Loading...

Application of Data Mining Techniques in Diagnosis & Prediction of Heart Disease

jahangiri, Sonia | 2018

419 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51698 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Akhavan Niaki, Taghi
  7. Abstract:
  8. Nowadays, data is the most important asset for health organizations in which the process of collecting, storing and analyzing of data leads to success of health organizations. Many companies have turned to data mining for the beneficial use of these data. The main purpose of data mining is to obtain useful knowledge from existing data. One of the diseases that is very significant for data miners is cardiovascular disease. Cardiovascular disease is the most important cause of death in the world. Therefore, it is necessary to improve the diagnostic and predictive measures of these patients. In this study, a database containing of characteristics of patients with chest pain who referred to emergency department of Loghman Hospital in Tehran, prepared. First of all pre-process step were taken On the features of the patients from Loghman Hospital and characteristics of the patients from the Cleveland Clinic Foundation. Then, five different algorithms including decision tree, naïve bayes, modified Bayes, KNN and LDA were used to classify existing data. Since, it is not possible to make a definitive statement about the normality of the data, the assumption of the normality for the characteristics in the naïve bayes method is not correct. To improve the performance of this algorithm, an algorithm was introduced including the choice of conditional distribution of each features and the estimation of their parameters. Different evaluation criteria for the modified Bayesian method and the other algorithms have been calculated. Finally, a multi-criteria decision-making technique was used to rank these methods and to select the best algorithm. The best-worst method for weighting the criteria was used and the TOPSIS method was used to rank them. The results of this method show that the modified Bayesian, LDA, decision tree, KNN and naïve bayes for the UCI site data set and the modified Bayesian, naïve bayes, LDA, decision tree, and KNN for the Loghman Hospital data set are preferred respectively
  9. Keywords:
  10. Data Mining ; Classification ; Multicriteria Decision Making ; Heart Diseases ; Health Care System

 Digital Object List

 Bookmark

No TOC