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

Genetic method for identifying hundreds of disease agents

A new paper compares the pathogen-detecting ability of a next-generation sequencing (NGS) system — the Respiratory Pathogen Infectious Diseases/Antimicrobial Resistance Panel (RPIP) — with a previously studied NGS system and standard of care (SOC) diagnostic methods for samples obtained with bronchoalveolar lavage.

“Gene editing via CRISPR/cas9 can lead to cell toxicity and genome instability”

CRISPR/Cas9 is a commonly used, very precise, gene editing technique often known as “genetic scissors”.

An electrophoresis case study

Madihah Abbas, Specialist Biochemistry Team Manager at Christie Pathology Partnership, looks at result interpretation, comparing gel and capillary zone electrophoresis.

Nanopore sequencing for rare genetic disorders

Using nanopore sequencing investigators can accurately detect specific genomic disorders in a fraction of the time it takes to conduct traditional and molecular cytogenetic testing.