According to an early study reported in the online journal BMJ Innovations, an artificial intelligence (AI) system created from the characteristics of individual heartbeats captured on an ECG (electrocardiogram) can effectively identify diabetes and pre-diabetes.
The method might be used to test for the disease in settings with limited resources, according to the researchers, if it is shown effective in larger investigations.
An estimated 463 million persons worldwide had diabetes in 2019, and detecting the condition early is essential to avoiding significant health issues down the road. But the measurement of blood glucose plays a significant role in diagnosis.
The researchers note that it is difficult to implement this as a mass screening test in situations with limited resources because it is not just invasive.
Even before obvious blood glucose changes, the cardiovascular system experiences early structural and functional changes that are visible on an ECG heart trace.
To predict pre-diabetes and type 2 diabetes in those who are at high risk for the condition, the researchers wanted to examine if machine learning (AI) approaches might be utilized to tap into the screening potential of the ECG.
They drew from those who took part in the Diabetes in Sindhi Families in Nagpur (DISFIN) project, which investigated the genetics of type 2 diabetes and other metabolic features in Sindhi families in Nagpur, India, who were at high risk of developing the condition.
Families living in Nagpur, which has a high population of Sindhi people, and has at least one known instance of type 2 diabetes were enrolled in the study.
Participants gave specifics about their own and their families medical histories, described their usual diets, and underwent a full range of clinical evaluations and blood testing. They were 61% female, with an average age of 48.
The diagnostic standards outlined by the American Diabetes Association allowed for the identification of pre-diabetes and diabetes.
Pre-diabetes and type 2 diabetes were both very common, with prevalence rates of 30% and 14%, respectively. Additionally, the prevalence of other significant concomitant diseases like high blood pressure (51%), obesity (about 40%), and disordered blood fats (36%), as well as insulin resistance (35%), was similar considerable.
A standard 12-lead ECG heart trace lasting 10 seconds was done for each of the 1262 participants included. And 100 unique structural and functional features for each lead were combined for each of the 10,461 single heartbeats recorded to generate a predictive algorithm.
Based on the shape and size of individual heartbeats, the algorithm quickly detected diabetes and prediabetes with an overall accuracy of 97% and a precision of 97%, irrespective of influential factors, such as age, gender, and coexisting metabolic disorders.
Important ECG features consistently matched the known biological triggers underpinning cardiac changes that are typical of diabetes and pre-diabetes.
The trial participants were all at high risk for diabetes and other metabolic problems, making them unlikely to reflect the broader population, according to the researchers. In people taking prescription medications for diabetes, high blood pressure, high cholesterol, etc., it was a little less accurate.
Furthermore, data on those who developed pre-diabetes or diabetes were not available, making it impossible to assess the effects of early screening.
In their conclusion, they state that their study "provides a theoretically reasonably cheap, non-invasive, and accurate alternative [to current diagnostic procedures] which can be utilized as a gatekeeper to successfully detect diabetes and pre-diabetes early in its development."
They do, however, stress that "strong validation on external, independent datasets will be required before adoption of this technique into everyday practice."
Comments
Post a Comment