README.md

metadata

title: Docmap Leads Classifier
emoji: 🌖
colorFrom: gray
colorTo: pink
sdk: gradio
sdk_version: 5.44.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: AI-powered healthcare leads classification using DeBERTa-v3-

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

DocMap Healthcare Leads Classifier

AI-powered classification of healthcare leads and patient inquiries using DeBERTa-v3-base.

🚀 Features

• Single Lead Classification: Classify individual patient inquiries
• Batch Processing: Handle multiple leads at once
• Priority Assessment: Determine urgency and priority levels
• Specialty Routing: Identify required medical specialties
• Confidence Scores: Transparent probability outputs

🏥 Use Cases

• Patient Triage: Prioritize urgent vs. routine cases
• Specialty Routing: Direct patients to appropriate departments
• Lead Qualification: Assess patient inquiry quality and urgency
• Resource Planning: Understand demand patterns

🔧 Technical Details

• Model: DeBERTa-v3-base fine-tuned for healthcare leads
• Input: Patient inquiry text (max 512 tokens)
• Output: Classification with confidence scores
• Performance: Fast inference on CPU/GPU

📊 Classification Categories

The model classifies leads into multiple categories including:

• Priority levels (low, medium, high, emergency)
• Specialty requirements
• Urgency indicators
• Patient type classification

🎯 Usage

1. Single Lead: Enter one patient inquiry for immediate classification
2. Batch Processing: Process multiple leads at once for efficiency
3. Examples: Use provided examples to understand input formats

📝 Input Format

Describe the patient's:

• Symptoms or condition
• Urgency level
• What they're seeking
• Any relevant medical history

🎯 Output

• Primary classification with confidence
• All class probabilities
• Formatted for easy reading
• Professional healthcare presentation

🔒 Privacy & Security

• No patient data is stored
• All processing is done in memory
• Secure inference environment
• Compliant with healthcare privacy standards

📞 Support

For technical support or questions about the classifier, contact the DocMap team.

---

Powered by DeBERTa-v3-base and HuggingFace Spaces