Bert Symptom Checker

🚀 AI-Powered Symptom Checker 🏥🤖

This model predicts potential medical conditions based on user-reported symptoms. Built using BERT and fine-tuned on the MedText dataset, it helps users get preliminary symptom insights.

🚀 Quick Start

You can quickly start using this model with the following code:

from transformers import pipeline

model = pipeline("text-classification", model="Lech-Iyoko/bert-symptom-checker")
result = model("I have a severe headache and nausea.")
print(result)

✨ Features

• Predicts potential medical conditions based on user-reported symptoms.
• Built on BERT and fine - tuned on the MedText dataset.
• Helps users obtain preliminary insights into their symptoms.

📦 Installation

Since this model uses the transformers library, you can install it via pip:

pip install transformers

💻 Usage Examples

Basic Usage

from transformers import pipeline

model = pipeline("text-classification", model="Lech-Iyoko/bert-symptom-checker")
result = model("I have a severe headache and nausea.")
print(result)

📚 Documentation

🔍 Model Details

📌 Limitations & Ethical Considerations

⚠️ Important Note

This model should not be used for medical diagnosis. Always consult a healthcare professional.

📝 Training Hyperparameters

• Preprocessing: Lowercasing, tokenisation, stopword removal
• Training Framework: Hugging Face transformers
• Training Regime: fp32 (full precision training for stability)
• Batch Size: 16
• Learning Rate: 3e - 5
• Epochs: 5
• Optimiser: AdamW
• Scheduler: Linear with warmup

⏱ Speeds, Sizes, Times

• Model Checkpoint Size: 4.5GB
• Training Duration: ~3 - 4 hours on Google Colab
• Throughput: 1200 samples per minute

🧪 Evaluation

Testing Data

• Dataset: MedText (1.4k samples)
• Dataset Type: Medical symptom descriptions → condition prediction

Splits

• Train: 80% (1,120 cases)
• Test: 20% (280 cases)

Metrics

📊 Results

The model shows excellent performance in the evaluation:

• Accuracy: 96.5% (measures overall correctness)
• F1 - Score: 95.1% (harmonic mean of precision & recall)
• Precision: 94.7% (correct condition predictions out of all predicted)
• Recall: 95.5% (correct condition predictions out of all actual)

Summary

• Strengths: High recall ensures most conditions are correctly identified.
• Weaknesses: Model might struggle with rare conditions due to dataset limitations.

⚙️ Model Architecture & Objective

• Architecture: BERT (bert-base-uncased) fine - tuned for medical text classification.
• Objective: Predict potential conditions/outcomes based on patient symptom descriptions.

💻 Compute Infrastructure

Hardware

• Training: Google Colab (NVIDIA T4 GPU, 16GB RAM)
• Inference: Hugging Face Inference API (optimised for CPU/GPU use)

Software

• Python Version: 3.8
• Deep Learning Framework: PyTorch (transformers library)
• Tokeniser: BERT WordPiece Tokenizer
• Preprocessing Libraries: nltk, spacy, textacy

📄 License

This project is licensed under the Apache 2.0 license.