SOTAVerified

Clinical Concept Extraction

Automatic extraction of clinical named entities such as clinical problems, treatments, tests and anatomical parts from clinical notes.

( Source )

Papers

Showing 110 of 24 papers

TitleStatusHype
Accurate clinical and biomedical Named entity recognition at scaleCode3
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From CharactersCode1
Recurrent neural networks with specialized word embeddings for health-domain named-entity recognitionCode0
CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domainCode0
Improving Clinical Document Understanding on COVID-19 Research with Spark NLPCode0
Clinical Concept Extraction with Contextual Word EmbeddingCode0
Embedding Strategies for Specialized Domains: Application to Clinical Entity RecognitionCode0
Bidirectional LSTM-CRF for Clinical Concept ExtractionCode0
Bidirectional LSTM-CRF for Clinical Concept ExtractionCode0
BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports0
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BERTlarge (MIMIC)Exact Span F190.25Unverified
2CharacterBERT (base, medical)Exact Span F189.24Unverified
3ClinicalBERTExact Span F187.4Unverified
4ELMo (finetuned on i2b2) + word2vec (i2b2)Exact Span F186.23Unverified
5deBruijn et al. (System 1.1)Exact Span F185.23Unverified