@article{jagannatha_bidirectional_2016-1,
	title = {Bidirectional {RNN} for {Medical} {Event} {Detection} in {Electronic} {Health} {Records}},
	volume = {2016},
	abstract = {Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored recurrent neural network frameworks and show that they significantly out-performed the CRF models.},
	language = {eng},
	journal = {Proc Conf},
	author = {Jagannatha, Abhyuday N. and Yu, Hong},
	month = jun,
	year = {2016},
	pmid = {27885364},
	pmcid = {PMC5119627},
	pages = {473--482}
}

{"_id":"zgFsYMdy2ZtTndFyA","bibbaseid":"jagannatha-yu-bidirectionalrnnformedicaleventdetectioninelectronichealthrecords-2016","downloads":0,"creationDate":"2017-02-27T16:14:39.948Z","title":"Bidirectional RNN for Medical Event Detection in Electronic Health Records","author_short":["Jagannatha, A. N.","Yu, H."],"year":2016,"bibtype":"article","biburl":"http://bio-nlp.org/papers/pubs-all.bib","bibdata":{"bibtype":"article","type":"article","title":"Bidirectional RNN for Medical Event Detection in Electronic Health Records","volume":"2016","abstract":"Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored recurrent neural network frameworks and show that they significantly out-performed the CRF models.","language":"eng","journal":"Proc Conf","author":[{"propositions":[],"lastnames":["Jagannatha"],"firstnames":["Abhyuday","N."],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"June","year":"2016","pmid":"27885364","pmcid":"PMC5119627","pages":"473--482","bibtex":"@article{jagannatha_bidirectional_2016-1,\n\ttitle = {Bidirectional {RNN} for {Medical} {Event} {Detection} in {Electronic} {Health} {Records}},\n\tvolume = {2016},\n\tabstract = {Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored recurrent neural network frameworks and show that they significantly out-performed the CRF models.},\n\tlanguage = {eng},\n\tjournal = {Proc Conf},\n\tauthor = {Jagannatha, Abhyuday N. and Yu, Hong},\n\tmonth = jun,\n\tyear = {2016},\n\tpmid = {27885364},\n\tpmcid = {PMC5119627},\n\tpages = {473--482}\n}\n\n","author_short":["Jagannatha, A. N.","Yu, H."],"key":"jagannatha_bidirectional_2016-1","id":"jagannatha_bidirectional_2016-1","bibbaseid":"jagannatha-yu-bidirectionalrnnformedicaleventdetectioninelectronichealthrecords-2016","role":"author","urls":{},"downloads":0,"html":""},"search_terms":["bidirectional","rnn","medical","event","detection","electronic","health","records","jagannatha","yu"],"keywords":[],"authorIDs":[],"dataSources":["NWFE68FH3u4we7mqC"]}