Utilization of genetic data can improve the prediction of type 2 diabetes incidence in a Swedish cohort

Genetic risk score is associated with T2DM and diabetes complications risks

BACKGROUND

Type 2 diabetes mellitus (T2DM) is a prototypical complex disease with polygenic architecture playing an important role in determining susceptibility to develop the disease (and its complications) in subjects exposed to modifiable lifestyle factors. A current challenge is to quantify the degree of the individual's genetic risk using genetic risk scores (GRS) capturing the results of genome-wide association studies while incorporating possible ethnicity- or population-specific differences.

METHODS

This study included three groups of T2DM (T2DM-I, N=1,032; T2DM-II, N=353; and T2DM-III, N=399) patients and 2,481 diabetes-free subjects. The status of the microvascular and macrovascular diabetes complications were known for the T2DM-I patients. Overall, 21 single nucleotide polymorphisms (SNPs) were analyzed, and selected subsets were used to determine the GRS (both weighted - wGRS and unweighted - uGRS) for T2DM risk predictions (6 SNPs) and for predicting the risks of complications (7 SNPs).

RESULTS

The strongest T2DM markers (P<0.0001) were within the genes for TCF7L2 (transcription factor 7-like 2), FTO (fat mass and obesity associated protein) and ARAP1 (ankyrin repeat and PH domain 1). The T2DM-I subjects with uGRS values greater (Odds Ratio, 95% Confidence Interval) than six had at least twice (2.00, 1.72-2.32) the risk of T2DM development (P<0.0001), and these results were confirmed in the independent groups (T2DM-II 1.82, 1.45-2.27; T2DM-III 2.63, 2.11-3.27). The wGRS (>0.6) further improved (P<0.000001) the risk estimations for all three T2DM groups. The uGRS was also a significant predictor of neuropathy (P<0.0001), nephropathy (P<0.005) and leg ischemia (P<0.0005).

CONCLUSIONS

If carefully selected and specified, GRS, both weighted and unweighted, could be significant predictors of T2DM development, as well as the diabetes complications development.

Predictive Estimates of Risks Associated with Type 2 Diabetes Mellitus on the Basis of Biochemical Biomarkers and Derived Time-Dependent Parameters

This work contributes to the development of effective statistical methods of big data analysis for type 2 diabetes mellitus (T2DM) risk assessment to be employed in routine clinical practice. The objective of this study to be reached via machine-learning analysis is twofold: investigation of a possible application of biochemical biomarkers for the T2DM risk prediction in case of a limited knowledge of biometrical parameters of an individual, as well as study on the predictive ability of a derived parameter (rate of a biomarker change over time) in T2DM risk prediction. Obtained statistical parameters (AUC, p-value, etc.) justify a relatively high quality of the model. Nevertheless, a further improvement may be addressed through the following avenues: analysis of adding new factors and models, including lifestyle/habits, and genetic parameters.