Downloads · 30 days
14
21% of all-time downloads
medical-report-generator
mou11/medical-report-generator
medical-report-generator is a text generation model from mou11. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
All-time downloads
66
Public
Repo size
27.3 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 MB · 89%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- llm-pipeline
- Access
- Public
- Created
- May 15, 2026
- Updated
- May 18, 2026
- SHA
- f17bb7cc
Try a prompt
Base models
Model card
From the Hugging Face model README
Medical Report Generator
Live Demo
👉 Try it on Hugging Face Spaces
Overview
An end-to-end clinical report generation pipeline that generates structured medical reports from patient data, detects hallucinations using NLI, outputs FHIR R4 compliant JSON, and exports professional PDF reports.
Results
| Report Type | BERTScore F1 | Safety Score |
|---|---|---|
| Radiology | 0.8628 | 0.625 |
| Discharge Summary | 0.9045 | 1.0 |
| Lab Report | 0.8129 | 0.375 |
Hallucination Detection
| Report Type | Total Claims | Hallucination Rate | Safety Score |
|---|---|---|---|
| Radiology | 4 | 0.375 | 0.625 |
| Discharge | 1 | 0.0 | 1.0 |
| Lab | 4 | 0.625 | 0.375 |
Features
- Generates 3 types of clinical reports: Radiology, Discharge Summary, Lab Report
- Hallucination detection using NLI (cross-encoder/nli-deberta-v3-base)
- FHIR R4 compliant JSON output (HL7 healthcare standard)
- BERTScore and ROUGE evaluation metrics
- Professional PDF export with quality assessment table
- Gradio web interface
Architecture
Patient Data → Report Generation (LLaMA 3.3 70B via Groq) → Hallucination Detection (DeBERTa NLI) → Evaluation (BERTScore + ROUGE) → FHIR R4 JSON → PDF Export
Tech Stack
| Component | Tool |
|---|---|
| LLM | Groq — LLaMA 3.3 70B |
| Hallucination Detection | cross-encoder/nli-deberta-v3-base |
| Evaluation | BERTScore + ROUGE |
| FHIR Output | HL7 R4 JSON |
| PDF Export | ReportLab |
| UI | Gradio |
| Platform | Google Colab (T4 GPU) |
How to Run
- Get a free Groq API key at console.groq.com
- Open
app.pyin Google Colab - Add your key to Colab Secrets as
GROQ_KEY_1 - Run all cells in order
Medical Disclaimer
This system is for educational and research purposes only. It does not provide medical advice. Always consult a qualified healthcare professional for medical decisions.
Project Status
✅ Report generation pipeline complete ✅ Hallucination detection implemented ✅ FHIR R4 compliant output ✅ PDF export working ✅ Gradio demo deployed on Hugging Face Spaces
- Task
- Text Generation
- Library
- transformers
- Type
- llm-pipeline
- License
- mit
- Created
- May 15, 2026
- Updated
- May 18, 2026