(HealthDay News) — Lipid profiling can predict the risk for type 2 diabetes (T2D) and cardiovascular disease (CVD) years before disease incidence, according to a study published online March 3 in PLOS Biology.
Chris Lauber, Ph.D., from Lipotype GmbH in Dresden, Germany, and colleagues assessed future T2D and CVD risk for 4,067 participants from a population-based cohort. Several risk scores for T2D and CVD incidence during up to 23 years of follow-up were computed by training machine learning models on the measurements obtained at baseline, when individuals were healthy.
The researchers found that a lipidomics risk score based on the quantification of 184 plasma lipid concentrations resulted in increases of 168 and 84% in the incidence rate of T2D and CVD in the highest-risk group and a 77 and 53% decrease in the incidence rate in the lowest-risk group, respectively, compared with the average case rates of 13.8 and 22%. There was only a marginal correlation for lipidomic risk with polygenic risk. By adding standard clinical variables to the model, risk stratification was further improved, resulting in a case rate of 51 and 53.3% for T2D and CVD, respectively, in the highest-risk group. Significantly altered lipidome compositions affecting 167 and 157 lipid species were seen in the highest-risk group for T2D and CVD, respectively.
“The lipidomic risk, which is derived from only one single mass-spectrometric measurement that is cheap and fast, could extend traditional risk assessment based on clinical assay,” Lauber said in a statement.
Several authors disclosed financial ties to Lipotype GmbH.
