Study: Indian Scientists Develop Ai Algorithm To Detect Diabetes And Pre-diabetes
The AI algorithm was developed by Indian scientists based on the characteristics of individual heartbeats recorded on an ECG (electrocardiogram), and it is capable of accurately predicting diabetes and pre-diabetes.
There is a team of Indian scientists that have developed an artificial intelligence (AI) algorithm that is derived from the features of the individual heartbeats recorded on an ECG (electrocardiogram) and is able to predict diabetes and pre-diabetes with great accuracy. As part of the study, the team from Lata Medical Research Foundation in Nagpur included clinical data from 1,262 individuals.
Study: Indian Scientists c Ai Algorithm To Detect Diabetes And Pre-diabetes
Each participant underwent a standard 12-lead ECG heart trace lasting 10 seconds, which lasted for a total of 30 seconds.
For each of the 10,461 single heartbeats recorded in this study, 100 unique structural and functional features were combined for each of the leads in order to generate a predictive algorithm which was named DiaBeats based on these features.
By using the DiaBeats algorithm to detect diabetes and prediabetes based on the shape and size of individual heartbeats, it was able to detect these conditions with an overall accuracy of 97% and a precision of 97%, regardless of influential factors such as age, gender, or co-existing metabolic disorders.
The ECG features that consistently matched the known biological triggers that are responsible for the heart changes that occur in diabetics and pre-diabetics did not vary from one study to the next.
According to the team, the method could be used to screen for the disease in low resource settings, if it is validated in larger studies.
In theory, this study can provide an inexpensive, non-invasive, and accurate alternative (to current diagnostic methods) which can be used as a gatekeeper to effectively detect diabetes and pre-diabetes early in the course of the disease.”
It should be noted, however, that the adoption of this algorithm into routine practice will require rigorous validation on external, independent datasets before it can be adopted.
In 2019, it is estimated that there were 463 million adults around the world who had diabetes. In order to prevent serious health problems in the future, detection of diabetes in its early stages is extremely important, but measuring blood glucose levels plays a key role in the diagnosis of this disease.
In a paper published in the online journal BMJ Innovations by researchers at the University of Cambridge, they pointed out that this type of test is not only invasive but also challenging to roll out in low-resource settings as a mass screening test.
An ECG heart trace will show indications of structural and functional changes in the cardiovascular system even before indications of changes in blood glucose levels appear, as they occur early on in the disease.
The researchers also acknowledge that the participants in the study were all at high risk for diabetes and other metabolic disorders, which means that they are unlikely to be representative of the general population.
There was a slight decrease in the accuracy of diabetes in those taking prescription medications for diabetes, high blood pressure, high cholesterol, etc.
Data were not available for those who had become pre-diabetic or diabetic, so it was impossible to determine the impact of early detection on the development of diabetes.