---
tags:
- fastai
---

#Project Description

The project aims to classify a given text input of symptoms into a medical specialty that might be relevant to the symptoms. The model classifies the input into one of the 28 specialties, such as gastroenterologist, pediatrics, etc., that it was trained in.

#Model Description

This model is a fine-tuned version of [deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) using the amazing [Blurr](https://ohmeow.github.io/blurr/) library (huggingface wrapper library using fastai)

#Dataset Used

The dataset for this task was built by scrapping [Patient.info](https://patient.info/forums). In the forum, posts are organized under different categories/groups such as anxiety disorder, acne, malaria, etc. These categories/groups were manually mapped to a specialty for eg anxiety to a psychiatrist, and malaria to an infectious disease specialist.

##Others

I have a blog on the same task using fastai's ULMFiT model. That can be found [here](https://moarshy.github.io/blogs/nlp/fastai/text%20classification/medical/2022/05/04/_10_29_specialtytextclassification.html). 

**Disclaimer**
This project is a fun project intended for learning purposes only.