https://github.com/amansrv/cardio-care-predictor-api

JSON API which returns predictions based on user input parameters using Scikit-learn and Flask.
https://github.com/amansrv/cardio-care-predictor-api

aiml flask-api json-api

Last synced: about 2 months ago
JSON representation

JSON API which returns predictions based on user input parameters using Scikit-learn and Flask.

• Host: GitHub
• URL: https://github.com/amansrv/cardio-care-predictor-api
• Owner: amansrv
• Created: 2023-09-23T09:24:55.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-09-23T18:47:17.000Z (almost 2 years ago)
• Last Synced: 2023-09-23T23:01:47.322Z (almost 2 years ago)
• Topics: aiml, flask-api, json-api
• Language: Jupyter Notebook
• Homepage: https://cardio-care-predictor-api.onrender.com/
• Size: 1.3 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Cardio Care Predictor API

![Python](https://badgen.net/badge/Python/3.7/orange)

![License](https://badgen.net/badge/license/MIT/blue)

- Flask REST API which predicts the probability of Coronary Heart Disease in a patient taking 9 different parameters based on the patient's history as input.

- The API uses a Logistic Regression Model from sci-kit-learn trained on the [Framingham Heart Study Dataset](https://www.kaggle.com/amanajmera1/framingham-heart-study-dataset) from Kaggle.

- The model achieved a test accuracy of around 88%.

## Useful Links

- Deployed on OnRender: [Onrender Link](https://cardio-care-predictor-api.onrender.com/)

- View the Jupyter Notebook: [Jupyter Notebook](https://github.com/amansrv/Cardio-Care-Predictor-API/blob/main/model/HeartDisease.ipynb)

- Flask REST API: [API](https://github.com/amansrv/Cardio-Care-Predictor-API/blob/main/app.py)

## Predict Endpoint

- Takes 9 parameters as input

- Returns a binary prediction (0 or 1) and probability as well.

	### Sample query

    	https://cardio-care-predictor-api.onrender.com/predict?age=31&sex=1&cigs=5&chol=230&sBP=280&dia=0&dBP=90&gluc=87&hRate=84

	### Sample output

      {

         "data":{

            "age": "31",

            "cigsPerDay": "5",

            "diaBP": "90",

            "diabetes": "0",

            "glucose": "87",

            "heartRate": "84",

            "sex": "1",

            "sysBP": "280",

            "totChol": "230"

         },

         "prediction":[

            1

         ],

         "probability":[

            [

               0.4587093009776524,

               0.5412906990223476

            ]

         ]

      }

## Model Endpoint

- Returns the model details such as intercept and coefficients.

		https://cardio-care-predictor-api.onrender.com/model

## Running locally

1. Clone the repository

   ```bash

      git clone https://github.com/amansrv/Cardio-Care-Predictor-API.git

	

      cd Cardio-Care-Predictor-API

   ```

2. Install dependencies

   ```bash

	   pip install requirements.txt

   ```

	

3. Start the Flask server

   ```bash

	   python3 app.py

   ```