A hybrid Neural Network Model for Joint Prediction of Presence and Period Assertions of Medical Events in Clinical Notes
| dc.contributor.author | Rumeng, Li | |
| dc.contributor.author | Abhyuday, Jagannatha | |
| dc.contributor.author | Yu, Hong | |
| dc.date | 2022-08-11T08:09:50.000 | |
| dc.date.accessioned | 2022-08-23T16:45:16Z | |
| dc.date.available | 2022-08-23T16:45:16Z | |
| dc.date.issued | 2018-04-16 | |
| dc.date.submitted | 2018-06-20 | |
| dc.identifier.citation | <p>AMIA Annu Symp Proc. 2018 Apr 16;2017:1149-1158. eCollection 2017.</p> | |
| dc.identifier.issn | 1559-4076 (Linking) | |
| dc.identifier.pmid | 29854183 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.14038/40648 | |
| dc.description.abstract | In this paper, we propose a novel neural network architecture for clinical text mining. We formulate this hybrid neural network model (HNN), composed of recurrent neural network and deep residual network, to jointly predict the presence and period assertion values associated with medical events in clinical texts. We evaluate the effectiveness of our model on a corpus of expert-annotated longitudinal Electronic Health Records (EHR) notes from Cancer patients. Our experiments show that HNN improves the joint assertion classification accuracy as compared to conventional baselines. | |
| dc.language.iso | en_US | |
| dc.relation | <p><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=29854183&dopt=Abstract">Link to Article in PubMed</a></p> | |
| dc.relation.url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977733/ | |
| dc.rights | Copyright ©2017 AMIA - All rights reserved. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose | |
| dc.subject | clinical text mining | |
| dc.subject | data mining | |
| dc.subject | neural networks | |
| dc.subject | electronic health records | |
| dc.subject | Artificial Intelligence and Robotics | |
| dc.subject | Databases and Information Systems | |
| dc.subject | Health Information Technology | |
| dc.title | A hybrid Neural Network Model for Joint Prediction of Presence and Period Assertions of Medical Events in Clinical Notes | |
| dc.type | Conference Paper | |
| dc.source.volume | 2017 | |
| dc.identifier.legacyfulltext | https://escholarship.umassmed.edu/cgi/viewcontent.cgi?article=4461&context=oapubs&unstamped=1 | |
| dc.identifier.legacycoverpage | https://escholarship.umassmed.edu/oapubs/3450 | |
| dc.identifier.contextkey | 12344366 | |
| refterms.dateFOA | 2022-08-23T16:45:16Z | |
| html.description.abstract | <p>In this paper, we propose a novel neural network architecture for clinical text mining. We formulate this hybrid neural network model (HNN), composed of recurrent neural network and deep residual network, to jointly predict the presence and period assertion values associated with medical events in clinical texts. We evaluate the effectiveness of our model on a corpus of expert-annotated longitudinal Electronic Health Records (EHR) notes from Cancer patients. Our experiments show that HNN improves the joint assertion classification accuracy as compared to conventional baselines.</p> | |
| dc.identifier.submissionpath | oapubs/3450 | |
| dc.contributor.department | Department of Quantitative Health Sciences | |
| dc.source.pages | 1149-1158 |
