Bvanaken

Rank:

Average Model Cost: $0.0000

Number of Runs: 5,510

Models by this creator

clinical-assertion-negation-bert

Clinical Assertion / Negation Classification BERT Model description The Clinical Assertion and Negation Classification BERT is introduced in the paper Assertion Detection in Clinical Notes: Medical Language Models to the Rescue? . The model helps structure information in clinical patient letters by classifying medical conditions mentioned in the letter into PRESENT, ABSENT and POSSIBLE. The model is based on the ClinicalBERT - Bio + Discharge Summary BERT Model by Alsentzer et al. and fine-tuned on assertion data from the 2010 i2b2 challenge. You can load the model via the transformers library: The model expects input in the form of spans/sentences with one marked entity to classify as PRESENT(0), ABSENT(1) or POSSIBLE(2). The entity in question is identified with the special token [entity] surrounding it. Example input and inference: Cite When working with the model, please cite our paper as follows:

$-/run

4.7K

Huggingface

CORe-clinical-outcome-biobert-v1

bvanaken

CORe Model - BioBERT + Clinical Outcome Pre-Training Model description The CORe (Clinical Outcome Representations) model is introduced in the paper Clinical Outcome Predictions from Admission Notes using Self-Supervised Knowledge Integration. It is based on BioBERT and further pre-trained on clinical notes, disease descriptions and medical articles with a specialised Clinical Outcome Pre-Training objective. You can load the model via the transformers library: From there, you can fine-tune it on clinical tasks that benefit from patient outcome knowledge. Pre-Training Data The model is based on BioBERT pre-trained on PubMed data. The Clinical Outcome Pre-Training included discharge summaries from the MIMIC III training set (specified here), medical transcriptions from MTSamples and clinical notes from the i2b2 challenges 2006-2012. It further includes ~10k case reports from PubMed Central (PMC), disease articles from Wikipedia and article sections from the MedQuAd dataset extracted from NIH websites. More Information For all the details about CORe and contact info, please visit CORe.app.datexis.com. Cite