healthcare-api.py

```python
#!/usr/bin/env python3
"""
Healthcare AI API for Web Integration
FastAPI backend for HIPAA-compliant AI services
"""

from fastapi import FastAPI, HTTPException, Depends, Security
from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
from pydantic import BaseModel
import uvicorn
from healthcare_ai_finetune import HealthcareAIApp, HIPAACompliantDataHandler
import json
from typing import Optional, List
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Initialize AI system
healthcare_ai = HealthcareAIApp()
healthcare_ai.initialize_models()

app = FastAPI(
    title="Healthcare AI API",
    description="HIPAA-compliant AI services for patient education and predictive analytics",
    version="1.0.0"
)

security = HTTPBearer()

class PatientData(BaseModel):
    age: int
    bmi: float
    blood_pressure_systolic: int
    blood_pressure_diastolic: int
    gender: str
    smoking_status: str
    diabetes_status: str
    condition: str
    symptoms: str

class PredictionRequest(BaseModel):
    patient_data: PatientData
    model_type: str = "both"  # "education", "prediction", or "both"

class HealthPrediction(BaseModel):
    risk_level: int
    confidence: float
    recommendations: List[str]

class EducationMaterial(BaseModel):
    content: str
    condition: str
    generated_at: str

class APIResponse(BaseModel):
    success: bool
    message: str
    data: Optional[dict] = None

def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)):
    """Simple token verification - enhance for production"""
    valid_tokens = ["healthcare_provider_token_2024"]
    if credentials.credentials not in valid_tokens:
        raise HTTPException(status_code=401, detail="Invalid token")
    return credentials.credentials

@app.get("/")
async def root():
    return {"message": "Healthcare AI API - HIPAA Compliant"}

@app.post("/api/generate-education", response_model=APIResponse)
async def generate_education_material(
    request: PredictionRequest,
    token: str = Depends(verify_token)
):
    """Generate patient education materials"""
    try:
        # Convert patient data to DataFrame format
        patient_df = pd.DataFrame([{
            'age': request.patient_data.age,
            'bmi': request.patient_data.bmi,
            'blood_pressure_systolic': request.patient_data.blood_pressure_systolic,
            'blood_pressure_diastolic': request.patient_data.blood_pressure_diastolic,
            'gender': request.patient_data.gender,
            'smoking_status': request.patient_data.smoking_status,
            'diabetes_status': request.patient_data.diabetes_status
        }])
        
        result = healthcare_ai.process_patient_case(
            patient_df,
            request.patient_data.condition,
            request.patient_data.symptoms
        )
        
        return APIResponse(
            success=True,
            message="Education material generated successfully",
            data={
                "education_material": result["education_material"],
                "condition": request.patient_data.condition
        )
        
    except Exception as e:
        logger.error(f"Error generating education material: {e}")
        raise HTTPException(status_code=500, detail="Internal server error")
    
@app.post("/api/predict-health", response_model=APIResponse)
async def predict_health_outcomes(
    request: PredictionRequest,
    token: str = Depends(verify_token)
):
    """Predict health outcomes and risk levels"""
    try:
        patient_df = pd.DataFrame([{
            'age': request.patient_data.age,
            'bmi': request.patient_data.bmi,
            'blood_pressure_systolic': request.patient_data.blood_pressure_systolic,
            'blood_pressure_diastolic': request.patient_data.blood_pressure_diastolic,
            'gender': request.patient_data.gender,
            'smoking_status': request.patient_data.smoking_status,
            'diabetes_status': request.patient_data.diabetes_status
        }])
        
        predictions, probabilities = healthcare_ai.health_predictor.predict_health_outcomes(patient_df)
        
        return APIResponse(
            success=True,
            message="Health prediction completed",
            data={
                "risk_prediction": int(predictions[0]),
                "confidence_score': float(np.max(probabilities[0])),
                'recommendations': result["treatment_recommendations"]
        )
        
    except Exception as e:
        logger.error(f"Error predicting health outcomes: {e}")
        raise HTTPException(status_code=500, detail="Internal server error")

@app.post("/api/comprehensive-analysis", response_model=APIResponse)
async def comprehensive_health_analysis(
    request: PredictionRequest,
    token: str = Depends(verify_token)
):
    """Complete health analysis with education and predictions"""
    try:
        patient_df = pd.DataFrame([{
            'age': request.patient_data.age,
            'bmi': request.patient_data.bmi,
            'blood_pressure_systolic': request.patient_data.blood_pressure_systolic,
            'blood_pressure_diastolic': request.patient_data.blood_pressure_diastolic,
            'gender': request.patient_data.gender,
            'smoking_status': request.patient_data.smoking_status,
            'diabetes_status': request.patient_data.diabetes_status
        }])
        
        result = healthcare_ai.process_patient_case(
            patient_df,
            request.patient_data.condition,
            request.patient_data.symptoms
        )
        
        return APIResponse(
            success=True,
            message="Comprehensive health analysis completed",
            data=result
        )
        
    except Exception as e:
        logger.error(f"Error in comprehensive analysis: {e}")
        raise HTTPException(status_code=500, detail="Internal server error")

@app.get("/api/health")
async def health_check():
    return {"status": "healthy", "service": "healthcare_ai"}

if __name__ == "__main__":
    uvicorn.run(
        "healthcare_api:app",
        host="0.0.0.0",
        port=8000,
        reload=True
    )
```