In most cases, heart disease diagnosis depends on a complex combination of clinical and pathological data. Because of this complexity, there is a significant amount of interest among clinical professionals and researchers regarding efficient and accurate heart disease prediction. In this project, we develop a heart disease prediction system that can assist medical professionals in predicting heart disease status based on the clinical data of patients.
The system will consist of multiple features, including an input clinical data section, an ROC curve display section, and a prediction performance display section (execute time, accuracy, sensitivity, specificity, and predict result). The project also discusses the pre-processing methods, classifier performances, and evaluation metrics.
We have investigated the accuracy levels of various machine learning techniques such as Support Vector Machines (SVM), K-nearest neighbour (KNN), Naïve Bayes, and Decision Trees (DT). The system developed in this study proves to be a novel approach that can be used in the classification of heart disease.
This project aims to predict heart disease using machine learning techniques. The code uses various plotting libraries, metrics for classification, scaler libraries, and model-building libraries, such as matplotlib, numpy, pandas, seaborn, scikit-learn, and more.
The README file includes sections for exploratory data analysis, feature analysis, data visualization, feature engineering, feature scaling, model implementation, and evaluation. It covers the process of importing the dataset, analyzing features, visualizing data, preprocessing, implementing machine learning models, and evaluating model performance using metrics like accuracy, confusion matrix, ROC curve, and AUC score.
The code utilizes popular Python libraries like matplotlib, numpy, pandas, seaborn, and scikit-learn for data manipulation, visualization, and machine learning model creation.
The project involves working with a dataset titled "heart.csv" to predict heart disease. There is comprehensive code for data exploration, visualization, feature engineering, feature scaling, and the implementation of K-Nearest Neighbor (KNN), Naive Bayes Classifier, Decision Tree, and Support Vector Machine (SVM) models.
- Exploratory Data Analysis: Analyzing dataset size, information, statistical description, correlation between features and target variable, and visualizing features.
- Feature Analysis: Analyzing age, sex, chest pain, maximum heart rate achieved, thalassemia, and acquired heart disease features.
- Model Implementation: Implementing K-Nearest Neighbor (KNN), Naive Bayes Classifier, Decision Tree, and Support Vector Machine (SVM) models.
- Evaluation: Evaluating model performance using accuracy, confusion matrix, ROC curve, and AUC score.
This project provides a comprehensive guide to predicting heart disease using machine learning techniques. It covers every aspect of the development process, from data exploration to model evaluation.