Update app.py

app.py

@@ -21,6 +21,7 @@ from sklearn.preprocessing import LabelEncoder
 from sklearn.impute import SimpleImputer
 from huggingface_hub import hf_hub_download
 import joblib
+import shap
 
 # ── Device ────────────────────────────────────────────────────────────────────
 device = torch.device("cpu")
@@ -143,6 +144,10 @@ gb_path = hf_hub_download(repo_id=REPO_ID, filename="gb_clinical_model_joblib.pk
 gb_model = joblib.load(gb_path)
 print("GB clinical model loaded")
 
+# SHAP explainer for the clinical model (created once, reused for every request)
+shap_explainer = shap.TreeExplainer(gb_model)
+print("SHAP explainer ready")
+
 print("All models ready.")
 
 # تحقق من اسماء الأعمدة في الـ scaler
@@ -243,6 +248,24 @@ def prepare_clinical_features(
     scaled = clinical_scaler.transform(X)
     return scaled
 
+def get_top_shap_features(clinical_feat, top_n=6):
+    """
+    Compute SHAP values for the clinical (GB) model's prediction and
+    return the top_n features ranked by absolute impact.
+    clinical_feat must be the scaled numpy array in ALL_COLS order.
+    Returns a list of (feature_name, shap_value) tuples.
+    """
+    shap_values = shap_explainer.shap_values(clinical_feat)
+
+    # Some SHAP/model versions return a list per class, others a single array
+    if isinstance(shap_values, list):
+        shap_row = shap_values[1][0]  # class "CKD" (positive class)
+    else:
+        shap_row = shap_values[0]
+
+    top_idx = np.argsort(np.abs(shap_row))[::-1][:top_n]
+    return [(ALL_COLS[i], float(shap_row[i])) for i in top_idx]
+
 # ── Grad-CAM++ ────────────────────────────────────────────────────────────────
 class GradCAMPlusPlus:
     def __init__(self, model, target_layer):
@@ -478,6 +501,9 @@ def predict_ckd_risk(
     # 5. GB clinical prediction
     clinical_prob = gb_model.predict_proba(clinical_feat)[0, 1]
 
+    # 5.b Top-6 SHAP features driving the clinical prediction
+    top_shap_features = get_top_shap_features(clinical_feat, top_n=6)
+
     # 6. Fusion model prediction
     retinal_tensor  = torch.tensor(retinal_feat_pca, dtype=torch.float32)
     clinical_tensor = torch.tensor(clinical_feat,    dtype=torch.float32)
@@ -542,7 +568,6 @@ def predict_ckd_risk(
   WBC Count (wbcc):     {wbcc} cells/cumm
   RBC Count (rbcc):     {rbcc} millions/cumm
   Blood Pressure (bp):  {bp} mmHg
-
   URINE TESTS
   Specific Gravity (sg):{sg}
   Albumin (al):         {al}
@@ -551,7 +576,6 @@ def predict_ckd_risk(
   Pus Cells (pc):       {pc}
   Pus Cell Clumps (pcc):{pcc}
   Bacteria (ba):        {ba}
-
   PATIENT INFO
   Age:                  {age} years
   Hypertension (htn):   {htn}
@@ -566,6 +590,9 @@ def predict_ckd_risk(
   Clinical Score:       {clinical_prob:.4f}
   Fusion Score:         {fusion_prob:.4f}
   Risk Level:           {risk_label}
+╠══════════════════════════════════════╣
+  TOP 6 CLINICAL FEATURES (SHAP)
+{chr(10).join(f"  {i+1}. {name:<8s} {'+' if val >= 0 else ''}{val:.4f}" for i, (name, val) in enumerate(top_shap_features))}
 ╚══════════════════════════════════════╝
 """
 
@@ -723,9 +750,7 @@ with gr.Blocks(title="CKD-MultiVision") as demo:
         with gr.TabItem("About"):
             gr.Markdown("""
             ## About CKD-MultiVision
-
             **Input Fields (24 total — matching UCI CKD Dataset):**
-
             | # | Field | Source | Description |
             |---|-------|--------|-------------|
             | 1 | age | Manual | Patient age in years |
@@ -752,12 +777,10 @@ with gr.Blocks(title="CKD-MultiVision") as demo:
             | 22 | appet | Manual | Appetite |
             | 23 | pe | Manual | Pedal edema |
             | 24 | ane | Manual | Anemia |
-
             **Pipeline:**
             - Retinal Image → EfficientNet-B3 → Feature Vector (1536) → PCA (64 dim)
             - Clinical Values (24) → StandardScaler → Gradient Boosting + Fusion Model
             - Cross-Modal Attention Fusion → Final Risk Level
-
             *Research prototype — not for clinical use.*
             """)