Modelpublic

DT4H/CardioBERTa.sv_enriched

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes10downloads

Model Card

DT4HCardioBERTasv_enriched

DT4H_CardioBERTa_sv_enriched is a Swedish biomedical terminology encoder for clinical concept normalization and entity linking. It is initialized from [DT4H/CardioBERTa.sv] and specialized using CUI-supervised terminology pairs and metric learning.

Backbone

The backbone belongs to the CardioBERTa family from CardioLM - a multilingual suite of small language models for the cardiology domain. CardioBERTa comprises language-specific encoder models adapted to cardiology through continued pretraining on monolingual biomedical and cardiology-related corpora using Masked Language Modeling (MLM). The family covers Czech, Dutch, English, Italian, Romanian, Spanish and Swedish.

Training


Language	Swedish (`sv`)
Triplet collection	`enriched`
Strategy	`synonyms`
Objective	Multi-Similarity Loss
Mining	All triplets, margin 0.2
Pooling	CLS
Epochs	1
Batch size	256
Learning rate	2e-5
Max. length	25

CUI-supervised synonym pairs.

Terminology statistics

Strategy	Triplets	CUIs	Unique terms	Unique positives	Terms/CUI	Δ terms
synonyms	80,858	80,858	155,374	80,488	1.95	0
parents	1,683,288	476,433	539,077	395,832	3.97	+383,703
grandparents	4,915,580	476,972	539,362	447,784	9.89	+383,988

This model uses 80,858 triplets, covering 80,858 CUIs and 155,374 unique normalized terms.

The training terminology is not distributed with this repository because it contains resources subject to UMLS licensing conditions. Only aggregate statistics are released.

Intended use

The model is intended for terminology embedding, biomedical candidate retrieval, concept normalization and entity linking, particularly in cardiology and clinical NLP pipelines. It is not intended for direct clinical decision-making.

Usage

python

import torch
import torch.nn.functional as F
from transformers import AutoModel, AutoTokenizer

model_id = "DT4H/DT4H_CardioBERTa_sv_enriched"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id)

inputs = tokenizer(
    "clinical concept",
    return_tensors="pt",
    truncation=True,
    max_length=25,
)

with torch.no_grad():
    output = model(**inputs)

embedding = F.normalize(
    output.last_hidden_state[:, 0, :],
    p=2,
    dim=1,
)

Reference

Danu et al. CardioLM - a multilingual suite of small language models for the cardiology domain.

Developed within the DataTools4Heart (DT4H) project, Grant Agreement 101057849.