Long term cardiovascular risk models’ combination

Abstract

The correct diagnosis of cardiovascular disease is a key factor to reduce social and economic costs. In this context, cardiovascular disease risk assessment tools are of fundamental importance. This work addresses two major drawbacks of the current cardiovascular risk score systems: reduced number of risk factors considered by each individual tool and the inability of these tools to deal with incomplete information. To achieve these goals a two phase strategy was followed. In the first phase, a common representation procedure, based on a Naïve-Bayes classifier methodology, was applied to a set of current risk assessment tools. Classifiers’ individual parameters and conditional probabilities were initially evaluated through a frequency estimation method. In a second phase, a combination scheme was proposed exploiting the particular features of Bayes probabilistic reasoning, followed by conditional probabilities optimization based on a genetic algorithm approach. This strategy was applied to describe and combine ASSIGN and Framingham models. Validation results were obtained based on individual models, assuming their statistical correctness. The achieved results are very promising, showing the potential of the strategy to accomplish the desired goals.