Plasma fibrinogen levels are associated with a strong family history of myocardial infarction

A new, accurate predictive model for incident hypertension

OBJECTIVE

Data mining represents an alternative approach to identify new predictors of multifactorial diseases. This work aimed at building an accurate predictive model for incident hypertension using data mining procedures.

METHODS

The primary study population consisted of 1605 normotensive individuals aged 20-79 years with 5-year follow-up from the population-based study, that is the Study of Health in Pomerania (SHIP). The initial set was randomly split into a training and a testing set. We used a probabilistic graphical model applying a Bayesian network to create a predictive model for incident hypertension and compared the predictive performance with the established Framingham risk score for hypertension. Finally, the model was validated in 2887 participants from INTER99, a Danish community-based intervention study.

RESULTS

In the training set of SHIP data, the Bayesian network used a small subset of relevant baseline features including age, mean arterial pressure, rs16998073, serum glucose and urinary albumin concentrations. Furthermore, we detected relevant interactions between age and serum glucose as well as between rs16998073 and urinary albumin concentrations [area under the receiver operating characteristic (AUC 0.76)]. The model was confirmed in the SHIP validation set (AUC 0.78) and externally replicated in INTER99 (AUC 0.77). Compared to the established Framingham risk score for hypertension, the predictive performance of the new model was similar in the SHIP validation set and moderately better in INTER99.

CONCLUSION

Data mining procedures identified a predictive model for incident hypertension, which included innovative and easy-to-measure variables. The findings promise great applicability in screening settings and clinical practice.

Fibrinogen and cardiovascular disease: genetics and biomarkers

Several prospective epidemiological studies and clinical observations provided evidence regarding fibrinogen and coronary artery disease (CAD). Many of these studies firmly correlate fibrinogen with CAD. However, it is uncertain whether this relation is causal or reflects genetic variability and residual confounding by other risk factors. Several polymorphisms on fibrinogen chain genes affect its levels, however only few of the genetic variants are associated with increased cardiovascular risk. As regards the role of fibrinogen in myocardial infarction (MI) studies indicate that genetic variations have at best a modest impact on the process resulting in MI. Therefore, the screening of fibrinogen genes might not be useful for the assessment of the risk of MI. However, the findings that specific genotypes lead to specific differences in fibrinogen levels, but may not be linked to cardiovascular risk, complicates the hypothesis of causality of fibrinogen in the pathogenesis of cardiovascular disease.

Present status of outcome prediction of invasive coronary treatment by using genetic markers

A growing number of studies suggest that the outcome after invasive coronary treatment may be in part genetically determined. Here, we review the present status of outcome prediction of invasive coronary treatments by using genetic markers. Although some studies found an association between one or another genetic marker with one or another clinical endpoint, many other studies found no such relations; to date, none of the genetic markers that have been investigated in association studies are used in routine clinical practice to prospectively assess the prognosis following invasive coronary treatment or to decide upon therapeutic strategies. Many associations between genetic markers and certain clinical endpoints were initially reported in small studies but could not be confirmed in larger ones. Some of these discrepancies may be explained by publication bias. Some genetic variants may have true effects on clinical endpoints, which, albeit biologically interesting, do not bear much clinical relevance. On the other hand, many-if not most-studies that have been published to date are more or less grossly underpowered and very rarely report on the results of an a priori power analysis. Thus, there is still a need for further high-quality studies designed to investigate the specific contribution of genetic factors to the outcome after invasive coronary interventions.