ÖZLEM AKAY, MEHMET TUNÇELİ
Experimental and Applied Medical Science - 2021;2(4):242-256
This study was considered as an application for the use of support vector machines (SVM), which is frequently used in many fields, in medical research and a prediction model was created with support vector machine regression (SVR) using medical study data. For determining the appropriate model and estimating the best parameter, estimation models were obtained with linear regression (LR), SVR, tuned-SVR that provide flexibility in terms of maximum error and penalty cost, and SVR using kernel functions. Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) values were calculated to evaluate the performance of the models. The obtained results showed that the SVR model using the radial kernel function provided the best prediction among the predictive models.
