Accurate Identification of Bacteria using Artificial intelligence
Microbiologists at Beth Israel Deaconess Medical Center (BIDMC), reveled on December 15, 2017 that microscopes with artificial intelligence (AI) can help microbiologists to diagnose blood infections at early stage.
The paper was published in Journal of Clinical Microbiology. AI-enhanced microscope system was found to be highly proficient at identifying bacterial images. The automated system could help alleviate the lack of highly trained microbiologists, which is expected to decrease as 20% of technologists reach retirement age in the next five years. According to Artificial Intelligence in Healthcare Market report Published by Coherent Market Insights, artificial intelligence in healthcare can analyze the relationship between treatment techniques and patient outcomes, which can be useful in medical practices such as diagnostic processes, drug development, personalized medicines, and patient monitoring care.
Automated microscope was designed to capture high-resolution image data from microscopic slides. Specific characteristics were selected to represent bacteria that most often cause bloodstream infections such as rod-shaped bacteria E. coli, round clusters of Staphylococcus species, and the pairs or chains of Streptococcus species.
“This marks the first demonstration of machine learning in the diagnostic area,” said senior author James Kirby, MD, Director of the Clinical Microbiology Laboratory at BIDMC and Associate Professor of Pathology at Harvard Medical School. “With further development, we believe this technology could form the basis of a future diagnostic platform that augments the capabilities of clinical laboratories, ultimately speeding the delivery of patient care.”
Unschooled neural network was fed more than 25,000 images from blood samples prepared during routine clinical workups. Researchers generated more than 100,000 training images using standard images of which the bacteria that had already been identified by human clinical microbiologists. The machine intelligence was programmed to sort the images into the three categories of bacteria such as rod-shaped, round clusters, and round chains or pairs, achieving nearly 95% accuracy. In addition to its clinical uses, this new tool could also have applications in microbiology training and research.
You may be interested
Researchers Demonstrate Quantum Walk in Bose-Einstein CondensateMohit Joshi - October 20, 2018
Researchers from Oklahoma State University manipulated the momenta of ultra-cold atoms to demonstrate a quantum walk Quantum analogs of a random walk form the basics of proposed…
Mobile Health Apps and Solutions Market Industry Insights, Dynamic Growth and Revenue Forecast 2018-2026Albert R - October 19, 2018
Mobile Health Apps and Solutions Market report 2018-2026 focuses on the major drivers and restraints for the key players. These research report also provides granular analysis of…
Drug Abuse Treatment Market – Launch and approval of novel drugs is projected to fuel market growth over the forecast periodMohit Joshi - October 19, 2018
Coherent Market Insights released a new market study on 2018-2026 Drug Abuse Treatment Market with 100+ market data Tables, Pie Chat, Graphs & Figures spread through Pages…