Researchers have developed a computer method using AI techniques that could lead to a deeper understanding of, and treatment for, Crohn’s disease, a chronic gastrointestinal inflammation that affects up to 780,000 people in the US alone.

The team from Rutgers University, which published the results of the study in the journal Genome Medicine, used artificial intelligence to examine genetic signatures of Crohn’s in 111 people, including 64 people with a Crohn’s disease diagnosis. Researchers then used an artificial intelligence method, known as AVA,Dx (Analysis of Variation for Association with Disease), to identify genes whose functions changed more in Crohn’s patients than in healthy people. 

The researchers were able to highlight known Crohn’s disease genes, as well as new potential Crohn’s genes. AVA,Dx also identified 16 percent of Crohn’s patients at 99 percent precision, and 58 percent of the patients with 82 percent precision in over 3,000 individuals from separately sequenced panels. 

“Our method is not a clinical diagnosis tool, but it generates interesting observations that need to be followed up,” explained senior author Yana Bromberg, an associate professor in the Department of Biochemistry and Microbiology at Rutgers University – New Brunswick.  

“Further experimental work could reveal the molecular reasons behind some forms of Crohn’s disease and, potentially, lead to better treatments of the disease.”

While the chronic inflammation caused by Crohn’s can occur in any part of the gastrointestinal tract, symptoms can also occur in other parts of the body. Crohn’s can cause joint pain and skin problems, and children with the disease may experience growth issues. 

Going forward, the team plans to expand its approach to uncover better treatments for patients with chronic conditions. Moreover, the study notes that while the model’s accuracy may improve by including more people, it could help reveal the origins of Crohn’s and improve early diagnosis and accuracy.

“We believe that we can use the knowledge gained from this study to similarly model other genetically linked diseases,” said Bromberg, who works in the School of Environmental Sciences and School of Arts and Sciences.

The team also noted that the results position AVA,Dx as both an effective method for revealing pathogenesis pathways and as a Crohn’s Disease risk analysis tool, which can improve clinical diagnostic time and accuracy.