01 / README

Project overview

Arrhythmias Predictor

Project Overview

Arrhythmias Predictor is a machine learning project designed to predict different types of arrhythmias using a dense neural network model. The project consists of a back-end API for handling predictions and a front-end application for user interaction. The project provides chat bot service for users tochat about their medical conditions and ask recommendations on what they should do.

Project Structure

Back-End

The back-end is responsible for loading the machine learning models, handling API requests, and making predictions. It is implemented using Python and Flask.

Key Files

API_key_loader.py: Handles loading of API keys.
app.py: Main application file that initializes the Flask app.
db_models.py: Defines the database models.
Gemini.py: Contains utility functions.
routes.py: Defines the API routes.

Predictor Model

The predictor model is a dense neural network designed for arrhythmia prediction. The models are stored in the predictor_model directory.

Front-End

The front-end application is built using modern web technologies and provides a user-friendly interface for interacting with the prediction API.

Key Files

package.json: Contains the project dependencies and scripts.
public/: Contains static assets.
src/: Contains the source code for the front-end application.

Getting Started

Prerequisites

Python 3.12
Node.js
Flask

Installation

Clone the repository:

git clone https://github.com/yourusername/arrhythmias-predictor.git
cd arrhythmias-predictor

Set up the back-end:

cd back-end
python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt

Set up the front-end:
```
cd front-end-app
npm install
```

Running the Project

Start the back-end server:
```
cd back-end
flask run
```
Start the front-end application:
```
cd front-end-app
npm start
```

Usage

Once the project is running, you can access the front-end application in your web browser. Use the interface to input data and get arrhythmia predictions.

Contributors

Elias Hizkiel Alota Michael Andualem