Upload README.md

README.md

@@ -15,6 +15,16 @@ tags:
 
 A MCP server for extracting and normalizing domain-specific entities from biomedical text. We leverage OpenAI LLMs to identify entities and match them to standardized terminology.
 
+## Motivation
+
+Biomedical text normalization addresses a critical challenge in healthcare informatics: approximately 80% of electronic health record (EHR) data exists as unstructured medical text. Such text often contains abbreviations, misspellings, and non-standardized terminology, creating barriers to effective data utilization. This variability hinders leveraging clinical narratives for:
+
+- **Clinical decision support** at the point of care
+- **Patient comprehension** of their own medical records
+- **Biomedical research** including cohort identification and pharmacovigilance
+
+By implementing named entity recognition and normalization to controlled vocabularies like SNOMED-CT, our MCP server enables downstream applications to process biomedical text with greater accuracy, bridging the gap between natural clinical language and structured data requirements of modern healthcare systems.
+
 ## Installation
 
 This project uses `uv` from Astral for dependency management. Follow these steps to set up the project:
@@ -81,3 +91,11 @@ The server exposes an MCP-compatible endpoint that can be used by AI agents. The
 - `target_entity`: Type of entity to extract ("Disease", "Tissue", or "Cell Type")
 
 and returns a list of normalized entities.
+
+## Future Improvements
+
+Our biomedical text normalization MCP server can be enhanced in several ways:
+
+- Expanded Entity Coverage: Extend beyond the current entity types (Disease, Tissue, Cell Type) to include medications, procedures, laboratory tests, and genomic entities.
+- User Feedback Loop: Implement a mechanism for users to correct normalization errors, creating a dataset for continuous model improvement.
+- Multilingual Support: Expand capabilities to handle medical text in languages beyond English.