Heart attack prediction

Fill the form and predict whether you have a risk of hear attack.

We can improve this model by changing the model architecture, and adding more training data. At this level I wanted to showcase my work towards implementation and deployment of Machine Learning model.

Development summary

High-level architecture of the application

Model summary

In this project I have implemented following models.

1. Logistic Regression
2. Random Forest Classifier
3. Support Vector Classifier (SVC)
4. Decision Tree Classifier

I used GridSearchCV to search for optimal hyperparameters. Best performance model was the Support Vector Classifier.

Best params: {'svc__C': 0.5, 'svc__gamma': 'scale', 'svc__kernel': 'sigmoid'}
Best score:  0.8618421052631579
Best estimator:  
SVC('svc__C'=0.5, 'svc__gamma'='scale', 'svc__kernel'='sigmoid')