# Thyroid Detection
This application builds a multi-class classification methodology to predict
the type of <a href="https://www.healthline.com/health/hypothyroidism-primary">Hypothyroidism</a>
based on the given training data. Refer to the <b>application workflow</b> below for details. The application is deployed on [Heroku](https://www.heroku.com/) and the code for this app can be found [__here__](https://gitfront.io/r/mohitagr18/da8c53c48426d8092e7403e82946f7e91965d3c3/thyroid-detection/).


[__Access Application__](https://thyroid-detection-app.herokuapp.com/)

<br>

__Libraries Used:__
- App framework - flask, wsgiref
- DB operations - sqlite3
- Data processing and ML - numpy, pandas, matplotlib, scikit-learn, xgboost, boto3, kneed, pickle
- General operations - os, shutil, csv, json, re, datetime, time

![image](assets/Thyroid-Detection.png)