A hybrid classification method for heart disease prediction | |
| Author | Manne, Venkata Chandra Swaroop |
| Call Number | AIT RSPR no.IM-21-09 |
| Subject(s) | Heart--Diseases--Data processing Machine learning |
| Note | A research submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | Heart Disease Prediction is a very wide and vast study. There have been numerous methods and algorithms proposed so far and every study aims to bring a better accuracy by proposing different methods. This is one such study. In this study we suggested a unique Hybrid Classification method for Heart Disease Prediction where we use Random Forest for Feature Selection followed by Classification by 6 different classifiers, namely Decision Tree, Multi-Layer Perceptron, Gaussian Naive Bayes, Logistic Regression, Ensemble Soft and Ensemble Hard classifiers. These 6 classifiers are compared between each other in terms of Accuracy, Precision and Recall. To know whether the result obtained is better than previously proposed methods, we also did Feature Selection using Variance Threshold, Correlation Coefficient and found them to be ineffective. So. we also used Genetic Algorithm which gave some optimal results but still not as great as the proposed method. From the Proposed Method, the Ensemble soft Classifier gave the best result and using that model we developed a Web Application using Python Flask which predicts whether or not the patient has heart disease after giving the input values which are features selected by Random Forest. |
| Year | 2021 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Vatcharapon Esichaikul; |
| Examination Committee(s) | Attaphongse Taparugssanagorn;Tripathi, Nitin Kumar; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Research studies project report (M. Eng.) - Asian Institute of Technology, 2021 |