Mohammad Momeny , Ali Mohammad Latif , Mehdi Agha Sarram , Kazem Hajmirzazade , Sorayya Gharravi , Naghiboalghara Seyed Mahammad,
Volume 6, Issue 1 (6-2019)
Abstract
Introduction: Diabetes or diabetes mellitus is a metabolic disorder in body when the body does not produce insulin, and produced insulin cannot function normally. The presence of various signs and symptoms of this disease makes it difficult for doctors to diagnose. Data mining allows analysis of patients’ clinical data for medical decision making. The aim of this study was to provide a model for increasing the accuracy of diabetes prediction.
Method: In this study, the medical records of 1151 patients with diabetes were studied, with 19 features. Patients’ information were collected from the UCI standard database. Each patient has been followed for at least one year. Genetic Algorithm (GA) and the nearest neighbor algorithm were used to provide diabetes prediction model.
Results: It was revealed that the prediction accuracy of the proposed model equals 0.76. Also, for the methods of Naïve Bayes, Multi-layer perceptron (MLP) neural network, and support vector machine (SVM), the prediction accuracy was 0.62, 0.65, and 0.75, respectively.
Conclusion: In predicting diabetes, the proposed model has the lowest error rate and the highest accuracy compared to the other models. Naïve Bayes method has the highest error rate and the lowest accuracy.
Setayesh Sadeghi, Amin Golabpour,
Volume 6, Issue 4 (3-2020)
Abstract
Introduction: Breast cancer is one of the most common types of cancer and the most common type of malignancy in women, which has been growing in recent years. Patients with this disease have a chance of recurrence. Many factors reduce or increase this probability. Data mining is one of the methods used to detect or anticipate cancers, and one of its most common uses is to predict the recurrence of breast cancer.
Cases and Methods: Out of 699 patients with breast cancer, 458 (66%) of them did not relapse and 241 (34%) of their cancer recurred. This information was collected from 91 to 94 years of history of patients with breast cancer in the academic Jihad. In this study, the combination of two nearest neighboring algorithms and a genetic algorithm are proposed to predict the relapse of patients with breast cancer. First, the nearest neighboring algorithm is presented to predict the recurrence of breast cancer. Then, using the genetic algorithm, the dependent variables are reduced to make the model more appropriate.
Results: The number of dependent variables is 14 variables, which is reduced by 6 genetic algorithms to better predict the model. To evaluate the model, the health parameter is used, which is 77.14% for the proposed model, which could not be more suitable for other methods.
Conclusion: In this study, the proposed algorithm was examined with other predictive methods and it was determined that the proposed algorithm is better.
