Using data analytics to improve diabetes prevention

Health / Pharma   |   
Published March 5, 2015   |   
Suzanne Elvidge

Many companies and research groups are working to treat diabetes, but preventing the disease will have a greater impact on health in at-risk groups. A team of US researchers are using data analytics to create a precision medicine approach to prevention of diabetes that steers efforts towards those who are at highest risk of developing the disease and who would benefit most from drug treatment or preventive lifestyle strategies.

“Simply having pre-diabetes is not everything… there’s a lot of variation, and that we need to go beyond single risk factors and look holistically at who are the people in whom a particular approach works best,” says lead author Jeremy Sussman, of the University of Michigan Medical School.

The aim was to use data analytics to create and test a simple model for doctors that could predict which pre-diabetic patients would gain the most from treatment with a drug that prevents diabetes, or from a lifestyle change such as weight loss or regular exercise. The research was published in the BMJ.

The researchers used data from over 3000 people in landmark clinical trial of diabetes prevention, the Diabetes Prevention Program, including a variety of different health factors such as blood sugar levels and waist-to-hip ratios. The Diabetes Prevention program was funded by the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) and looked at whether short-term and long-term lifestyle changes or metformin could delay diabetes in overweight or obese people with abnormal blood sugar tests. Many also had other risk factors such as family history or race.

Of the 17 factors that were assessed that could predict an individual’s risk of diabetes, seven were most important:
– Fasting blood sugar
– Long-term blood sugar (HbA1C)
– Total triglycerides
– Family history of high blood sugar
– Waist measurement
– Height
– Waist-to-hip ratio

The team created a scoring scale based on these factors and the clinical trial data. According to the scale, less than one in 10 of the trial participants who scored in the lowest 25% would develop diabetes in the next three years, compared with almost half in the top 25%. Based on this, the people with the very highest risk of developing diabetes were the only ones who actually benefitted from taking metformin. However, in this sub-group, the drug really made a difference, bringing down their risk of the disease by 21%.

By contrast, exercise and weight loss, with encouragement from a health coach, benefited everyone to some extent, whatever their risk score.

– For the quarter of study participants that the model said had the highest risk of diabetes, lifestyle interventions cut their chance of developing the disease by 28%
– For the study participants with the lowest diabetes risk, this same intensive lifestyle change brought down their risk too, but by only 5%Use of the model could help doctors work out who is at the highest risk, and create targeted prevention programmes. While advice on exercise and weight loss had a smaller impact on the people at lower risk, it still made a small difference, and can also reduce cardiovascular risk, mood and mobility.

According to the researchers, this approach could also be used to develop precise prediction models for other diseases and treatments.

“We think this approach should be broadly applicable, since one of the main determinants of any patient’s likelihood of benefiting from a therapy is their risk of having the bad outcome that we are trying to prevent,” says co-author David M Kent, of the Predictive Analytics and Comparative Effectiveness Center at the Tufts Medical Center. “It is poorly appreciated how many patients receive treatments unnecessarily — when the possibility of benefit is very low, and may well be exceeded by the burdens of treatment. If these types of analyses were incorporated routinely into trial design, we believe we would have a much clearer understanding of this issue.”

This article originally appeared here. Republished with permission. Submit your copyright complaints here.