Breaking News
  • Oppn’s aim to defeat me, my aim to take Delhi forward: Arvind Kejriwal before filing nomination
  • Delhi polls: AAP drops Jitender Singh Tomar over false declaration charges
  • Zomato acquires Uber Eats business in India
  • AP Assembly clears proposal for three state capitals - Visakhapatnam, Kurnool, and Amravati
  • Amazon launches electric delivery rickshaws in India

No More Pricking! Artificial Intelligence Can Now Detect Low Blood Sugar

Publish On: 16 Jan, 2020 05:19 PM | Updated   |   Madhurima  

Low blood sugar can now be detected from raw ECG signals, through a method which requires artificial intelligence or AI. The patient would only need to wear a sensor that will help with the detection. As of now, the methods to check sugar levels either require finger-pricks or needles which cause pain. 


The latest procedure has been invented at the University of Warwick situated in the United Kingdom. It has an accuracy rate of 82% and can most definitely substitute the other present-day machines which require getting pricked in the finger. Children with diabetes can really benefit from this technology.


The research revealed that the detection of hypoglycemia, meaning very high blood sugar is 82% reliable precisely.


A statement by Dr. Leandro Pecchia in the Nature Springer journal Scientific Reports reads, "Our innovation consisted in using AI for automatic detecting hypoglycemia via few ECG beats. This is relevant because ECG can be detected in any circumstance, including sleeping. Fingerpicks are never pleasant and in some circumstances are particularly cumbersome. Taking fingerpick during the night certainly is unpleasant, especially for patients in pediatric age.” Pecchia belongs to the School of Engineering.


The technology is capable of producing algorithm outputs over time, where if green lines are produced, that would signify the glucose levels being normal. Whereas, red lines are to represent low glucose levels.


The study also mentioned "Our approach enable personalised tuning of detection algorithms and emphasise how hypoglycaemic events affect ECG in individuals. Basing on this information, clinicians can adapt the therapy to each individual.”