Skip to content

Stroke Disease Prediction classifies a person with Stroke Disease and a healthy person based on the input dataset. This package can be imported into any application for adding security features. Input data is preprocessed and is given to over 7 models, where a maximum accuracy of 99.4% is achieved.

License

Notifications You must be signed in to change notification settings

NIRMAL1508/STROKE-DISEASE-PREDICTION

Repository files navigation

ML_Project

Deplying Machine Learning Algorithms to predict the occurance of stroke in a person.

Problem Statement

Stroke is the second largest cause of mortality worldwide and remains an enormous health burden for individuals. Hypertension, heart illness, diabetes and dysregulation of glucose metabolism, atrial fibrillation, and lifestyle variables are some of the controllable risk factors of stroke. The objective of our project is to successfully predict a person’s likelihood of suffering a stroke based on potentially modifiable risk variables by applying machine learning methods to big data sets. This may be done by analyzing medical records using machine learning models to find patterns that are related to the risk of stroke.

About the dataset

The dataset we use consists of 5111 rows and 12 columns.
● Id : Unique Identifier.
● Gender : "Male", "Female" or "Other".
● Age : Age of the patient.
● Hypertension : 1 if the patient has hypertension or 0 if not.
● Heart_disease : 1 if the patient has a heart disease or 0 if not.
● Ever_married : "No" or "Yes".
● Work_type : "Never_worked", "Children", "Govt_job", "Private", “Self_emp".
● Residence_type : "Rural" or "Urban".
● Avg_glucose_level : Average glucose level in blood.
● Bmi : body mass index.
● Smoking_status : "Formerly smoked", "Never smoked", "Smokes" or "Unknown".
● Stroke : 1 if the patient will have a stroke or 0 if not.

ML Algorithms Used

Decision Trees
Random Forest
Logistic Regression
Naive Bayes
SVM
KNN
Neural Networks MLP

Libraries and Frameworks Needed

scikit-learn
numpy
mathplotlib
seaborn

SETUP

1.Download the repository usiing the "git clone" command.
2.Upload the "stroke_prediction.ipynb" file to google colab.
3.Upload the "healthcare-dataset-stroke-data.csv" file to the runtime.
4.Copy and Paste the relative path of the dataset to """ stroke_data=pd.read_csv('/healthcare-dataset-stroke-data.csv') """
5.Run the colab file.

About

Stroke Disease Prediction classifies a person with Stroke Disease and a healthy person based on the input dataset. This package can be imported into any application for adding security features. Input data is preprocessed and is given to over 7 models, where a maximum accuracy of 99.4% is achieved.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published