Skip to content

Varion AI is an AI research group dedicated to integrating ICP's decentralized AI into healthcare systems.

Notifications You must be signed in to change notification settings

VarionAI/varion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Varion AI

Overview

Varion AI is an AI research group dedicated to integrating ICP's decentralized AI into healthcare systems. Our mission is to assess the capabilities and reliability of ICP's DeAI and explore its potential to enhance the modern healthcare systems and a vision of how decentralized technologies can address these issues.

Powered by the Internet Computer Protocol, Varion AI provides a secure, scalable, and decentralized infrastructure, seamlessly integrating with centralized infrastructure to bridge between Web2 and Web3 data.

Deployment: https://bnm7h-gqaaa-aaaap-qht7a-cai.icp0.io/

Features

  • Cardiovascular Disease Prediction: Utilizes DeAI to analyze patient data and predict heart-related risks by evaluating metrics such as heart rate, blood pressure, oxygen saturation, respiratory rate, and temperature. This helps identify high-risk patients for timely interventions, reducing cardiovascular morbidity and mortality rates.
  • Real-Time Monitoring Dashboard: The user-friendly dashboard enables healthcare professionals to view and analyze patient data in real-time, allowing hospitals to update the spreadsheet with new ECG data every minute. This continuous updating ensures that the dashboard is consistently refreshed with the most recent information.
  • Patient Management Strategies: This feature allows healthcare professionals to easily search, filter, and sort patient data based on various criteria. Users can search for patients by ID, filter patients by risk level, and sort patients by cardiac probability. The feature provides real-time updates and visual indicators to help identify high-risk patients at a glance.
  • On-Chain Inference: Run machine learning models on a decentralized platform, leveraging the unique capabilities of DeAI on the Internet Computer.

Technical Architecture

Getting Started

This section guides you through the initial setup of the necessary tools and environments for this project. We are using Rust with WebAssembly and the Dfinity platform.

Rust Setup

First, ensure you have Rust installed. We will then set the default toolchain to stable and add the WebAssembly target.

  1. Install Rust and Cargo (if not already installed): Visit Rust's installation page.
  2. Set the default toolchain to stable:
    rustup default stable
  3. Add the WebAssembly target:
    rustup target add wasm32-unknown-unknown

Node Package Installation

Next, ensures that the project has all the necessary libraries and tools to run or build the application.

npm install

Dfinity's DFX Setup

We will be using Dfinity's dfx for our development environment.

  1. Install Dfinity's dfx: Follow the instructions on Dfinity's SDK documentation.
  2. Starts the replica, running in the background:
    dfx start --background
  3. Deploys your canisters to the replica and generates your candid interface:
    dfx deploy

Start the Development Server

If you are making frontend changes, you can start a development server.

npm start

Varion's User Manual

Once deployment is complete, check out Varion's User Manual for a comprehensive guide on how to fully utilize the application at Varion Gitbook.

Developers

  • Anders Willard Leo - ML Engineer
  • Alden Budiman - Product Manager
  • Brian Altan - Project Lead
  • Kenneth Bryan - Web3 Engineer
  • Terris Alvin - UI/UX Designer

License

Apache 2.0/MIT All original work licensed under either of

Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0) MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT) at your option.

About

Varion AI is an AI research group dedicated to integrating ICP's decentralized AI into healthcare systems.

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages