Heart disease detection and classification

Objectives

1. to train machine learning models that can accurately predict whether a person may have a heart disease or not, leveraging the information provided in the Cardiovascular Disease dataset. 2. To Evaluate the performance

Socio-Economic Benefit

By developing reliable predictive models, healthcare professionals can enhance their ability to identify individuals at risk, implement targeted interventions, and ultimately improve cardiovascular health outcomes. The application of machine learning techniques to this dataset holds the potential to unlock valuable insights and contribute to the ongoing efforts to combat the global burden of cardiovascular diseases.

Methodologies

Data Exploration and Visualization Data Preprocessing and Normalisation Machine Learning Models: CatBoostClassifier LogisticRegression RidgeClassifier RandomForestClassifier GradientBoostingClassifier GaussianNB DecisionTreeClassifier XGBClassifier SVC deep learning: simple neural network deeper neural network deeper neural network with more layers Long Short-Term Memory (LSTM) Network Convolutional Neural Network (CNN) evaluation

Outcome

the Heart Failure Classification Project has demonstrated the potential of machine learning and deep learning techniques in predicting the presence of cardiovascular disease. Random-forest and the CNN model have emerged as the top performers.showcasing their effectiveness in this domain. By building upon these insights and exploring further avenues for improvement, the project holds the promise of contributing to the ongoing efforts to combat the global burden of cardiovascular diseases through early prognosis and targeted interventions.

Project Team Members

PROJECT GALLERY

Heart disease detection and classification

23 May, 2024 11:56 am