Update README.md

README.md

@@ -1,17 +1,33 @@
 ---
 license: apache-2.0
-base_model: google/medgemma-1.5-4b-it
-tags: [medical, dermatology, adverse-event-detection, medgemma]
+base_model:
+- google/medgemma-1.5-4b-it
+- AlphaRaven/medgemma-4b-antihallu
+tags:
+- medical
+- dermatology
+- adverse-event-detection
+- medgemma
 ---
 # MedGemma AE Detection
 
-MedGemma 1.5-4B fine-tuned for **visual adverse event detection** from clinical photographs.
+MedGemma 1.5-4B fine-tuned for **visual adverse event detection** from clinical photographs using paired image comparison.
 
-- **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)
+- **Base model**: `AlphaRaven/medgemma-4b-antihallu`
+- **Method**: LoRA fine-tuning (r=8, alpha=16, target: q_proj/v_proj)
+- **Training**: 100 epochs
+- **Task**:
+  - 1. Paired comparison of baseline vs. current patient photos.
+    2. Classify skin AEs from patient photos into 21 categories (normal + 7 AE types × 3 CTCAE grades; alopecia G1-G2 only)
 - **AE types**: maculopapular rash, acneiform rash, periorbital edema, SJS, stomatitis, pruritus, alopecia
 
+## Performance (test set, 42 paired images):
+    - Accuracy: 95.2%
+    - Weighted F1: 0.951
+    - 
+## Dataset**: Synthetic clinical photographs (Gemini-generated)
+    - 147 train / 21 val / 42 test paired images
+
 ## Usage
 
 ```python
@@ -21,4 +37,7 @@ model = AutoModelForImageTextToText.from_pretrained("AlphaRaven/medgemma-ae-dete
 processor = AutoProcessor.from_pretrained("google/medgemma-1.5-4b-it")
 ```
 
-Part of the [Clinical Trial Simulation Engine](https://github.com/AlphaRaven/ClinicalTrialEngine) pipeline.
+  Input: Two images (baseline photo + current photo) with a clinical reasoning prompt using CTCAE grading criteria.
+  Output: JSON array of detected AEs with ae_term, grade, and reasoning.
+
+Part of the [Clinical Trial Simulation Engine](https://github.com/AlphaRaven/ClinicalTrialEngine) pipeline.