AI finds patterns among gut bacteria that signal cholera risk

Machine-based algorithms in use by an international team of researchers have found a way to predict people’s susceptibility to cholera through gut bacteria.

Out of trillions of bacteria swimming around the gut, the artificial intelligence (AI) determined a hundred microbes that establish levels of susceptibility to cholera infection. It is a level of detail, researchers said, which humans never could have detected by eye, but will now allow the deciphering of patterns among the approximately 1 billion humans at active risk of the disease and the development of vaccine counters.

“Our study found that this ‘predictive microbiota’ is as good at predicting who gets ill with cholera as the clinical risk factors that we’ve known about for decades,” said Dr. Regina C. LaRocque, of the Massachusetts General Hospital Division of Infectious Diseases as well as a senior author of the study. “We’ve essentially identified a whole new component of cholera risk that we did not know about before.”

For the research, scientists turned to rectal swab samples from Dhaka residents exposed to cholera. The machine was trained to specifically assess 4000 different bacterial taxa in each sample, from which it gleaned the 100 microbes associated with cholera susceptibility.

“Normally, you have to eyeball the data, studying one bacterial species at a time in hopes of finding a signal that is associated with infection,” Firas Midani, a lead author of the study and graduate student, said. “Machines have the ability to look at a hundred species at a time, and amalgamate them into one signal.”

Researchers from Duke University, Massachusetts General Hospital, and the International Centre for Diarrheal Disease Research in Dhaka, Bangladesh teamed up for the study. Their results were published in the Journal of Infectious Diseases.