Cardiovascular disease is a class of diseases referring to functional abnormality of heart, which is the leading cause of deaths worldwide. Nowadays, one of the most popular methods to diagnose heart disease is based on electrocardiography (ECG) - a recording of the electrical activity of the heart. According to its characteristics, different patterns have been carefully studied in order to produce clinical decision-making. However, the diversity of patterns raises a lot of difficulties to memorize all of them. On the other hand, the historical patterns of prior ECG is also important to the diagnostic process. Therefore, in this research, we make an important use-inspired novel contribution namely, a framework based on semantic technologies, that allows to: (i) store ECG's features in a scalable linked database; (ii) flexibly access to ECG's characteristics through pattern queries; (iii) easily translate clinical ECG interpretation and heart disease diagnosis guides into semantic rules that can be automatically performed. Moreover, the new rules can be also easily and incrementally added to the framework.

View PDF No PDF? Try Arxiv!