Create app.py

app.py

@@ -0,0 +1,234 @@
+import os
+import base64
+import gradio as gr
+import pandas as pd
+from groq import Groq
+from PIL import Image
+import io
+
+# Initialize Groq client
+client = Groq(
+    api_key=os.environ.get("GROQ_API_KEY")
+)
+
+# Function to encode images to base64
+def encode_image(image):
+    buffered = io.BytesIO()
+    image.save(buffered, format="JPEG")
+    return base64.b64encode(buffered.getvalue()).decode('utf-8')
+
+# Extract ECG readings from image using Llama Vision model
+def analyze_ecg_image(image, vision_model="llama-3.2-90b-vision-preview"):
+    if image is None:
+        return "No image provided."
+    
+    # Convert to PIL Image if needed
+    if not isinstance(image, Image.Image):
+        image = Image.open(image)
+    
+    # Encode the image
+    base64_image = encode_image(image)
+    
+    # Create chat completion with vision model
+    vision_prompt = "Analyze this ECG image carefully. Extract and report all visible parameters, intervals, rhythm patterns, and any abnormalities. Report exact numerical values where visible. Format your response as a structured report with clear sections for different measurements and observations."
+    
+    try:
+        vision_completion = client.chat.completions.create(
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": vision_prompt},
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"data:image/jpeg;base64,{base64_image}",
+                            },
+                        },
+                    ],
+                }
+            ],
+            model=vision_model,
+            temperature=0.2,  # Lower temperature for more factual responses
+            max_completion_tokens=1024,
+        )
+        
+        ecg_analysis = vision_completion.choices[0].message.content
+        return ecg_analysis
+    
+    except Exception as e:
+        return f"Error analyzing ECG image: {str(e)}"
+
+# Generate medical assessment based on ECG readings and patient history
+def generate_assessment(ecg_analysis, patient_history=None, chat_model="llama-3.3-70b-versatile"):
+    if not ecg_analysis or ecg_analysis.startswith("Error"):
+        return "Please analyze an ECG image first."
+    
+    # Construct prompt based on available information
+    if patient_history:
+        prompt = f"""You are a highly trained cardiologist assistant. Based on the ECG analysis below and the patient's history, provide a comprehensive assessment of the patient's cardiac status. Indicate clearly if there are any concerning findings that require immediate medical attention.
+
+ECG ANALYSIS:
+{ecg_analysis}
+
+PATIENT HISTORY:
+{patient_history}
+
+Provide your assessment in the following format:
+1. Summary of findings
+2. Key abnormalities (if any)
+3. Potential clinical implications
+4. Recommendation (including urgency level)
+"""
+    else:
+        prompt = f"""You are a highly trained cardiologist assistant. Based on the ECG analysis below, provide a comprehensive assessment of the patient's cardiac status. Indicate clearly if there are any concerning findings that require immediate medical attention.
+
+ECG ANALYSIS:
+{ecg_analysis}
+
+Provide your assessment in the following format:
+1. Summary of findings
+2. Key abnormalities (if any)
+3. Potential clinical implications
+4. Recommendation (including urgency level)
+"""
+    
+    try:
+        assessment_completion = client.chat.completions.create(
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are a medical AI assistant specialized in cardiology. Provide accurate, clinically relevant interpretations of ECG data. If there are concerning findings that might indicate a medical emergency, clearly highlight them. Avoid definitive diagnoses but provide reasoned medical assessments based on the data provided."
