Upload 2 files

chatbot.py

@@ -0,0 +1,125 @@
+import random
+from datetime import datetime
+
+class HealthcareChatbot:
+    def __init__(self):
+        self.health_knowledge_base = {
+            'heart_health': {
+                'tips': [
+                    "Maintain a heart-healthy diet rich in fruits, vegetables, and whole grains",
+                    "Aim for at least 150 minutes of moderate exercise per week",
+                    "Monitor your blood pressure regularly",
+                    "Avoid smoking and limit alcohol consumption",
+                    "Manage stress through relaxation techniques"
+                ],
+                'symptoms': {
+                    'chest_pain': "Chest pain can be a sign of heart issues. Consult a doctor immediately.",
+                    'shortness_breath': "Shortness of breath may indicate cardiac problems. Seek medical attention."
+                }
+            },
+            'diabetes_management': {
+                'tips': [
+                    "Monitor blood sugar levels regularly",
+                    "Follow a balanced diet with controlled carbohydrates",
+                    "Take medications as prescribed by your doctor",
+                    "Stay physically active with regular exercise",
+                    "Get regular eye and foot examinations"
+                ]
+            },
+            'hypertension': {
+                'tips': [
+                    "Reduce sodium intake in your diet",
+                    "Maintain a healthy body weight",
+                    "Limit alcohol and caffeine consumption",
+                    "Practice stress management techniques",
+                    "Take prescribed medications regularly"
+                ]
+            },
+            'general_health': {
+                'tips': [
+                    "Get 7-9 hours of quality sleep each night",
+                    "Stay hydrated by drinking plenty of water",
+                    "Practice good hygiene and hand washing",
+                    "Get regular health check-ups",
+                    "Maintain a balanced diet and healthy lifestyle"
+                ]
+            }
+        }
+        
+        self.urdu_responses = {
+            'greeting': "السلام علیکم! میں آپ کی صحت کے معاملات میں مدد کر سکتا ہوں۔",
+            'heart_health': "دل کی صحت کے لیے مشورے:\n• پھل، سبزیاں اور سارے اناج سے بھرپور غذا کھائیں\n• ہفتے میں کم از کم 150 منٹ ورزش کریں\n• اپنا بلڈ پریشر باقاعدگی سے چیک کریں",
+            'diabetes': "ذیابیطس کے انتظام کے لیے:\n• خون میں شکر کی سطح باقاعدگی سے چیک کریں\n• متوازن غذا کھائیں\n• دوائیں ڈاکٹر کے مشورے سے لیں",
+            'hypertension': "ہائی بلڈ پریشر کے لیے:\n• نمک کا استعمال کم کریں\n• صحت مند وزن برقرار رکھیں\n• ورزش کو اپنی عادت بنائیں"
+        }
+    
+    def get_response(self, user_input, language='English'):
+        """Generate context-aware healthcare responses"""
+        user_input_lower = user_input.lower()
+        
+        # Greeting detection
+        if any(word in user_input_lower for word in ['hello', 'hi', 'hey', 'سلام', 'ہیلو']):
+            if language == 'Urdu':
+                return self.urdu_responses['greeting']
+            else:
+                return "Hello! I'm your healthcare assistant. How can I help you today?"
+        
+        # Topic-based responses
+        response = self.generate_topic_response(user_input_lower, language)
+        
+        return response
+    
+    def generate_topic_response(self, user_input, language):
+        """Generate response based on detected health topic"""
+        
+        if any(word in user_input for word in ['heart', 'cardiac', 'chest', 'دل', 'سینہ']):
+            tips = self.health_knowledge_base['heart_health']['tips']
+            if language == 'Urdu':
+                return self.urdu_responses['heart_health']
+            else:
+                return "Heart Health Tips:\n" + "\n".join([f"• {tip}" for tip in tips])
+        
+        elif any(word in user_input for word in ['diabetes', 'sugar', 'glucose', 'شوگر', 'ذیابیطس']):
+            tips = self.health_knowledge_base['diabetes_management']['tips']
+            if language == 'Urdu':
+                return self.urdu_responses['diabetes']
+            else:
+                return "Diabetes Management Tips:\n" + "\n".join([f"• {tip}" for tip in tips])
+        
+        elif any(word in user_input for word in ['blood pressure', 'hypertension', 'bp', 'بلڈ پریشر']):
+            tips = self.health_knowledge_base['hypertension']['tips']
+            if language == 'Urdu':
+                return self.urdu_responses['hypertension']
+            else:
+                return "Hypertension Management Tips:\n" + "\n".join([f"• {tip}" for tip in tips])
+        
+        else:
+            # General health tips
+            tips = self.health_knowledge_base['general_health']['tips']
+            if language == 'Urdu':
+                return "عام صحت کے نکات:\n" + "\n".join([f"• {tip}" for tip in random.sample(tips, 3)])
+            else:
+                return "General Health Tips:\n" + "\n".join([f"• {tip}" for tip in random.sample(tips, 3)])
+    
+    def get_emergency_advice(self, symptoms, language='English'):
+        """Provide emergency advice for concerning symptoms"""
+        emergency_symptoms = {
+            'chest_pain': {
+                'english': "Chest pain can be serious. Seek immediate medical attention.",
+                'urdu': "سینے میں درد سنگین ہو سکتا ہے۔ فوری طبی امداد حاصل کریں۔"
+            },
+            'severe_shortness_breath': {
+                'english': "Severe shortness of breath requires emergency care.",
+                'urdu': "سانس لینے میں شدید دشواری ہنگامی علاج کی ضرورت ہے۔"
+            },
+            'fainting': {
+                'english': "Fainting spells need immediate medical evaluation.",
+                'urdu': "بیہوشی کے دورے فوری طبی تشخیص کی ضرورت ہے۔"
+            }
+        }
+        
+        for symptom, advice in emergency_symptoms.items():
+            if symptom in symptoms:
+                return advice['urdu'] if language == 'Urdu' else advice['english']
+        
+        return None

