Cardiovascular disease detection from high utility rare rule mining

We propose a method to search rare cardiovascular disease symptom rules from historical health examination records according to its hazard ratio utility and further detect the disease given new medical record data. Further, we aim to assist both medical experts and patients by alerting the current symptoms and preparing the early treatments. In general, the proposed method first deals with the uncertainty of age and other continuous features using a fuzzy set. Next, we define the hazard ratio utility of each item set to assist the mining process. Based on the utility, we discover the rare cardiovascular disease patterns employing High Utility Rare Itemset Mining. At last, we add a prediction step to check the given health record data whether diagnosed cardiovascular. Subsequently, we can obtain rare symptoms of cardiovascular disease, which are later applied to detect the new related record data. The rare symptoms that are confirmed by their utility risk for cardiovascular disease can assist the medical experts' decision better than the common symptoms as it is often hard to be recognized at a glance. The proposed method evaluated on a public cardiovascular dataset. The experimental results showed that the generated rare cardiovascular disease patterns successfully applied to detect the cardiovascular given the symptoms data.