Search published articles


Showing 2 results for Support Vector Machine
Evaluation of Data Mining Algorithms for Detection of Liver Disease
Mohammad Reza Shahraki , Mahboubeh Mesgar,
Volume 13, Issue 1 (5-2019)
Abstract
Background and Aim: The liver, as one of the largest internal organs in the body, is responsible for many vital functions including purifying and purifying blood, regulating the body's hormones, preserving glucose, and the body. Therefore, disruptions in the functioning of these problems will sometimes be irreparable. Early prediction of these diseases will help their early and effective treatment. Regarding the importance of liver diseases and increasing number of patients, the present study, using data mining algorithms, aimed to predict liver disease.
Materials and Methods: This descriptive study was performed using 721 data from liver patient in zahedan. In this study, after preprocessing data, data mining techniques such as SVM: Support Vector Machine, CHAID, Exhaustive CHAID and boosting C5.0, data were analyzed using IBM SPSS Modeler 18 data mining software.
Result: The validity obtained for boosting C5.0 94/09, for Exhaustive CHAID algorithm 88/71, for SVM 87/09, for CHAID algorithm 85/47 prediction of liver disease. the boosting C5.0 algorithm showed a better performance of this algorithm among other algorithms.
Conclusion: According to the rules created by boosting C5.0 algorithm, for a new sample, one can predict the likelihood of a person for developing liver disease with high precision.

Diagnosing Breast Cancer by Machine Learning
Mr Kasra Dolatkhahi, Adel Azar, Tooraj Karimi, Mohammad Hadizadeh,
Volume 15, Issue 4 (10-2021)
Abstract
Background and Aim: Cancer and in particular Breast cancer are among the diseases that have the highest mortality rate in Iran after heart disease. The accurate prognosis for Breast cancer is important, and the presence of various symptoms and features of this disease makes it difficult for doctors to diagnose. This study aimed to identify the factors affecting Breast cancer, modeling and ultimately diagnosing the risk of Breast cancer.
Materials and Methods: In the present study, first, by content analysis and library studies, the effective factors in Breast cancer were identified, then with the help of a team of experts consisting of physicians and subspecialists in Breast oncology and Breast surgery; With the help of the Delphi method, the factors were adjusted and 26 final factors that were numerically correct and string based on local and climatic conditions were approved. Then, according to the final factors and based on the medical records of 5208 patients in the Cancer Research Center of Shahid Beheshti University of medical sciences, to diagnose cancer, Decision Tree, Random Forest, and Support Vector Machine methods were used as machine learning methods.
Results: In the first step, by content analysis method, 29 effective factors in Breast cancer were identified. Then, taking into account the indigenous and climatic conditions and using the Delphi method and also using the opinions of 18 Experts during three years, 26 factors were finalized. In the final step, using the medical records of the patients and the results obtained from the three methods mentioned, random forest, had the highest accuracy of 94.75% and precision of 97.26% in diagnosing Breast cancer. It has been noted that, compared to other similar studies, indigenous databases have been exploited, the accuracy obtained has been very close to previous studies, and in many cases much better.
Conclusion: Using the random forest method and taking advantage of the factors affecting Breast cancer, the ability to diagnose cancer has been provided with greatest accuracy.
 

Page 1 from 1     

© 2024 , Tehran University of Medical Sciences, CC BY-NC 4.0

Designed & Developed by: Yektaweb