Predictive Analytics of Comparison Fuzzy Modelling Towards Symptoms of Colorectal Cancer in Malaysia

Abstract

Colorectal cancer (CRC) is a cancer that begins in the colon and rectum of the human body and is the third leading cause of death among cancer patients. Colorectal cancer develops when cells in the body begin to proliferate uncontrollably with such symptoms. However, the high-risk symptoms of CRC in Malaysia are still ambiguous and unclear. The problem of using linear regression arises with the use of uncertain and imprecise data. Since the fuzzy set theory’s concept can deal with data not to a precise point value (uncertainty data), this study uses comparison fuzzy modelling as predictive analytics to predict the high-risk symptoms that contribute to the development of colorectal cancer in Malaysia. Secondary data of 180 colorectal cancer patients who received treatment in a general hospital with seventeen independent variables with different combinations of variable types were considered. Other than that, the parameter, error, and explanation for the model were included using two measurement statistical errors. Fuzzy linear regression with symmetric parameters found ovarian symptom is the high-risk symptom to develop colorectal cancer. The weightage value is 25.73, with the results of the least value of the mean square error (MSE) value being 98.212 and the root mean square error (RMSE) value being 9.910.