Cardiovascular disease is primarily caused by risk factors like high blood pressure, unhealthy diet, and physical inactivity. As the leading cause of death globally, it accounts for approximately 17.9 million fatalities annually, representing 31% of all global deaths. This makes cardiovascular disease the most significant threat to human health worldwide.
Although early detection can significantly improve outcomes, insufficient screening methods and delayed diagnosis often lead to preventable complications. Therefore, developing rapid and accurate diagnostic tools is crucial for effective prevention and treatment of cardiovascular conditions.
To address this challenge, we utilize Singa to develop a machine learning model for cardiovascular disease risk prediction. The training dataset is sourced from Kaggle https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset. You can download the dataset, pass the path to the script, and then you can run the program by using the script.
cardiovascular.py in the healthcare/data directory is the scripts for preprocessing Cardiovascular Disease datasets.
cardionet.py in the healthcare/models directory includes the MLP model construction codes.
train.py is the training script, which controls the training flow by doing BackPropagation and SGD update.
python train.py cardionet -dir pathToDataset