Classification of Prostate Cancer and Determination of Related Factors with Different Artificial Neural Network
Abstract
Objective: In this study, it is aimed to classify prostate cancer, compare the predictions of these two models and determine the factors associated with the disease by applying Multilayer Perceptron Neural Network (MLPNN) and Radial-Based Function Neural Network (RBFNN) methods on the open access Prostate cancer dataset.
Methods: In this study, the dataset named "Prostate Cancer Data Set" was used by obtaining from https://www.kaggle.com/sajidsaifi/prostate-cancer address. To classify prostate cancer, MLPNN and RBFNN methods, which are artificial neural network models, is used. The classification performance of the models was evaluated with the sensitivity, specificity, accuracy, negative predictive value and positive predictive value, which are among the classification performance metrics. Prostate cancer related factors were estimated by using MLPNN and RBFNN models.
Results: With the applied MLPNN model, performance metric values were obtained as AUC 0.937, Sensitivity 100%, accuracy 92.5%, Selectivity 84.6%, Positive predictive value 87.5% and Negative predictive value 100%. With the RBFNN model, the performance metric values were obtained as AUC 0.921, Sensitivity 83.3%, accuracy 86.6%, Selectivity 91.6%, Positive predictive value 93.7% and Negative predictive value 78.5%. When the effects of variables in the dataset in this study on prostate cancer are examined; The three most important variables for the MLPNN model were obtained as perimeter, area and compactness, respectively. For the RBFNN model, the three most important variables were obtained as perimeter, area and compactness, respectively.
Conclusion: It was seen that MLPNN and RBFNN models used in this study gave successful predictions in the classification of prostate cancer. In addition, estimating the significance values of factors associated with the disease with these classification models made it different from similar studies with the same dataset.
Methods: In this study, the dataset named "Prostate Cancer Data Set" was used by obtaining from https://www.kaggle.com/sajidsaifi/prostate-cancer address. To classify prostate cancer, MLPNN and RBFNN methods, which are artificial neural network models, is used. The classification performance of the models was evaluated with the sensitivity, specificity, accuracy, negative predictive value and positive predictive value, which are among the classification performance metrics. Prostate cancer related factors were estimated by using MLPNN and RBFNN models.
Results: With the applied MLPNN model, performance metric values were obtained as AUC 0.937, Sensitivity 100%, accuracy 92.5%, Selectivity 84.6%, Positive predictive value 87.5% and Negative predictive value 100%. With the RBFNN model, the performance metric values were obtained as AUC 0.921, Sensitivity 83.3%, accuracy 86.6%, Selectivity 91.6%, Positive predictive value 93.7% and Negative predictive value 78.5%. When the effects of variables in the dataset in this study on prostate cancer are examined; The three most important variables for the MLPNN model were obtained as perimeter, area and compactness, respectively. For the RBFNN model, the three most important variables were obtained as perimeter, area and compactness, respectively.
Conclusion: It was seen that MLPNN and RBFNN models used in this study gave successful predictions in the classification of prostate cancer. In addition, estimating the significance values of factors associated with the disease with these classification models made it different from similar studies with the same dataset.
Keywords
Prostate cancer, Multilayer perceptron neural network, Radial-based function neural network, Classification
References
- Ah T. New markers and Phi score in prostate cancer. Turk Urol Sem, 2012; 3: 61-69.
- Ari A & Berberler ME. Interface design for the solution of prediction and classification problems with artificial neural networks. Acta Infologica, 2017; 1: 55-73.
- Arslan AGUDT & Esatoglu AE. Systematic Compilation of studies investigating radical prostatectomy costs and cost effectiveness. Journal of Academic Value Studies,2018; 4: 143-162
- Badger TA, Segrin C, Figueredo AJ, Harrington J, Sheppard K, Passalacqua S, Pasvogel A & Bishop M. Psychosocial interventions to improve quality of life in prostate cancer survivors and their intimate or family partners. Quality of Life Research, 2011; 20: 833-844.
- Efe O & Kaynak O. Artificial neural networks and applications. Istanbul: Bogazici University Publishing House, 2000
- Elmas C. Artificial intelligence applications. Seckin Publishing,2016
- Etikan I, Cumurcu BE, Celikel FC & Erkorkmaz U. Artificial neural networks method and classification of psychiatric diagnoses using this method. Turkey Journal of Medical Sciences, 2009; 29: 314-320.
- Foster C, Bostwick D, Bonkhoff H, Damber JE, Van der Kwast T, Montironi R & Sakr W. Cellular and molecular pathology of prostate cancer precursors. Scandinavian Journal of Urology and Nephrology, 2000; 34: 19-43.
- Gemici E, Ardiclioglu M & Kocabas F. Modeling of flow in rivers with artificial intelligence methods. Erciyes University Institute of Science Journal of Science, 2013; 29: 135-143.
- Haykin S. Neural networks: a comprehensive foundation, Prentice-Hall Inc. Upper Saddle River, New Jersey, 1999; 7458: 161-175.