The study, published in the journal Genome Medicine, used artificial intelligence (AI) to examine genetic signatures of Crohn's disease in 111 people.
The method can help in revealing previously undiscovered genes linked to the disease, and in predicting whether thousand others had the disease.
"Our method is not a clinical diagnosis tool, but it generates interesting observations that need to be followed up," said senior author Yana Bromberg, Associate Professor at Rutgers University in the US.
"Further experimental work could reveal the molecular reasons behind some forms of Crohn's disease and, potentially, lead to its better treatment," Bromberg said.
Crohn's disease affects around 780,000 people in the US.
Chronic inflammation may occur in any part of the gastrointestinal tract, although symptoms may occur elsewhere. It can also cause joint pain and skin problems, and children with the disease may have growth problems, according to the US National Library of Medicine.
The research team evaluated genetic variants in the 111 people, including 64 with Crohn's disease, and used AI techniques to pinpoint genes whose functions changed more in Crohn's patients than in healthy people, and vice versa.
While the model's accuracy might improve by including more people, it could help reveal the origin of Crohn's disease and improve early diagnosis, the study said. "We can use the knowledge gained from this study to similarly model other genetically-linked diseases," Bromberg said.
( With inputs from IANS )