Researchers at Duke University, Massachusetts General Hospital, and the International Center for Diarrheal Disease Research in Bangladesh used machine learning algorithms to identify patterns within communities of bacteria present in the human gut that experts would not be able to detect with the naked eye.
Regina C. LaRocque of the Massachusetts General Hospital Division of Infectious Diseases, a senior author of the study, said these patterns could identify people at risk of cholera infection before they become sick.
The team trained the algorithm to scan the results from 4,000 different bacterial taxa in each sample, seeking patterns that distinguished those who became ill from those who did not.
The researches said their model could predict illness even better than models previously built by infectious disease experts.
From Duke Today
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found