Mental disorders are disorders of behavior, moods and thoughts that can change a person's behavior differently than usual. Cases of mental disorders obtained from medical record data at the Naimata Mental Hospital (RSJ) in 2019 were 6,157 patients with 2 mental specialists. The lack of a number of mental specialists has caused some mental health programs not to run properly, resulting in a longer recovery rate for mental disorders. In this study, a case-based reasoning system was created to overcome the problem of the lack of mental health workers at Naimata Hospital. The system uses the dempster shafer method for the indexing process and cosine similarity to calculate the similarity value. This system diagnoses 9 types of mental disorders based on 125 symptoms. The output of the system is a diagnosis of the type of mental disorder suffered by the patient. Based on the test results on 90 data on a case basis by dividing the data into 10 folds, the system accuracy for similarity is 49.83% and indexing is 81.01%. The test was carried out another way, by dividing the data randomly into 3 groups, namely 9:1, 8:2 and 7:3 20 times. The first group got an average indexing of 85.21% and similarity 49.22%, the second group got an average indexing of 82.01% and similarity 48.84%, the third group got an average indexing of 78.82% and similarity 48.09%. The average accuracy is low due to the unbalanced case data for each type of disturbance.
Copyrights © 2022