Skip to content

This Project aims to classify the diabetes disease using Artificial Neural Network (ANN) from scratch using only numpy libraries

License

Notifications You must be signed in to change notification settings

Komalsai234/Diabetes-Disease-Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Diabetes Disease Classification

This Project focuses on diabetes, a group of metabolic disorders characterized by high blood sugar levels over an extended period. These disorders can lead to various symptoms, including frequent urination, increased thirst, and heightened hunger. If left untreated, diabetes can result in numerous complications, such as diabetic ketoacidosis and hyperosmolar hyperglycemia, which can be life-threatening. Also, serious long-term complications include cardiovascular disease, stroke, chronic kidney disease, foot ulcers, and eye damage.

Objective

The objective of this project is to use Machine learning and Deep learning to classify one of the dangerous Diabetes disease and implement this using Neural Network used in this training from scratch and understand the Mathematical concepts like Forward propagation, Back propagation, and Activation Functions behind the Neural Networks.

Dataset

The Dataset is taken from Kaggle. It consists of several medical predictor variables and one target variable, Outcome. Predictor variables includes the number of pregnancies the patient has had, their BMI, insulin level, age, pregnancies, Blood Pressure (BP), Diabetes Pedigree Function, Skin Thickness.

Model used for training

  • Artificial Neural Network (ANN) implemented from scratch using python and numpy.

Model Evalution

  • Accuracy: 99.07%

Deployment

About

This Project aims to classify the diabetes disease using Artificial Neural Network (ANN) from scratch using only numpy libraries

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published