Breakthrough in determining cholera infection risk

Image: Healthcare Analytics News
Image: Healthcare Analytics News

Scientists have developed machine-learning algorithms that can identify patterns in the bacteria of a patient’s gut to determine whether the patient is likely to get infected if exposed to cholera, reports Healthcare Analytics News.

The researchers believe such artificial intelligence (AI) could be critical in areas of high cholera risk, since it can analyse trillions of bacteria, much more than can be done by humans.

The study also demonstrates the power of machine learning to uncover medical insights that would otherwise remain obscure.

The research is a joint collaboration between Duke University, Massachusetts General Hospital, and the International Centre for Diarrheal Disease Research, in Bangladesh.

One reason it matters is that it’s still not understood exactly why some people exposed to cholera get the disease while others don’t.

Bangladesh has been plagued by cholera outbreaks, and the centre has been a leading institution in the fight to test and distribute treatments and vaccines for the disease.

For this study, the researchers identified Bangladeshi 76 households where a resident had been hospitalised for cholera, thus putting other residents at high risk of infection. The team collected rectal swabs from study participants and then tracked whether they went on to develop cholera.

About a third of patients became infected with cholera, but the rest did not. With those data, the machine-learning algorithm identified nearly 1000 bacterial taxa that seemed to be indicative of whether a patient would come down with cholera.

“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 Regina C. LaRocque, MD, MPH, a senior author and assistant professor of medicine at Harvard Medical School.

“We’ve essentially identified a whole new component of cholera risk that we did not know about before.”

Lawrence A David, PhD, a senior author of the study and assistant professor of molecular genetics and microbiology at Duke School of Medicine, said this information could help researchers prevent cholera infections.

“Some of the preventative methods that we foresee include identifying types of microbiota that are associated with susceptibility, and then investigating interventions that discourage those risk-associated microbiota,” he told Healthcare Analytics News.

“Such interventions that might benefit the microbiome include nutrition or sanitation.”

Poor sanitation and a lack of clean water are among the major risk factors for cholera, which infects between 1.3 and 4 million people per year, according to the World Health Organization.

David said the technology could be used to better understand other diseases, too.

“Yes, our general strategy is replicable for other diseases,” he said. “The most straightforward extensions would be other diseases where microbiota samples can be obtained prior to disease.”

One way to make such AI-driven prevention methods a reality is to create large-scale microbiome biobanks, David said. He said Duke is currently a biobank for cancer patients at risk of Graft-versus-Host Disease.