A Machine Learning Approach to Heart Attack Prediction

Computer Engineering

In today’s modern world cardiovascular disease is the most lethal one. This disease assaults an individual right away that may make surprising ramifications for the human life. So diagnosing patients accurately on time is the most testing task for the medicinal crew. The coronary illness treatment is very high and not reasonable by the vast majority of the patients especially in India. The examination extension is to build up an early forecast treatment utilizing information mining advances. Nowadays every hospital keeps the periodical medical reports of cardiovascular patients through a few clinic management gadget to manage their health-care. The data mining techniques namely decision tree and random forest are used to analyze heart attack dataset where classification of more common symptoms related to heart attack is done using c4.5 decision tree algorithm, alongside, random forest is applied to boost the certainty of the classification result of heart attack prediction.A decision tree is used for function selection system and SVM classifier for class. In this system various data mining technologies are applied to make a proactive approach against failures in early predictions diagnosis of the disease.classification accuracy of SVM algorithm was better than DT algorithm.C 4.5 generates a decision tree where each node splits the classes based on the gain of information. The overall accuracy of the SVM using four kernel types was above 73% and the overall accuracy of the DT method was 69%. We proposed an automated system for medical diagnosis that would enhance medical care and reduce cost. Our intent is to provide a ubiquitous service that is both feasible, sustainable and which also make people to assess their risk for heart attack at that point of time or later.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.