README.md

---
license: mit
language:
- en
base_model:
- google-bert/bert-base-uncased
pipeline_tag: text-classification
library_name: transformers.js
tags:
- medical
---
# Model Card for Disease Symptom Recognition Model

## Model Details

### Model Description

This model is a fine-tuned BERT-based architecture designed to recognize and classify symptoms of diseases. It has been trained on a curated dataset containing labeled descriptions of various disease symptoms and converted to ONNX for efficient inference.

- **Developed by:** Mihi
- **Funded by:** Self-funded
- **Shared by:** Mihi
- **Model type:** NLP Classification
- **Language(s):** English
- **License:** MIT
- **Finetuned from model:** BERT base uncased

### Model Sources

- **Repository:** [GitHub Repository Link] (replace with actual link)
- **Demo:** [Demo Link] (replace with actual link)

---

## Uses

### Direct Use

This model can be used directly for symptom classification in applications like:

- Symptom checkers for healthcare applications
- Medical chatbots for triage
- Data analysis in public health studies

### Downstream Use

The model may be fine-tuned further or integrated into larger healthcare solutions involving disease diagnosis or prediction.

### Out-of-Scope Use

- The model is not designed for diagnosing diseases.
- It should not be used as a substitute for professional medical advice.

---

## Bias, Risks, and Limitations

- The model's performance is limited to the scope and quality of the training data. It may not perform well on symptoms outside its training domain.
- Potential biases in the training data can lead to inaccurate predictions for underrepresented diseases or symptoms.

### Recommendations

- Ensure proper pre-screening of the output by medical professionals before clinical application.
- Perform further fine-tuning or retraining if applied in domains outside the original dataset.

---

## How to Get Started with the Model

Install the required dependencies:
```bash
pip install transformers onnxruntime