Update app.py

app.py

@@ -13,22 +13,51 @@ from reportlab.platypus import TableStyle
 model = joblib.load("typhoidguard_model_reduced.pkl")
 
 # Risk & Agent Logic
+# Risk & Agentic Logic
 def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, potassium):
 
+    # Prepare input
     data = pd.DataFrame([{
         "Platelet Count": platelets,
         "Age": age,
         "Hemoglobin (g/dL)": hb,
         "Treatment Duration": duration,
         "Calcium (mg/dL)": calcium,
-        "Potassium (mmol/L)": potassium,
+        "Potassium": potassium,
         "Gender": gender
     }])
 
-    risk = model.predict_proba(data)[0][1] * 100
-    risk = round(risk, 2)
+    # 1️⃣ Model probability
+    # If your model is a pipeline: classifier is last step
+    try:
+        prob = model.predict_proba(data)[0][1]  # probability of treatment failure
+    except:
+        # fallback
+        prob = 0.0
 
-    # Agent Reasoning
+    prob_pct = round(prob * 100, 2)
+
+    # 2️⃣ Risk label
+    if prob > 0.65:
+        risk_label = "🔴 HIGH RISK"
+        color = "#d62828"
+    elif prob >= 0.35:
+        risk_label = "🟡 MODERATE RISK"
+        color = "#f4a261"
+    else:
+        risk_label = "🟢 LOW RISK"
+        color = "#2a9d8f"
+
+    # 3️⃣ Agent triage logic (like your local function)
+    patient_data = data.iloc[0].to_dict()
+    if (prob > 0.65 and patient_data.get("Platelet Count", 999999) < 150000):
+        recommendation = "Immediate referral to secondary care facility recommended. Close monitoring required."
+    elif 0.35 <= prob <= 0.65:
+        recommendation = "Close monitoring advised. Repeat blood tests within 48 hours."
+    else:
+        recommendation = "Continue standard treatment protocol."
+
+    # 4️⃣ Top clinical risk factors
     factors = []
     if platelets < 150000:
         factors.append("Low Platelet Count")
@@ -36,25 +65,17 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
         factors.append("Low Hemoglobin")
     if duration > 7:
         factors.append("Prolonged Treatment Duration")
+    if calcium < 8.5:
+        factors.append("Low Calcium")
+    if potassium < 3.5 or potassium > 5.0:
+        factors.append("Abnormal Potassium")
 
-    if risk > 65:
-        status = "🔴 HIGH RISK"
-        recommendation = "Immediate referral to secondary care facility recommended. Close monitoring required."
-        color = "#d62828"
-    elif 35 <= risk <= 65:
-        status = "🟡 MODERATE RISK"
-        recommendation = "Close monitoring advised. Repeat blood tests within 48 hours."
-        color = "#f4a261"
-    else:
-        status = "🟢 LOW RISK"
-        recommendation = "Continue standard treatment protocol."
-        color = "#2a9d8f"
-
+    # 5️⃣ Construct HTML response
     explanation = f"""
     <div style="font-family:Arial; padding:15px;">
         <h2 style="color:{color};">Patient: {name}</h2>
-        <h3>Risk of Treatment Failure: {risk}%</h3>
-        <h3>Status: {status}</h3>
+        <h3>Risk of Treatment Failure: {prob_pct}%</h3>
+        <h3>Status: {risk_label}</h3>
         <h4>Clinical Risk Factors:</h4>
         <ul>
             {''.join([f"<li>{f}</li>" for f in factors])}
@@ -66,7 +87,6 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
 
     return explanation
 
-
 # PDF Generation
 def generate_pdf(name, age, gender, platelets, hb, duration, calcium, potassium):