CASE-BASED REASONING UNTUK DIAGNOSIS PENYAKIT JANTUNG; CASE-BASED REASONING FOR HEART DISEASES DIAGNOSIS

Wahyudi, Eka, Sri Hartati

2015 | Disertasi | FMIPA

Case Based Reasoning (CBR) is a computer system that uses for reasoning old knowledge to solve new problems. CBR provide solutions for new cases by looking at the old case which is closest to the new case. This research attempts to establish a system of Case-Based Reasoning for diagnosing heart disease. The process of diagnosis is done by inserting new cases (target case) containing symptoms at diagnosis will into the system, then the process of calculating the value of similarity between the new case with the base case (base case) using the nearest neighbor similarity method, minkowski distance similarity, and euclidean distance similarity. Case taken is the case with the highest similarity value. If a case does not succeed in the diagnosis or threshold < 80, the case will be revised by experts. Revised successful cases are stored to add the system knowledge. Method with the best diagnostic result accuracy will be used in building the CBR system for heart disease diagnosis. The test results using medical records data validated by expert indicate that the system is able to recognize diseases heart using nearest neighbor method, minskowski and euclidean correctly respectively of 100%. Using nearest neighbor get accuracy of 86.21%, minkowski 100%, and euclidean 94.83%.

Kata Kunci : Case-based reasoning; nearest neighbor similarity; minkowski distance similarity; euclidean distance similarity