Google+ Facebook Twitter Twitter

AI and ecg heart trace to predict diabetes

An artificial intelligence (AI) algorithm, derived from the features of individual heartbeats recorded on an ECG (electrocardiogram), can accurately predict diabetes and pre-diabetes, suggests preliminary research.

If validated in larger studies, the approach could be used to screen for the disease in low-resource settings, say the researchers.

Families with at least one known case of type 2 diabetes and living in Nagpur, India were enrolled in the study.

The prevalence of both type 2 diabetes and pre-diabetes was high – around 30% and 14%, respectively. The prevalence of insulin resistance was also high – 35%.

Based on the shape and size of individual heartbeats, the algorithm quickly detected diabetes and pre-diabetes with an overall accuracy of 97% and a precision of 97%, irrespective of influential factors, such as age, gender, and coexisting metabolic disorders.

Image credit |Shutterstock

Related Articles

Viral respiratory infection, illustration-CREDIT-science photo library C0553686

Beyond SARS-COV-2

Dr Jennifer Cane, a Postdoctoral Research Assistant, asks what sequencing respiratory viruses can tell us.


Microsatellite instability cancer tests

New US research compares the data of newly diagnosed cancer patients who received two different types of tests to determine their course of treatment.

mri examination-CREDIT-istock-1140748315

Novel genetic variants associated with Alzheimer’s disease

New research has identified several genetic variants that may influence Alzheimer’s disease risk, putting researchers one step closer to uncovering biological pathways to target for future treatment and prevention.

The lesser horseshoe bat (Rhinolophus hipposideros)-Image Credit | istock-816193242

Bat swarming and immunity

Bats carry some of the deadliest zoonotic diseases that can infect both humans and animals, such as Ebola and COVID-19.