AlphaRaven/medgemma-ae-detection

MedGemma AE Detection

MedGemma 1.5-4B fine-tuned for visual adverse event detection from clinical photographs.

• Base model: google/medgemma-1.5-4b-it
• Method: LoRA fine-tuning (50 epochs)
• Task: Classify skin AEs from patient photos into 21 categories (normal + 7 AE types × 3 CTCAE grades)
• AE types: maculopapular rash, acneiform rash, periorbital edema, SJS, stomatitis, pruritus, alopecia

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained("AlphaRaven/medgemma-ae-detection")
processor = AutoProcessor.from_pretrained("google/medgemma-1.5-4b-it")

Part of the Clinical Trial Simulation Engine pipeline.