Dev-Goel / Stroke-Prediction

The project aims at predicting whether a patient is likely to get a stroke based on the input parameters like gender, age, BMI, average glucose level, various diseases like hypertension, heart disease, and smoking status. (Course: CSL2050 Pattern Recognition and Machine Learning)

Pattern Recognition and Machine Learning-CSL2050 Course Project

Course Instructor: Dr. Richa Singh

Stroke Prediction

The World Health Organization (WHO) identifies strokes as the second leading cause of death globally. A stroke happens when a person’s blood supply to their brain is interrupted or reduced, causing brain cells to die within minutes. It prevents the brain tissue from getting the oxygen and nutrients that it needs and is responsible for approximately 11% of total deaths.
The objective is to examine the use of various machine learning classification models on the given dataset that can aid in identifying the chance of stroke. The project aims at classifying the stroke based on the input parameters like gender, age, various diseases, and smoking status. Since, the project is related to medical domain multiple models were trained and their performance was compared considering the sensitivity, accuracy, as well as specificity scores.

Built With

• Scikit-learn - ML library used
• Pandas - Python Data Manipulation library used
• Seaborn - Data Visualization library used
• NumPy - Numerical Python library used
• Matplotlib - Data Visualization library used
• Imblearn - ML library used

Collaborators

Name	Year	Branch
Dev Goel	Sophomore	CSE
Ravi Ramavat	Sophomore	CSE
Sarvesh Kulkarni	Sophomore	EE