https://github.com/Vice777/SAFE-HEART

Classify the chances of having a Heart Attack based on your Heart's Condition.
https://github.com/Vice777/SAFE-HEART

kaggle machine-learning matplotlib mlfromscratch mlp-classifier multilayer-perceptron-network numpy pandas pickle streamlit streamlit-webapp

Last synced: 4 months ago
JSON representation

Classify the chances of having a Heart Attack based on your Heart's Condition.

• Host: GitHub
• URL: https://github.com/Vice777/SAFE-HEART
• Owner: Vice777
• Created: 2022-08-04T14:41:08.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-10-22T08:47:18.000Z (over 2 years ago)
• Last Synced: 2024-07-29T20:16:14.128Z (6 months ago)
• Topics: kaggle, machine-learning, matplotlib, mlfromscratch, mlp-classifier, multilayer-perceptron-network, numpy, pandas, pickle, streamlit, streamlit-webapp
• Language: Jupyter Notebook
• Homepage: https://vice777-safe-heart-classifier-multilayer-perceptron--app-idf5su.streamlitapp.com/
• Size: 3.62 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Safe-Heart-Classifier-Multi-Layer-Perceptron-from-Scratch

LINK : https://vice777-safe-heart-classifier-multilayer-perceptron--app-idf5su.streamlitapp.com/

___



## Description:


Classify the chances of having a Heart Attack based on your Heart's Condition.


In this end-to-end Machine Learning project-tutorial, I have created and trained Multi-Layer model from scratch, using NumPy.


Furthermore, the model with the best accuracy is embedded in the web-app developed using streamlit module for the purpose of classification of your Heart's Condition.   


___

Understanding the Problem Statement


This project uses the popular Heart Attack Analysis & Prediction Dataset  for training the model and making predictions.


For the purpose of prediction and classification, the features given in the table below are used. 


Detailed description about the features is provided within the table.



  

     

        Features 

        Description 

     

     

        Age  

        Age of the patient 

     

     

        Sex  

        Sex of the patient 

     

     

        cp  

        Chest Pain type chest pain type: 

            
 

                
Value 1: Typical angina
 

                
Value 2: Atypical angina
 

                
Value 3: Non-anginal pain
 

                
Value 4: Asymptomatic
 

            
 

         

     

     

        trtbps  

        Resting Blood Pressure (in mm Hg) 

     

     

        chol  

        Cholestoral in mg/dl fetched via BMI Sensor 

     

     

        fbs  

         

            (Fasting blood sugar > 120 mg/dl)  

            
1 = true
 

            
0 = false 
 

         

     

     

        restecg 

         

            
 

                
Value 0: Normal
 

                
Value 1: Having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV)
 

                
Value 2: Showing probable or definite left ventricular hypertrophy by Estes criteria
 

             

        
 

     

     

        thalach  

        Maximum Heart Rate achieved 

     

     

        exang 

        Exercise induced angina                         

        
1 = yes
 

            
0 = no
 

         

     

     

        Oldpeak  

        ST depression induced by exercise relative to rest  

     

     

        slp  

        Peak exercise ST segment Slop 

            
 0 = Downsloping
 

            
 1 = Flat
 

            
 2 = Upsloping
 

         

     

     

        caa  

        The number of major vessels (0–3) 

     

     

        thall  

        A blood disorder called Thalassemia 

            
 Value 1: fixed defect (no blood flow in some part of the heart)
 

            
 Value 2: normal blood flow
 

            
 Value 3: reversible defect (a blood flow is observed but it is not normal)
 

         

     

     

        target  

        Percentage of deliverable volume 

            
 0= less chance of heart attack
 

            
 1= more chance of heart attack
 

         

     


 


 

___

Key Project Takeaways

This project provided hands-on experience in real-time data handling and working behind Neural Networks :



  
Data preprocessing and cleaning for training and testing the data

  
Building an efficient Neural Network (Multi-Layer Perceptron) from scratch using NumPy

  
Mathematics behind  Activation Functions and Gradient Losses



  
Web-app development using Streamlit