AI Helps Predict Susceptibility to Cholera Infections

A new study describes how artificial intelligence (AI) can be used to spot colonization patterns of 100 different microbe communities associated with susceptibility to cholera.

Researchers at Duke University (Durham NC, USA), Harvard Medical School (HMS; Boston, MA, USA), and the International Centre for Diarrheal Disease Research (ICDDRB; Dhaka, Bangladesh) have developed a machine learning algorithm that can spot patterns within communities of bacteria living in the human gut that are invisible to human eyes. To do so, they prospectively studied household contacts of cholera patients to compare those who were infected with those who were not.


Of the 76 household contacts studied, about a third went on to develop cholera during the follow-up period, and about two-thirds remained uninfected. The researchers profiled the microbiota from the contacts' rectal swab samples using sequencing technology and then loaded all the data into a computer for analysis. They then trained a predictive machine-learning algorithm to scan the results from 4,000 different bacterial taxa in each of the samples, looking for patterns that distinguished those who got sick from those who didn't. Eventually, the machine identified a set of 100 microbes associated with susceptibility to cholera.

The researchers also showed that the model generated by AI could predict illness better than models previously built by infectious disease experts. The model also suggested hypotheses that might explain why the patterns identified by the computer work. For example, when they picked a bacterial species identified by their model and studied it in the laboratory, they found that the bacteria promoted the growth of cholera in-vitro. The findings indicate that the composition of the gut microbiota could create an environment that is more or less hospitable to pathogens. The study was published on April 12, 2018, in the Journal of Infectious Diseases.

“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 senior author Regina LaRocque, MD, MPH, of HMS. “Scientists have long had a hunch that gut bacteria might affect a person's susceptibility to diarrheal diseases. We've essentially identified a whole new component of cholera risk that we did not know about before.”

“These are patterns that even the most sophisticated scientist couldn't detect by eye,” added senior author Lawrence David, PhD, an assistant professor of molecular genetics and microbiology at Duke School of Medicine. “While some people are warning about artificial intelligence leading to killer robots, we are showing the positive impact of AI in its potential to overcome disease.”

Cholera is an infection in the small intestine with symptoms that include profuse, watery diarrhea and vomiting. Transmission occurs primarily by drinking water or eating food that has been contaminated by the feces of an infected person, including one with no apparent symptoms. The severity of the diarrhea and vomiting can lead to rapid dehydration and electrolyte imbalance, and death in some cases.

Related Links:
Duke University
Harvard Medical School
International Centre for Diarrheal Disease Research