{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/accurate-clinical-and-biomedical-named-entity","title":"Accurate clinical and biomedical Named entity recognition at scale","arxiv_id":null,"date":"2022-07-19","proceeding":"Software Impacts 2022 7","authors":["Kocaman","Veysel;  Talby","David"],"abstract":"We introduce an agile, production-grade clinical and biomedical Named entity recognition (NER) algorithm based on a modified BiLSTM-CNN-Char DL architecture built on top of Apache Spark. Our NER implementation establishes new state-of-the-art accuracy on 7 of 8 well-known biomedical NER benchmarks and 3 clinical concept extraction challenges: 2010 i2b2/VA clinical concept extraction, 2014 n2c2 de-identification, and 2018 n2c2 medication extraction. Moreover, clinical NER models trained using this implementation outperform the accuracy of commercial entity extraction solutions, AWS Medical Comprehend and Google Cloud Healthcare API by a large margin (8.9% and 6.7% respectively), without using memory-intensive language models.","url_abs":"https://www.softwareimpacts.com/article/S2665-9638(22)00079-3/fulltext","url_pdf":"https://www.softwareimpacts.com/action/showPdf?pii=S2665-9638%2822%2900079-3","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"accurate-clinical-and-biomedical-named-entity","repo_url":"https://github.com/JohnSnowLabs/spark-nlp-workshop","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clinical-concept-extraction","task_name":"Clinical Concept Extraction"},{"task_slug":"de-identification","task_name":"De-identification"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-on-anatem","task":"Named Entity Recognition (NER)","dataset":"AnatEM","model":"BertForTokenClassification (Spark NLP)","rank_in_archive_order":5,"of":5,"metrics":{"F1":"91.65"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-bc4chemd","task":"Named Entity Recognition (NER)","dataset":"BC4CHEMD","model":"BertForTokenClassification (Spark NLP)","rank_in_archive_order":1,"of":7,"metrics":{"F1":"94.39"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-bc5cdr","task":"Named Entity Recognition (NER)","dataset":"BC5CDR","model":"BertForTokenClassification (Spark NLP)","rank_in_archive_order":5,"of":16,"metrics":{"F1":"90.89"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-bionlp13-cg","task":"Named Entity Recognition (NER)","dataset":"BioNLP13-CG","model":"BertForTokenClassification (Spark NLP)","rank_in_archive_order":2,"of":3,"metrics":{"F1":"87.83"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-species800","task":"Named Entity Recognition (NER)","dataset":"Species800","model":"BertForTokenClassification (Spark NLP)","rank_in_archive_order":2,"of":2,"metrics":{"F1":"82.59"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}