Technologists and microbiologists, from Duke University, have collaborated on using artificial intelligence in order to examine patterns within the communities of bacteria living in the human gut (the gut microbiome). Analysis of these patterns suggests an indication can be made as to who, among the approximately one billion people on the planet, are most at risk of a cholera infection and will thus develop the diarrheal disease.
Cholera is an infectious bacterial disease, which leads to severe watery diarrhea. Untreated, this can result in dehydration and potentially death. The disease is caused by eating food or drinking water contaminated with the bacterium Vibrio cholerae. Cholera affects an estimated 3–5 million people worldwide and causes 28,800–130,000 deaths a year.
Describing the outcome of the new research, lead scientist Dr. Lawrence A. David, explains: “These are patterns that even the most sophisticated scientist couldn’t detect by eye. 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.”
The research showed how predictive microbiota (indicator organisms) found in the guts of some people, but not others, can be used to assess how someone will react to being infected with the cholera-causing organisms.
To identify population differences, the researchers collected rectal swab samples from people in Dhaka. Those selected for sampling were people who lived in the same household with a patient hospitalized with cholera. In all 76 household contacts were studied.
With the study group, a third went on to develop cholera during the follow-up period, whereas about two-thirds remained uninfected. The reason for this was found in the composition of the gut bacteria between these two groups.
The patterns were found through the use of artificial intelligence. The scientists identified the collected bacteria from the study group guts, using sequencing technology. Next they trained a computer to scan the results from 4000 different bacterial taxa found in each of the samples. The artificial intelligence was used to look for patterns. The output was a set of 100 microbes associated with susceptibility in people to cholera.
The new research has been published in the Journal of Infectious Diseases, with the research paper titled “Human Gut Microbiota Predicts Susceptibility to Vibrio Cholera Infection.”
