TRENDING ON ONEINDIA
- Kerala: PM Modi Inaugurates Kollam Bypass; Assures 100 Percent Rural Connectivity
- India vs Australia 2nd ODI; As It Happened — Kohli, Dhoni Power India To 6-Wicket Win
- New Maruti Wagon R 2019 — Exterior And Interiors Revealed In Official Video
- Xiaomi Redmi 7 Teased To Be Priced Around Rs. 8,500
- Interim Budget 2019 May Increase Income Tax Exemption Limit To Rs. 5 Lakh
- Every Place You Need To Visit If You Are A First-timer In Una
- Kangana Takes A Jibe At Bollywood Again!
- Lisa Ray's Nature-Inspired Dress Makes For An Ideal Evening Party Wear
AI (artificial intelligence) is being considered as the future of tech world. However, can it help make a positive difference in other fields too? Well, the answer may be yes.
According to a recent study, microscopes enhanced with artificial intelligence (AI) could help in the quick and accurate diagnosis of the deadly blood infections, resulting in improving the patients' odds of survival. In usual cases, the bacteria that cause bloodstream infections are the rod-shaped bacteria including Escherichia coli or E.coli, the round clusters of Staphylococcus species, and the pairs or chains of Streptococcus species.
Quick identification and delivery of antibiotic medications is the only way to treat bloodstream infections, which can take the lives of up to 40 percent of patients who develop them.
The study was conducted by scientists of Beth Israel Deaconess Medical Centre (BIDMC) in Boston, who used an automated microscope designed to collect high-resolution image data from microscopic slides.
A convolutional neural network (CNN), which is a class of artificial intelligence modeled on the mammalian visual cortex and used to analyze visual data, was trained to categorize bacteria based on their shape and distribution.
The scientists fed the neural network over 100,000 images from blood samples, in order to the train the AI system.
The machine intelligence learned how to sort the images into the three categories of bacteria; rod-shaped, round clusters, and round chains or pairs; ultimately achieving about 95 percent accuracy, said the researchers.
"This marks the first demonstration of machine learning in the diagnostic area," said James Kirby, Director at the Clinical Microbiology Laboratory at BIDMC.
"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," Kirby added, in the paper published in the Journal of Clinical Microbiology.
Automated classification can also ameliorate the shortage of human technologists by helping them work more efficiently, "conceivably reducing technologist read time from minutes to seconds", Kirby also suggested.
What's more, the new tool could also have applications in microbiology training and research.