Expert System to Predict Acute Inflammation of Urinary Bladder and Nephritis Using Naïve Bayes Method

Bad life habits such as not consuming enough water and often delaying the urge to urinate are the causes of bladder-related diseases. In this study, a solution is given to overcome this problem by developing an expert system that can predict acute inflammation of nephritis and urine bladder disease using one of the classification algorithm that is often used and gets a lot of attention from researchers in predicting problems, namely Naïve Bayes. Data utilized include a list of symptoms that include patient fever, nausea, lumbar discomfort, urinary pushing (continuous urination, urethra burning and micturition pain, itching and urethra fluid swelling). The results of the diagnostic analysis consist of a confusion matrix and system accuracy values. The accuracy value of predicting acute urine bladder disease is 83% and acute nephritis of renal pelvis origin is 96%.