Detection of Coronary Heart Disease by Data Mining Methods Using Clinical Data

Authors : Burak Yağin

Pages : 104-109

View : 44 | Download : 21

Publication Date : 2022-12-31

Article Type : Research

Abstract :Objective: Cervical cancer is the fourth most prevalent malignancy among women worldwide. Low- and middle-income countries are much more burdened than high-income nations. Therefore, the need to develop new diagnostic techniques to predict the course of the disease and the prognosis of this malignancy has increased. In this study, cervical cancer will be classified to create an accurate diagnostic predictive model using the machine learning method The Multilayer Perceptron (MLPNN) and Radial Based ANN (RBFNN), and disease-related risk factors will be determined. Methods: This current study considered the open-access data set of patients that cervical cancer and no-cervical cancer samples. For this purpose, data from 72 patients were included. The data set was divided as 80:20 as a training and test dataset. MLPNN and RBFNN were used for the classification Accuracy, specificity, AUC, positive predictive value, and negative predictive value performance metrics were evaluated for model performance. Results: Among the performance criteria in the test stage obtained from the RBFNN model that has the best classification result; accuracy, specificity, AUC, positive predictive value, and negative predictive value were obtained as 92.3%, 100.0%, 96.5%, 100.0%, and 91.6%, respectively. According to the variable importance obtained as a result of the model, the variables most associated with the diagnosis were behavior sexual risk, empowerment abilities, and motivation strength, respectively. Conclusion: The applied machine learning model successfully classified cervical cancer and created a highly accurate diagnostic prediction model. With the parameters determined as a result of the modeling, the clinician will be able to simplify and facilitate the decision-making process for the diagnosis of cervical cancer.
Keywords : Heart disease, artificial intelligence, data mining, random forest, parameter optimization