DisTEMIST-bi-encoder

Model Description

DisTEMIST-bi-encoder is a domain-specific bi-encoder model for medical entity linking in Spanish, trained using synonym pairs from the DisTEMIST corpus and SNOMED-CT (Fully Specified Name and preferred synonyms). The training data was curated from the gold standard corpus and enriched with knowledge-based synonyms to enhance entity normalization tasks.

💡 Intended Use

• Domain: Spanish Clinical NLP
• Tasks: Entity linking of DisTEMIST mentions to SNOMED-CT concepts
• Evaluated On: DisTEMIST (Gold Standard, Unseen Mentions, Unseen Codes)
• Users: Researchers and developers focusing on specialized medical NEL

💬 Definitions

• Unseen Mentions: Mentions that do not appear in training but reference known codes.
• Unseen Codes: Mentions associated with SNOMED-CT codes never seen during training.

📈 Performance Summary (Top-25 Accuracy)

Evaluation Split	Top-25 Accuracy
Gold Standard	0.903
Unseen Mentions	0.819
Unseen Codes	0.793

🧪 Usage

from transformers import AutoModel, AutoTokenizer
import torch

model = AutoModel.from_pretrained("ICB-UMA/DisTEMIST-bi-encoder")
tokenizer = AutoTokenizer.from_pretrained("ICB-UMA/DisTEMIST-bi-encoder")

mention = "insuficiencia renal aguda"
inputs = tokenizer(mention, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs)
embedding = outputs.last_hidden_state[:, 0, :]
print(embedding.shape)

Use with Faiss or FaissEncoder for efficient retrieval.

⚠️ Limitations

• The model is specialized for DisTEMIST mentions and may underperform in other domains or corpora.
• Expert supervision is advised for clinical deployment.

📚 Citation

Gallego, Fernando and López-García, Guillermo and Gasco, Luis and Krallinger, Martin and Veredas, Francisco J., Clinlinker-Kb: Clinical Entity Linking in Spanish with Knowledge-Graph Enhanced Biencoders. Available at SSRN: http://dx.doi.org/10.2139/ssrn.4939986

Authors

Fernando Gallego, Guillermo López-García, Luis Gasco-Sánchez, Martin Krallinger, Francisco J Veredas