A team of researchers has shown that artificial intelligence (AI) can help predict the type of bacteria that cause infection in pneumonia patients. The research is presented at ASM Microbe Online, the annual meeting of the American Society for Microbiology.
“This research highlights the potential of AI as an additional tool for physicians in identifying causative pathogens from pneumonia, even before the results of sputum culture are available,” said Joowhan Sung, MD, a hospitalist at MedStar Southern Maryland Hospital. “We have shown that doctors can be helped by AI in deciding on appropriate antibiotics.”
In the study, investigators showed that AI could use the information available in the emergency room and predict whether the patient had MRSA or pseudomonas so that doctors could immediately prescribe specific antibiotics targeting specific bacteria.
Infections caused by antibiotic-resistant bacteria are difficult to treat and can be life-threatening. According to the CDC, “more than 2.8 million antibiotic-resistant infections occur, and more than 35,000 people die from them.”
Pneumonia caused by bacteria such as methicillin-resistant Staphylococcus Aureus (MRSA) or pseudomonas can be fatal because they are resistant to commonly prescribed antibiotics. Although there are effective antibiotics against these infections, the test, culture of sputum, takes at least 48 hours to incubate and identify these bacteria from sputum, while these patients can deteriorate in a few hours.
Investigators presented an analysis of more than 50,000 data on admissions to intensive care units (ICU) at Beth Israel Deaconess Medical Center (BIDMC) in Boston, Massachusetts. Researchers analyzed the records of patients admitted for pneumonia and trained a “neural network” AI agent using the set of Data. The AI agent has shown promising results in predicting the bacteria responsible for infection.
“Similar techniques can be applied to future research on pneumonia in the middle of the current pandemic, such as capturing bacterial co-infection in people with known COVID-19, which could be fatal if left undetected,” Sung said.
Jun Hyek Jang, MS, senior researcher at AvoMD, Inc. and Joongheum Park, MD, a hospitalist at Beth Israel Deaconess Medical Center, also contributed to this work. This research received no external funding.
ASM Microbe Online presents the dynamic and cutting-edge science of ASM Microbe 2020, the annual meeting of the American Society for Microbiology. Explore the latest microbial science research with ePosters, listen to experts in the field during live keynotes, and access track-related content with an organized selection of on-demand sessions.
A potential new weapon in the war against superbugs
Supplied by American Society for Microbiology
Quote: Artificial intelligence can help predict the bacteria responsible for pneumonia in emergency rooms (July 24, 2020) recovered on July 26, 2020 on https://medicalxpress.com/news/2020-07-artificial-intelligence-bacteria-responsible-pneumonia.html
This document is subject to copyright. Apart from fair use for study or private research purposes, no party can be reproduced without written permission. The content is provided only for information.