Predictive Analytics using Machine Learning Algorithm

Predictive Analytics using Machine Learning Algorithm

Use case - Stroke Prediction

Problem:-

• Stroke a major cause of death and serious long-term disability. A stroke can affect a person at any age, and it usually occurs suddenly. But, strokes can be prevented through therapeutic manipulation, and the modifiable risk factors are crucial. Today there is much collected data regarding cases of various diseases in medical science and it can be utilized to predict chances of stroke in a patient early.

Benefits:- 

• The insurance company and Hospital get major benefit of ML based stroke prediction.
• The ML based stroke prediction could help  hospital/health care system to predict strokes with high accuracy. For example, the development of simulated blood vessels provides us a different way of thinking about the causes of diseases. That is, the predicted result can help doctors to objectively diagnose, and doctors can provide a personalized warning and a lifestyle correction message
• Doctors can provide the appropriate treatment to patients early

Sample Dataset  - Metadata:-

sample data

ML –Stroke Prediction -Process:-

Cloud Deployment:-

Result Verification – Original Stroke vs Predicted Stroke:-

Key Learnings:-  

After doing above we will learn following:-

1. Python - Basics(syntax and usage)
2. Python –Libraries(Pandas, Numpy, Matplotlib, Bokeh)
3. Machine Learning – Understanding of supervised and unsupervised learning , different types of algorithms available.
4. Logistic Regression Algorithm application.
5. Random Forest Algorithm application.
6. GIT.
7. Hosting Python application on Amazon cloud (EC2).