Microsoft_Hackathon

Healthcare Diagnosis Chatbot

Problem Statement

Build a chatbot capable of diagnosing common medical conditions based on user symptoms input. Utilize machine learning models trained on medical data to provide accurate suggestions and recommendations for further action.

About the Web-app and its Features

Our Healthcare Diagnosis Chatbot has 3 main features:

Disease Diagnosis

Select up to 5 symptoms from a list of 43 using our drag-and-drop interface. Our KNN model predicts potential diseases based on your inputs. Note: This prediction is based on user-provided data and should not replace professional medical advice. Always consult a healthcare provider for an accurate diagnosis.

Chest X-Ray Scan

Based on the chest X-Ray uploaded by the user, one of the 14 diseases (abscess, yards, atelectasis, atherosclerosis of the aorta, cardiomegaly, emphysema, fracture, hydropneumothorax, hydrothorax, pneumonia, pneumosclerosis, post-inflammatory changes, post-traumatic ribs deformation, sarcoidosis, scoliosis, tuberculosis, venous congestion) is predicted. This is achieved using a 3-layer CNN Architecture. Note: This prediction is based on user-provided data and should not replace professional medical advice. Always consult a healthcare provider for an accurate diagnosis.

Prescription Scan

Lastly, we also provide a handwriting-to-text option for the user, where the user enters the picture of a hand-written image containing medicine names and generates a text corresponding to the handwritten image. Enabling better legibility.

Built Using

• 
• 
• 
• 
• 
• 

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Prerequisites

It is expected to have:

1. The latest Python Version (Python 3.12 used by us)
2. Internet Connection

Installation

Below are the installation steps

1. Clone the repo

   git clone https://github.com/anagraw/Microsoft_Hackathon.git

Client Directory

2. Redirect to the client directory

   cd .\client\

3. Install NPM packages

   npm install

Server Directory

4. Redirect to the server directory

   cd .\server\

5. Install the package/library requirements

   pip install -r requirements.txt

Running

Below are the steps to run the web-app Both the client and server should be running parallelly

Client Directory

 npm run dev

Server Directory

  python main.py

Model Input Files Required for Running

Examples of files that can be used as input for testing Chest X-ray scans and Prescription scan are available in the test folder

Video Demo of the Web-App