Analyze Medical Reports with Bedrock, LangChain and Streamlit

Powered by Amazon Bedrock and Advanced LLMs

At the heart of our solution are the large language models available through Amazon Bedrock, including Anthropic’s Claude and Amazon Nova Foundation Models. The chosen model processes natural language queries with medical context awareness, enabling detailed interpretation of healthcare data. Medical reports are securely stored in Amazon S3 and processed via LangChain. The Streamlit interface allows real-time interaction, presenting results through interactive visualizations powered by Plotly.

Key Insights About Analyze Medical Reports with Bedrock

This section explores the key aspects and implications of analyzing medical reports with Bedrock in the current market landscape.

Prerequisites: What You’ll Need

Before getting started, ensure you have:

• An active AWS account with appropriate permissions
• Python 3.x installed on your system
• AWS CLI configured with your credentials
• An S3 bucket for storing medical reports
• Access to Amazon Bedrock models

Step-by-Step Deployment Guide

Step 1: Clone the Repository

git clone https://github.com/aws-samples/sample-medical-analysis-dashboard.git

Step 2: Navigate to the Project Directory

Change to the project directory after cloning.

Step 3: Create and Activate a Virtual Environment

For Mac/Linux:

python3 -m venv venv
source venv/bin/activate

For Windows:

python3 -m venv venv
venv\Scripts\activate

Step 4: Update pip to the Latest Version

python3 -m pip install --upgrade pip

Step 5: Install Required Packages

pip install -r requirements.txt

Step 6: Configure AWS Credentials

Follow the AWS CLI configuration guide for environment variables:

export AWS_ACCESS_KEY_ID='your-access-key'
export AWS_SECRET_ACCESS_KEY='your-secret-key'

Step 7: Upload Sample CSV Files to S3

Upload the sample medical report files to your S3 bucket:

aws s3 cp basic_test.csv s3://BUCKET_NAME/
aws s3 cp blood_test.csv s3://BUCKET_NAME/

Next, go to app.py line 68 and update the S3 bucket name to match your actual bucket:

BUCKET_NAME = "your-bucket-name"

Step 8: Run the Application

streamlit run app.py

Sample Medical Report Format

Here’s an example of the CSV format for medical reports:

Parameter,Value,Reference_Range,Unit
Hemoglobin,13.8,13.5-17.5,g/dL
RBC,4.8,4.5-5.9,million/µL
WBC,8500,4000-11000,cells/µL
Glucose,92,70-100,mg/dL
Creatinine,1.0,0.7-1.3,mg/dL

Example Queries You Can Ask

Once the dashboard is running, try these sample queries:

Basic Query

What is the hemoglobin level in report?

Comparative Analysis

How does this compare to other parameters in the report? Are there any that stand out?

Advanced Pattern Analysis

Can you analyze the distribution patterns of percentage-based measurements versus absolute values in this report, and identify any notable patterns in their reference ranges?

HIPAA Compliance and Security Considerations

When deploying this solution in a production environment, ensure:

• HIPAA-compliant AWS configurations are in place
• Data encryption at rest and in transit
• Proper access controls and audit logging
• Regular security assessments and compliance reviews

Cleanup: Avoiding Ongoing Charges

To avoid ongoing AWS charges, follow these cleanup steps:

# Deactivate virtual environment
deactivate

# Remove project directory and virtual environment
rm -rf medical-analysis-dashboard/

Additionally, delete the created Amazon S3 bucket through the AWS Console or CLI.

Best Practices for Peak Performance

• Tune the foundational model on organization-specific medical data
• Use pre-trained medical LLMs available in AWS Marketplace
• Configure Amazon Bedrock guardrails to ensure compliance
• Implement proper error handling and logging
• Regular model evaluation and performance monitoring

Take Action: Start Your AI-Powered Healthcare Journey

Ready to take your medical report analysis to the next level? Clone the repository, follow the deployment steps, and start exploring the power of AI-driven insights. Don’t just read medical reports; understand them. Dive into the sample medical analysis dashboard and revolutionize your healthcare data experience today!