burakkahveci/Stroke-Risk-Prediction-with-Machine-Learning

Stroke Risk Prediction with Machine Learning Models

Introduction

• A stroke is a serious life-threatening medical condition that happens when the blood supply to part of the brain is cut off.

Signs and symptoms of stroke include:

• Trouble speaking and understanding what others are saying. You may experience confusion, slur your words or have difficulty understanding speech.
• Problems seeing in one or both eyes. You may suddenly have blurred or blackened vision in one or both eyes, or you may see double.
• Trouble walking. You may stumble or lose your balance. You may also have sudden dizziness or a loss of coordination.

Dataset Informations

• Name: Stroke Prediction Dataset
• Feautres: 11 clinical features for predicting stroke events
• Observation: The data contains 5110 observations

Content

1. Load and Review Dataset
   • Reading Dataset & Pre-examination
   • Basic Visualization
2. Data Preprocessing & Variables types adjustment
3. Train & Test Split
4. Machine Learning Models
   • General Informations
   • Logistic Regression (LR)
   • Naive Bayesian (NB)
   • K-nearest neighbors (KNN)
   • Support Vector Machine (SVM)
   • Non-Linear SVM (Radial Basis Function)
   • Artificial Neural Networks (ANN)
   • Classification And Regression Tree (CART)
   • Random Forest (RF)
   • Gradient Boosting Machines (GBM)
5. Evaluation of Results
6. Creation of Prediction Funtion
7. Artificial Patients Profiles for Prection Function
8. Stroke Risk Prediction of Patients

Results

Tables

Models	Results (Accuracy)
Logistic Regression	0.944
Naive Bayesian	0.870
K-Nearest Neighbors	0.946
Support Vector Machines	0.946
Non Linear SVM	0.946
Artificial Neural Networks	0.946
CART	0.943
Random Forest	0.946
Gradient Boosting	0.946

Artificial Patients Profiles

Stroke Risk Prediction of Artificial Patients

Contact

Linkedin - Kaggle - Mail - Instagram