As most infections are seeded from a patient's own microbiota, resistance-gaining recurrences can be predicted and minimized by machine learning.
An Israeli research group says its artificially intelligent antibiotic prescribing algorithm can cut the risk of antibiotic resistance by half.
Antibiotics are essential to curing bacterial infections, but their overuse promotes the appearance and proliferation of antibiotic-resistant bacteria.
“We wanted to understand how antibiotic resistance emerges during treatment and find ways to better tailor antibiotic treatment for each patient to not only correctly match the patient’s current infection susceptibility, but also to minimize their risk of infection recurrence and … resistance to treatment,” said Prof. Roy Kishony from the Technion – Israel Institute of Technology.
The group focused on two common bacterial infections — urinary tract infections and wound infections – to show how each patient’s past infection history can be used to choose the best antibiotic to reduce the chance of antibiotic resistance emerging.
“As most infections are seeded from a patient’s own microbiota, these resistance-gaining recurrences can be predicted using the patient’s past infection history and minimized by machine learning – personalized antibiotic recommendations, offering a means to reduce the emergence and spread of resistant pathogens,” the researchers explained.
They used genomic sequencing techniques and machine learning analysis of patient records to develop this approach, described in Science.
“We found that the antibiotic susceptibility of the patient’s past infections could be used to predict their risk of returning with a resistant infection following antibiotic treatment,” explained lead author Dr. Mathew Stracy.