Swiss pharmaceutical giant Roche said Tuesday it would soon begin marketing a device that uses artificial intelligence to predict possible low blood sugar events during the night and thus help sufferers of diabetes sleep without worry.
Diabetes is a chronic, metabolic disease characterized by elevated blood sugar levels that is treated with insulin injections. Sufferers can also have problems with episodes of low blood sugar levels—hypoglycaemia—during the night that disrupt their sleep, some requiring medical intervention.
Roche said its latest continuous glucose monitor, a wearable sensor, takes readings of blood sugar levels every five minutes and is paired with an AI app.
“Its integrated AI-enabled predictive algorithms indicate hypoglycaemia risk within the next 30 minutes, continuously forecast how glucose levels will develop within the next two hours, and estimate the risk of nocturnal hypoglycaemia,” it said.
The technology enables “proactive intervention before glucose levels require immediate attention” and “is designed to alleviate … concerns about nighttime hypoglycaemia and lower its risk,” added Roche.
It said the predictive AI algorithms exceeded high performance requirements in terms of accuracy and that it judged the system meets European health and safety standards.
While generative AI applications like ChatGPT have garnered the most public attention, artificial intelligence has been increasingly deployed in a number of areas like language translation and image recognition, including to aid medical professionals.
More than 422 million people suffer from diabetes across the world in 2014, according to the World Health Organization, with rising levels of obesity driving rising numbers of type 2 diabetes, which occurs when the body becomes resistant to insulin or doesn’t make enough insulin.
© 2024 AFP
Citation:
Roche to use AI to help diabetics sleep peacefully (2024, July 9)
retrieved 9 July 2024
from https://medicalxpress.com/news/2024-07-roche-ai-diabetics-peacefully.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.