DSM-V Modelling as an Expert System Pilot in Classification of Insomnia Tendency Based on Time Range

Abstract

Insomnia is a form of sleep disorder. This study develops an expert system model that can help determine the tendency of insomnia based on the Diagnostic and Statistical Manual for Mental Disorders (DSM-V) guidelines. The forward chaining design method was used in this study because it is bottom-up by collecting facts from patients and concluded based on the DSM-V guidelines. The forward chaining method was chosen to test the hypothesis of the classification of insomnia tendencies. The factual information then acts as a knowledge base fed into computer programs that can generate system rules. In addition, tacit knowledge is used, as evidenced by O'Leary validation, to strengthen the validation of psychologist practitioners. There are three validation criteria: the accuracy of the knowledge base, completeness of the knowledge base, and condition-decision matches. The parameters used are based on complaints, dysfunction, time range, and other factors. The results of modeling and analysis of the rule system using the forward chaining method classify insomnia tendencies into three types based on time range: episodic, persistent, and recurring. The validation results carried out by practicing psychologists based on the analysis showed that the three rule systems were following the DSM-V guidelines and practical experience.