B. canis, were found to be the most pathogenic and harmful.
Dr. Rahman also said B. Live vaccines such as abortus (S-19) and RB51 are currently in use, but emphasized that they pose a risk of side effects. In contrast, fever-killed vaccines have proven to be safer and more effective in research, paving the way for the development of a new generation of vaccines to prevent brucellosis in Bangladesh.
“Under the direct supervision of Dr. Siddiqur Rahman, we have demonstrated that machine learning techniques can be effectively applied to understand transmission dynamics and prevention strategies for brucellosis,” said Doctoral Researcher Colonel (RETD) SM Azizul Karim Husaini.
He said, “We followed the right protocol and achieved the desired results. This success exists as a proud milestone for both the national and the veterinary science community.”
