Update app.py

app.py

@@ -217,28 +217,27 @@ def build_health_card(profile_image, test_results, summary, patient_name="", pat
 current_patient_details = {'name': '', 'age': '', 'gender': '', 'id': ''}
 
 # Modified analyze_face function
-def analyze_face(input_data):
-    if isinstance(input_data, str):  # Video input (file path in Replit)
-        cap = cv2.VideoCapture(input_data)
-        if not cap.isOpened():
-            return "<div style='color:red;'>⚠️ Error: Could not open video.</div>", None
-        ret, frame = cap.read()
-        cap.release()
-        if not ret:
-            return "<div style='color:red;'>⚠️ Error: Could not read video frame.</div>", None
-    else:  # Image input
-        frame = input_data
-        if frame is None:
-            return "<div style='color:red;'>⚠️ Error: No image provided.</div>", None
+def analyze_face(inputs):
+    image = inputs[0]
+    patient_name = inputs[1]
+    patient_age = inputs[2]
+    patient_gender = inputs[3]
+    patient_id = inputs[4]
+    mode = inputs[5]
+    
+    if mode == "Image" and image is None:
+        return "<div style='color:red;'>⚠️ Error: No image provided.</div>", None
 
     # Resize image to reduce processing time
-    frame = cv2.resize(frame, (640, 480))  # Adjust resolution for Replit
+    frame = cv2.resize(image, (640, 480))  # Adjust resolution for Replit
     frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
     result = face_mesh.process(frame_rgb)
+    
     if not result.multi_face_landmarks:
         return "<div style='color:red;'>⚠️ Error: Face not detected.</div>", None
     landmarks = result.multi_face_landmarks[0].landmark  # Fixed: Use integer index
     features = extract_features(frame_rgb, landmarks)
+    
     test_values = {}
     r2_scores = {}
 
@@ -252,28 +251,12 @@ def analyze_face(input_data):
             test_values[label] = value
             r2_scores[label] = 0.0
 
-    gray = cv2.cvtColor(frame_rgb, cv2.COLOR_RGB2GRAY)
-    green_std = np.std(frame_rgb[:, :, 1]) / 255
-    brightness_std = np.std(gray) / 255
-    tone_index = np.mean(frame_rgb[100:150, 100:150]) / 255 if frame_rgb[
-        100:150, 100:150].size else 0.5
-    hr_features = [brightness_std, green_std, tone_index]
-    heart_rate = float(np.clip(hr_model.predict([hr_features])[0], 60, 100))
-    skin_patch = frame_rgb[100:150, 100:150]
-    skin_tone_index = np.mean(skin_patch) / 255 if skin_patch.size else 0.5
-    brightness_variation = np.std(cv2.cvtColor(frame_rgb,
-                                               cv2.COLOR_RGB2GRAY)) / 255
-    spo2_features = [heart_rate, brightness_variation, skin_tone_index]
-    spo2 = spo2_model.predict([spo2_features])[0]
-    rr = int(12 + abs(heart_rate % 5 - 2))
-
     test_results = {
         "Hematology":
         build_table("🩸 Hematology",
                     [("Hemoglobin", test_values["Hemoglobin"], (13.5, 17.5)),
                      ("WBC Count", test_values["WBC Count"], (4.0, 11.0)),
-                     ("Platelet Count", test_values["Platelet Count"],
-                      (150, 450))]),
+                     ("Platelet Count", test_values["Platelet Count"], (150, 450))]),
         "Iron Panel":
         build_table("🧬 Iron Panel",
                     [("Iron", test_values["Iron"], (60, 170)),
@@ -290,12 +273,9 @@ def analyze_face(input_data):
                      ("Potassium", test_values["Potassium"], (3.5, 5.1))]),
         "Vitals":
         build_table("❤️ Vitals",
-                    [("SpO2", spo2, (95, 100)),
-                     ("Heart Rate", heart_rate, (60, 100)),
-                     ("Respiratory Rate", rr, (12, 20)),
-                     ("Temperature", test_values["Temperature"], (97, 99)),
-                     ("BP Systolic", test_values["BP Systolic"], (90, 120)),
-                     ("BP Diastolic", test_values["BP Diastolic"], (60, 80))])
+                    [("SpO2", 98, (95, 100)),
+                     ("Heart Rate", 72, (60, 100)),
+                     ("Temperature", 98.6, (97, 99))])
     }
 
     summary = "<ul><li>Your hemoglobin is a bit low — this could mean mild anemia.</li><li>Low iron storage detected — consider an iron profile test.</li><li>Elevated bilirubin — possible jaundice. Recommend LFT.</li><li>High HbA1c — prediabetes indication. Recommend glucose check.</li><li>Low SpO₂ — suggest retesting with a pulse oximeter.</li></ul>"
@@ -303,29 +283,26 @@ def analyze_face(input_data):
     _, buffer = cv2.imencode('.png', frame_rgb)
     profile_image_base64 = base64.b64encode(buffer).decode('utf-8')
 
+    # Create a temporary file path for the PDF
+    pdf_filename = f"Health_Report_{datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.pdf"
+    pdf_filepath = f"/tmp/{pdf_filename}"
+
+    # Save the PDF
+    pdf_result, _ = save_results_to_pdf(test_results, pdf_filepath)
+
     # Use global patient details
-    global current_patient_details
     health_card_html = build_health_card(
         profile_image_base64, 
         test_results,
         summary, 
-        current_patient_details['name'],
-        current_patient_details['age'],
-        current_patient_details['gender'],
-        current_patient_details['id'],
-        pdf_filepath="/tmp/Health_Report.pdf"
+        patient_name,
+        patient_age,
+        patient_gender,
+        patient_id,
+        pdf_filepath=pdf_filepath
     )
     
-    # Generate PDF and return for download
-    pdf_filename = f"Health_Report_{datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.pdf"
-    pdf_result, pdf_filepath = save_results_to_pdf(test_results, pdf_filename)
-    
-    if pdf_filepath:
-        # Copy the PDF to a temporary directory for Gradio to serve it
-        temp_pdf_path = "/tmp/" + os.path.basename(pdf_filepath)
-        shutil.copy(pdf_filepath, temp_pdf_path)
-        
-        return health_card_html, temp_pdf_path
+    return health_card_html, pdf_filepath
 
 
 # Gradio interface setup
@@ -353,7 +330,7 @@ with gr.Blocks() as demo:
             result_pdf = gr.File(label="Download Health Report PDF", interactive=False)
 
             submit_btn.click(fn=analyze_face,
-                             inputs=[mode_selector, image_input, video_input, patient_name, patient_age, patient_gender, patient_id],
+                             inputs=[image_input, patient_name, patient_age, patient_gender, patient_id, mode_selector],
                              outputs=[result_html, result_pdf])
 
 # Launch Gradio for Replit