termmap_semantic_model

Model Description

This is a clinical semantic mapping model trained for medical terminology normalization and semantic search. The model is specifically designed for the TermMap system to map medical terms across different coding systems (RXNORM, SNOMED, ICD10, etc.) using semantic similarity.

Model Details

• Model Type: Sentence Transformer (BERT-based)
• Architecture: 6-layer BERT with 384 hidden dimensions
• Vocabulary Size: 30,522 tokens
• Max Sequence Length: 512 tokens
• Embedding Dimension: 384
• Training Data: UMLS (Unified Medical Language System) - Iteration 3
• Loss Function: MultipleNegativesRankingLoss
• Base Model: sentence-transformers/all-MiniLM-L6-v2

Intended Use

This model is designed for:

• Medical terminology mapping: Finding semantic equivalents across different medical coding systems
• Clinical semantic search: Retrieving relevant medical concepts using semantic similarity
• Healthcare NLP: Supporting various medical text processing tasks
• OpenSearch integration: Providing embeddings for semantic search in medical databases

Performance

The model has been trained on comprehensive UMLS data including:

• Medical terminology from multiple coding systems
• Semantic relationships between medical concepts
• Clinical text from various healthcare domains

Technical Specifications

• Framework: PyTorch + Sentence Transformers
• Precision: FP32
• Model Size: ~90MB

Applications

TermMap System

This model powers the semantic search component of the TermMap medical terminology mapping pipeline:

1. Exact Lookup: Direct code-to-code mapping
2. Semantic Search: This model finds semantically similar terms
3. Reranking: Results are reranked using specialized medical models
4. Validation: Final validation and scoring

Clinical Use Cases

• EHR Data Normalization: Standardizing clinical terms in electronic health records
• Medical Coding: Assisting in ICD-10, CPT, and other medical coding tasks
• Clinical Decision Support: Finding related medical concepts and treatments
• Research: Supporting medical research through semantic term matching

Model Card Authors

HiLabs Clinical Team

Citation

If you use this model in your research, please cite:

@misc{termmap_semantic_model,
  author = {HiLabs Team},
  title = {TermMap - Terminology Mapper},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/hilabs/termmap_semantic_model}
}

License

Apache 2.0

Contact

For questions or issues related to this model, please contact the HiLabs team.