UTILIZING NATURAL LANGUAGE PROCESSING IN CASE-BASED REASONING FOR DIAGNOSING AND MANAGING SCHIZOPHRENIA DISORDER

Some methods have been developed to help diagnose mental disorders and provide treatment. These methods are developed as an alternative to solve the problems of imbalance between mental health services and the number of psychiatrists/psychologists, for example, CBR systems, and expert systems. In most health services, the initial examination of patients with mental disorders is performed by non-specialist medical personnel. At a certain stage when the patient is unable to express the symptoms, the examining
officer is required to state the conditions in daily language. Based on this condition, the
paramedics will carry out the next diagnosis. In handling of case-based reasoning assisted diagnoses, the use of natural language as an expression of the patient’s condition is not
an input commonly used in the system. Hence that the natural language processing model becomes symptoms is needed. In this research, natural language processing was developed
to produce symptoms according to the patient’s condition. The results of this natural language processing will be inputted into a case-based reasoning system. The result of the natural language experiment using 124 data, shows a precision level of 88% and a recall of 67% for the original natural language text. For normalized natural language text, it yields a precision of 92%, and a recall of 78%. This provides input to a case-based reasoning system for diagnosing the type of schizophrenia disorder and its treatment