Med Simplify

Making medical data easy to understand.

Comment

Med Simplify

Inspiration

Healthcare data is notoriously messy. Doctors write unstructured notes filled with shorthand, abbreviations, and inconsistencies, making it difficult for systems to consume or exchange information.

Med Simplify bridges this gap by converting raw medical notes into clean, interoperable data and visualizing them meaningfully.

What it Does

Med Simplify is a GenAI-powered Streamlit application that:

  1. Summarizes medical notes – Converts unstructured clinical text into structured summaries.
  2. Transforms summaries into FHIR resources – Ensures interoperability using healthcare’s most common standard.
  3. Validates summaries & FHIR outputs – Uses embeddings and cosine similarity for confidence scoring.
  4. Generates knowledge graphs – Inserts FHIR data into Neo4j and visualizes relationships between medical entities.

How I Built It

Summarization (Summary_code.py)

  • Used ChatOpenAI (via LangChain) with carefully designed HumanMessage prompts to turn raw notes into clear summaries.

FHIR Conversion (Summary_to_FHIR.py)

  • Transformed summaries into FHIR-compliant JSON using LLM prompting.

Validation

  • Summary Validation (Validating_summary.py): Compared generated vs. reference summaries using OpenAI Embeddings and cosine similarity.
  • FHIR Validation (Validating_FHIR.py): Converted FHIR back into text (fhir_to_text) and checked consistency with the original summary.

Graph Generation (insert_and_visualize_graph.py)

  • Inserted FHIR resources into Neo4j using Cypher queries.
  • Visualized relationships with NetworkX and Matplotlib.

Streamlit App (app.py)

  • Built a unified UI that handles uploads, summarization, FHIR conversion, validation, and graph visualization seamlessly.

Challenges I Ran Into

  • Integrating all modules properly in Streamlit.
  • Debugging mismatches between LLM outputs, JSON formatting for FHIR, and graph insertion.
  • Designing validation that is meaningful, not just “LLM says it’s fine.”

Accomplishments

  • Successfully integrated GenAI + FHIR + Neo4j + Streamlit into a single, functional application.
  • Completed the project independently, from concept to deployment.
  • Built a scalable pipeline, not just a demo.

What I Learned

  • Working with GenAI in healthcare contexts.
  • Importance of FHIR standards for interoperability.
  • Hands-on experience with graph databases (Neo4j) and visualization.
  • Crafting better LLM prompts for reliable outputs.

What's Next for Med Simplify

  • Scalability – Larger datasets and hospital EHR integration.
  • Improved validation – Domain-specific checks beyond cosine similarity.
  • Deployment – Cloud-based deployment for real-world testing.
  • Extensions – Multi-language support and specialty-specific customizations.

Built With

  • langchain
  • langchain-openai
  • matplotlib
  • neo4j
  • networkx
  • scipy
  • streamlit
Share this project:

Updates