Measuring the Heart Attack Possibility using Different Types of Machine Learning Algorithms

Aim:

            To apply machine learning techniques result in improving the accuracy in the prediction of cardiovascular disease.

Abstract:

            Heart disease is one of the most significant problem is arising in the world today. Cardiovascular disease prediction is a critical challenge in the area of clinical data analysis. Machine learning (ML) has been showing an effective assistance in making decisions and predictions from the large quantity of data produced by the healthcare industries and hospitals. This project proposes a prediction model to predict whether a person has a heart disease or not and to provide awareness or diagnosis on the risk to the patient. The prediction model is projected with mixtures of various options and a number of other classifications techniques. This is done by comparing the accuracies of different algorithms to the separate results of SVM, KNN, Decision Tree and Random Forest and uses the algorithm with high accuracy for prediction. Our goal is to enhance the performance of the model by removing unnecessary and insignificant attributes from the dataset and only collecting those that are most informative and useful for the classification task. Thus the main focus of the system is to make use data analytics to predict the presence of the disease or not.

Introduction:

            Heart is an important organ of the human body. It pumps blood to every part of our anatomy. If it fails to function correctly, then the brain and various other organs will stop working, and within few minutes, the person will die. Healthcare means the maintenance or advancement of health through the prevention and diagnosis of people. Nowadays, healthcare is increasing day by day due to lifestyle and hereditary. Cardiovascular disease has become the deadliest enemy. A person with cardiovascular disease cannot be cured simply. So, diagnosing patients at the correct time is the toughest work in the medical industry and needs to be diagnosed at initial stages to reduce the risk on the patient in the future. Every human body possesses different numbers for blood pressure, cholesterol, and pulse rate. But the normal values would be, blood pressure is 120/80, cholesterol is 200 mg/dl and pulse rate is 72. So combining these machine learning algorithms with medical data sources is useful. This paper suggests different machine learning methods that are useful for forecasting the uncertainty levels of cardiovascular disease for a person depending on the collected attributes.

Proposed System:

          In our proposed system, we use multiple algorithms for high accurate level of prediction. The algorithms used in our proposed systems are Support Vector, KNN, Decision Tree and Random Forest machine learning technique for heart disease prediction of significant features. ML process starts from a pre-processing data phase followed by feature selection based on data cleaning, classification of modeling, performance evaluation, and the results with improved accuracy. After creating a trained dataset, User should register on android app. After login to the app, user will give the input. That input passes to firebase. Firebase acts as an intermediate between trained dataset and user. After the prediction, the predicted value passes to the Firebase. That Firebase gives the predict value to the user on android app via notification.