ocr_processor.py

@@ -0,0 +1,118 @@
+import cv2
+import numpy as np
+import pytesseract
+from PIL import Image
+import re
+
+class PrescriptionOCR:
+    def __init__(self):
+        self.medication_keywords = [
+            'tablet', 'capsule', 'mg', 'ml', 'injection', 'dose',
+            'twice', 'thrice', 'daily', 'weekly', 'monthly'
+        ]
+    
+    def preprocess_image(self, image):
+        """Enhanced image preprocessing for medical prescriptions"""
+        try:
+            # Convert to numpy array
+            img_array = np.array(image)
+            
+            # Convert to grayscale
+            if len(img_array.shape) == 3:
+                gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
+            else:
+                gray = img_array
+            
+            # Noise removal
+            denoised = cv2.medianBlur(gray, 3)
+            
+            # Thresholding
+            _, thresh = cv2.threshold(denoised, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+            
+            # Morphological operations
+            kernel = np.ones((2, 2), np.uint8)
+            processed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
+            
+            return processed
+            
+        except Exception as e:
+            print(f"Image preprocessing error: {e}")
+            return np.array(image)
+    
+    def extract_medication_info(self, text):
+        """Extract medication information from OCR text"""
+        medications = []
+        lines = text.split('\n')
+        
+        for line in lines:
+            line_clean = line.strip()
+            if any(keyword in line_clean.lower() for keyword in self.medication_keywords):
+                # Extract dosage information
+                dosage_pattern = r'(\d+\s*(?:mg|ml|tablet|cap)s?)'
+                dosages = re.findall(dosage_pattern, line_clean, re.IGNORECASE)
+                
+                # Extract frequency
+                freq_pattern = r'(?:once|twice|thrice|\d+\s*times)\s*(?:daily|a day|per day)'
+                frequency = re.findall(freq_pattern, line_clean, re.IGNORECASE)
+                
+                medication_info = {
+                    'text': line_clean,
+                    'dosages': dosages,
+                    'frequency': frequency[0] if frequency else 'Unknown',
+                    'confidence': 'High' if dosages else 'Medium'
+                }
+                medications.append(medication_info)
+        
+        return medications
+    
+    def process_prescription(self, image):
+        """Main method to process prescription and extract information"""
+        try:
+            # Preprocess image
+            processed_img = self.preprocess_image(image)
+            
+            # OCR with medical-specific configuration
+            custom_config = r'--oem 3 --psm 6 -l eng'
+            extracted_text = pytesseract.image_to_string(processed_img, config=custom_config)
+            
+            # Extract medication information
+            medications = self.extract_medication_info(extracted_text)
+            
+            # Calculate confidence score
+            confidence = self.calculate_confidence(extracted_text, medications)
+            
+            return {
+                'raw_text': extracted_text,
+                'medications': medications,
+                'confidence_score': confidence,
+                'medication_count': len(medications)
+            }
+            
+        except Exception as e:
+            return {
+                'raw_text': '',
+                'medications': [],
+                'confidence_score': 0,
+                'error': str(e)
+            }
+    
+    def calculate_confidence(self, text, medications):
+        """Calculate confidence score for OCR extraction"""
+        if not text.strip():
+            return 0
+        
+        # Base score based on text length and medication detection
+        base_score = min(100, len(text) / 10)
+        
+        # Bonus for medication detection
+        medication_bonus = len(medications) * 15
+        
+        # Penalty for likely errors
+        error_penalty = 0
+        if len(text) < 20:
+            error_penalty += 20
+        if len(re.findall(r'[^\w\s.,]', text)) > len(text) * 0.3:
+            error_penalty += 15
+        
+        final_score = base_score + medication_bonus - error_penalty
+        return max(0, min(100, final_score))