+                },
+                {
+                    "role": "user",
+                    "content": prompt
+                }
+            ],
+            model=chat_model,
+            temperature=0.2,  # Lower temperature for more factual responses
+            max_completion_tokens=2048,
+        )
+        
+        return assessment_completion.choices[0].message.content
+    
+    except Exception as e:
+        return f"Error generating assessment: {str(e)}"
+
+# Doctor's chat interaction with the model about the patient
+def doctor_chat(message, chat_history, ecg_analysis, patient_history, chat_model="llama-3.3-70b-versatile"):
+    if not ecg_analysis or ecg_analysis.startswith("Error"):
+        return "Please analyze an ECG image first before starting a chat.", chat_history
+    
+    # Prepare chat context
+    context = f"""ECG ANALYSIS:
+{ecg_analysis}
+
+"""
+    
+    if patient_history:
+        context += f"""PATIENT HISTORY:
+{patient_history}
+
+"""
+    
+    # Construct full chat history for context
+    messages = [
+        {
+            "role": "system",
+            "content": f"You are a medical AI assistant specialized in cardiology. You are helping a doctor interpret ECG results and patient data. Answer the doctor's questions based on the following information:\n\n{context}"
+        }
+    ]
+    
+    # Add chat history to the context
+    for entry in chat_history:
+        messages.append({"role": "user", "content": entry[0]})
+        messages.append({"role": "assistant", "content": entry[1]})
+    
+    # Add the current message
+    messages.append({"role": "user", "content": message})
+    
+    try:
+        chat_completion = client.chat.completions.create(
+            messages=messages,
+            model=chat_model,
+            temperature=0.3,
+            max_completion_tokens=1024,
+        )
+        
+        response = chat_completion.choices[0].message.content
+        chat_history.append((message, response))
+        return "", chat_history
+    
+    except Exception as e:
+        error_message = f"Error in chat: {str(e)}"
+        chat_history.append((message, error_message))
+        return "", chat_history
+
+# Create Gradio interface
+with gr.Blocks(title="Cardiac ECG Analysis System") as app:
+    gr.Markdown("# Cardiac ECG Analysis System")
+    gr.Markdown("Upload an ECG image and optional patient history to get an automated analysis and assessment.")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Input components
+            ecg_image = gr.Image(type="pil", label="Upload ECG Image")
+            vision_model = gr.Dropdown(
+                choices=["llama-3.2-90b-vision-preview", "llama-3.2-11b-vision-preview"], 
+                value="llama-3.2-90b-vision-preview", 
+                label="Vision Model"
+            )
+            analyze_button = gr.Button("Analyze ECG Image")
+            
+            patient_history = gr.Textbox(
+                lines=10, 
+                label="Patient History (optional)", 
+                placeholder="Enter patient's medical history, age, sex, symptoms, medications, etc."
+            )
+            
+            chat_model = gr.Dropdown(
+                choices=["llama-3.3-70b-versatile", "llama-3.3-8b-versatile"], 
+                value="llama-3.3-70b-versatile", 
+                label="Chat Model"
+            )
+            assess_button = gr.Button("Generate Assessment")
+        
+        with gr.Column(scale=1):
+            # Output components
+            ecg_analysis_output = gr.Textbox(label="ECG Analysis", lines=15)
+            assessment_output = gr.Textbox(label="Medical Assessment", lines=15)
+    
+    gr.Markdown("## Doctor's Consultation")
+    gr.Markdown("Ask follow-up questions about the patient's ECG results and medical condition.")
+    
+    chatbot = gr.Chatbot(label="Consultation")
+    message = gr.Textbox(
+        lines=2, 
+        label="Doctor's Question",
+        placeholder="Ask a question about this patient's cardiac status..."
+    )
+    chat_button = gr.Button("Send")
+    
+    # Set up event handlers
+    analyze_button.click(
+        analyze_ecg_image, 
+        inputs=[ecg_image, vision_model], 
+        outputs=ecg_analysis_output
+    )
+    
+    assess_button.click(
+        generate_assessment, 
+        inputs=[ecg_analysis_output, patient_history, chat_model], 
+        outputs=assessment_output
+    )
+    
+    chat_button.click(
+        doctor_chat, 
+        inputs=[message, chatbot, ecg_analysis_output, patient_history, chat_model], 
+        outputs=[message, chatbot]
+    )
+
+# Launch the app
+if __name__ == "__main__":
+    app.launch()