Skip to content

Luismbpr/medpredml01

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project: medpredml01


Creation and deployment of an application that predicts whether a set of inputs correspond or not to a disease.


Table of Contents


About

The initial project consisted of a set of models created using ML and DL Models based on different disease datasets acquired from different sources.

The initial project had to be separated into two separate projects. A project that takes numerical inputs and another project that takes images as inputs to predict whether an image corresponds to a disease or not.

This part of the project consists of models that require numerical inputs.

Creation and deployment of an application that predicts whether a set of inputs correspond or not to a disease.

  • [Back to Table of Contents](#table-of-contents

Project Procedure

  • Dataset:

    • Dataset Acquisition.

    • Dataset Analysis.

  • Model:

    • Model Creation.

    • Model Testing.

    • Model Deployment.

  • Application:

    • Application Creation.

    • Application Testing (Local and External).

    • Application Modification (Local and External).

    • Application Deployment (Local and External).

  • Documentation:

    • Creation of Required Documentation.


List of Diseases


The diseases that this app can predict are the following:


  • Cancer.

  • Diabetes.

  • Heart Disease.

  • Liver Disease.

  • Kidney Disease.


* [Back to Table of Contents](#table-of-contents)

Dataset Information

The information for the acquisition of each disease was gathered by different entities and with different methods.

Each Dataset contains specific information and whether a user has or not the disease.

The sources used for the acquisition of the datasets are the following


Cancer Dataset Information

  • Taken from: UCI.

  • For more information about cancer please visit: cancer.net).


Diabetes Dataset Information

  • Sources:
  • Donor of database: Vincent Sigillito ([email protected]) Research Center, RMI Group Leader Applied Physics Laboratory The Johns Hopkins University Johns Hopkins Road Laurel, MD 20707 (301) 953-6231.
  • (NIDDK) National Institute of Diabetes and Digestive and Kidney Diseases

Heart Disease Dataset Information

  • Taken from: UCI.

  • For more information about heart disease please visit the following websites:

  • cdc.gov.

  • heart.org.


Kidney Disease Dataset Information

  • Taken from: UCI.

  • For more information kidney disease please visit the following websites:

  • NIDDK.


Liver Disease Dataset Information


Project Deployment


Resources

Different languages and resources where used in order for this application to be deployed.

Languages Used

  • Python
    • Data Analysis.

    • Model Creation.

    • Model Deployment.

  • HTML and CSS
    • Website - Front-End for model deployment.


Other Resources

  • Flask.

  • Gunicorn.

  • Heroku.



Other Information

Medical Web App based on:

The model creation decision was done taking in consideration various factors, some of them involving the app deployment on the web.

- Based on Shobhit Srivastava's and Karan Mehra's Project

- For further questions about the way this project was made or to see other projects made by me please click here

- For further questions about the way this project was made or for further inquiries e click here



Notes

  • This project was not endorsed by any company.

  • Special gratitude to all the people who make the datasets and all the information available.

  • The application and information displayed here is for educational purposes. The accuracy of the models varies and will make some prediction errors. This should not be taken as medical advice.


About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published