Heart Disease Prediction using machine learning

It may have occurred to you or a loved one on several occasions that you or they require emergency medical assistance, but they are unavailable due to a variety of factors. The Heart Disease Prediction application is a project aimed at providing end-user support and online consultation. We propose a

Project Title

Heart Disease Prediction using machine learning

Project Area of Specialization

Artificial Intelligence

Project Summary

It may have occurred to you or a loved one on several occasions that you or they require emergency medical assistance, but they are unavailable due to a variety of factors. The Heart Disease Prediction application is a project aimed at providing end-user support and online consultation. We propose a web application that allows users to receive real-time guidance on their heart illness via an online intelligent system. The program is loaded with numerous facts as well as the heart illness that goes along with them. Users may use the app to share their heart-related difficulties. It then examines the user's personal information to see if there are any illnesses that might be linked to it. Here, we employ some advanced data mining algorithms to determine the most accurate ailment that may be linked to the patient's information. Based on different attributes involved in the dataset. User can search for doctor’s help at any point of time. User can talk about their Heart Disease and get instant diagnosis. Doctors get more clients online. Very useful in case of emergency.

Project Objectives

The objective of this study is to effectively predict if the patient suffers from heart disease. The health professional enters the input values from the patient's health report. The data is fed into model which predicts the probability of having heart disease. The health-care industry collects massive volumes of data that may include some hidden information that might help decision-makers make better judgments. Advanced data mining techniques are utilized to provide relevant findings and make smart data judgments. In this study, a neural network is used to construct an effective heart disease prediction system (EHDPS) for forecasting the risk level of heart disease. Age, sex, blood pressure, cholesterol, and obesity are among the 15 medical factors used by the algorithm to make predictions. The EHDPS is a test that predicts whether or not a patient may develop heart disease. It enables considerable knowledge to be established, such as correlations between medical variables connected to heart disease and patterns. As a training procedure, we used a multilayer perceptron neural network with backpropagation. The collected outcomes have demonstrated.

Project Implementation Method

The health-care industry collects massive volumes of data that may include some hidden information that might help decision-makers make better judgments. Advanced data mining techniques are utilized to provide relevant findings and make smart data judgments. In this study, a neural network is used to construct an effective heart disease prediction system. The Dataset is Preprocessed
There are no null values in the dataset. However, there were a lot of outliers to deal with, and the sample wasn't spread evenly. There were two techniques employed. One that did not use outliers or a feature selection procedure, instead putting the data directly to machine learning algorithms, yielded unfavorable results. However, after leveraging the dataset's normal distribution to overcome the problem, Examining the Data's Distribution.
When it comes to predicting or classifying an issue, the distribution of the data is crucial. We can observe that heart illness occurred 54.46 percent of the time in the dataset, whereas no heart disease occurred 45.54 percent of the time. As a result, we must balance the dataset to avoid overfitting. This will aid the model's search for a pattern in the data that is linked to heart disease.

Benefits of the Project

By applying different machine learning algorithms and then using deep learning to see what difference comes when it is applied to the data, three approaches were used. In the first approach, normal dataset which is acquired is directly used for classification, and in the second approach, the data with feature selection are taken care of and there is no outliers detection. The results which are achieved are quite promising and then in the third approach the dataset was normalized taking care of the outliers and feature selection; the results achieved are much better than the previous techniques, and when compared with other research accuracies, our results are quite promising, Additionally, the calculation time was lowered, which is beneficial for deploying a model. It was also discovered that the dataset should be normalized; otherwise, the training model might become over fitted, resulting in insufficient accuracy when a model is evaluated for real-world data issues that differ greatly from the dataset on which the model was trained. It was also discovered that statistical analysis is crucial when analyzing a dataset, which should have a Gaussian distribution, and that outlier detection is also vital, which is handled using the Isolation Forest approach. The problem here is that the dataset's sample size is quite small. If you have a huge dataset.

Technical Details of Final Deliverable

By applying the first approach, the accuracy achieved by the Random Forest is 76.7%, Logistic Regression is 83.64%, K-Neighbors is 82.27%, Support Vector Machine is 84.09%, Decision Tree is 75.0%, and XGBoost is 70.0%. SVM is having the highest accuracy here which is achieved by using the cross-validation and grid search for finding the best parameters or in other words doing the hyper parameter tuning. Then after machine learning, deep learning is applied by using the sequential model approach. In the model, 128 neurons are used and the activation function used is ReLU, and in the output layer which is a single class prediction problem, the sigmoid activation function is used, with loss as binary. After selecting the features (feature selection) and scaling the data as there are outliers, the robust standard scalar is used; it is used when the dataset is having certain outliers. In the second approach, the accuracy achieved by Random Forest is 88%, the Logistic Regression is 85.9%, K-Neighbors is 79.69%, Support Vector Machine is 84.26%, the Decision Tree is 76.35%, and XGBoost is 71.1%. Here the Random Forest is the clear winner with a precision of 88.4% and an F1 score of 86.5%.Then deep learning is applied with the same parameters before and the accuracy achieved is 86.8%, and the evaluation accuracy is 81.9%, which is better than the first approach.

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com