Pavilion Publishing and Media Ltd
Blue Sky Offices Shoreham, 25 Cecil Pashley Way, Shoreham-by-Sea, West Sussex, BN43 5FF, UNITED KINGDOM
Tel: +44 (0)1273 434 943
Email: [email protected]
An artificial intelligence (AI) algorithm can accurately predict diabetes and prediabetes according to preliminary research published in BMJ Innovations.
The algorithm uses an electrocardiogram (ECG) to detect structural and functional changes in the cardiovascular system, which could be indicative of diabetes.
The researchers say this new method could help to reduce reliance on blood glucose measurements, which is an invasive procedure that is challenging roll out as a mass screen test in low resource settings.
New technique could be used to screen for diabetes in low resource settings
The researchers wanted to discover whether the AI techniques could be used to harness the screening potential of ECG to predict pre-diabetes and type 2 diabetes in people at high risk of the disease.
For this reason, the study drew on participants in the Diabetes in Sindhi Families in Nagpur (DISFIN) study, which looked at the genetic basis of type 2 diabetes and other metabolic traits in high-risk families in Nagpur, India.
The prevalence of both type 2 diabetes and pre-diabetes was high: around 30% and 14%, respectively. And the prevalence of insulin resistance was also high -35% as was the prevalence of other influential coexisting conditions – high blood pressure (51%), obesity (around 40%), and disordered blood fats (36%).
In total, 1,262 participants were included. The average age of the participants was 48 and the majority (61%) were women. Each participant provided details of their personal and family medical histories, their normal diet, and underwent a full range of blood tests and clinical assessments.
DiaBeats algorithm detected diabetes and prediabetes with an overall accuracy of 97%
A standard 12-lead ECG heart trace lasting 10 seconds was done for each participant and 100 unique structural and functional features for each lead were combined for each of the single heartbeats recorded. This generated a predictive algorithm, known as DiaBeats.
Based on the shape and size of individual heartbeats, the DiaBeats 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.
Further research needed to confirm findings
The researchers acknowledge various limitations to the study, including that the study participants were all at high risk of diabetes and other metabolic disorders. The findings are therefore unlikely to be applicable to the general population.
DiaBeats was also found to be slightly less accurate in those taking prescription meds for diabetes, high blood pressure, high cholesterol etc.
Furthermore, no data were available for those who became pre-diabetic or diabetic, making it impossible to determine the impact of early screening.
The researchers therefore conclude that while the study provides “a relatively inexpensive, non-invasive, and accurate alternative” to current diagnostic methods, further studies will need to be done to validate the findings.