<![CDATA[The increase in cases of coronary heart disease without detailed knowledge of the causes is a serious problem that requires immediate treatment. This study aims to analyze the relationship between causal factors and the incidence of coronary heart disease using the Frequent Pattern Growth (FP-Growth) algorithm. This algorithm is applied to medical data of inpatients at RSUD dr. Fauziah Bireuen to identify patterns of relationships that often arise between risk factors such as age, gender, diabetes, cholesterol, hypertension and uric acid on the diagnosis of coronary heart disease. There were 180 patient medical record data with 17 items used for analysis. The results show the three most significant relationship patterns: the combination of risk factors for diabetes and high cholesterol has a support value of 50% and confidence of 67%, the risk of diabetes in men has a support value of 47% and confidence of 63%, and the combination of cholesterol and hypertension shows a support value of 45 % and confidence 66%. These results are expected to provide better insight into the prevention, early detection and treatment of coronary heart disease, as well as improving health services in hospitals. This research also emphasizes the importance of applying data mining technology in the analysis of complex health data.]]>
Copyrights © 2025
