ANALYSIS OF MEDICATION USED PATTERNS IN PATIENTS WITH NEUROLEPTIC MALIGNANT SYNDROME BY ASSOCIATION RULES TECHNIQUE

Abstract

Objective: The purpose of this study was to find out the relationship of the pattern of medication use in schizophrenic patients with Neuroleptic Malignant Syndrome (NMS) by using data mining tasks in term of association rules technique.

Material and Method: This was a retrospective study from data base and inpatients medical records of 9 patients who was diagnosed as Neuroleptic Malignant Syndrome (NMS) according to ICD 10: G21.0 at Somdet Chaopraya Institute of Psychiatry from 1st August 2005 to 31st December 2013. This association rules by Weka program which is a collection of machine learning algorithms for data mining tasks was used to analyze.

Results: 41 schizophrenic patients diagnosed as NMS were identified and most of them were males (58.54%). 5 pattern of frequency used medication pattern were found which were perphenazine and trihexyphenidyl, diazepam and trihexyphenidyl, chlorpromazine and trihexyphenidyl, perphenazine + diazepam and trihexyphenidyl, chlorpromazine and trihexyphenidyl. The most frequency used of medication pattern was perphenazine and trihexyphenidyl (60.9%).

Conclusion: NMS in Somdet Chaopraya Institute of Psychiatry had found 41 patients from 29,792 inpatients (0.14%). In addition, perphenazine and trihexyphenidyl was the most frequency used medication pattern with NMS. However, two items of typical antipsychotic drug group (using this drug group is risk for NMS occurrence) which were perphenazine or chlorpromazine and trihexyphenidyl were used together. Therefore, clinician should be concerned about NMS occurrence, especially using this patterns together.