Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.
We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate represen...
| Publicado en: | Journal of the American Medical Informatics Association Vol. 25; no. 1; pp. 93 - 99 |
|---|---|
| Autores principales: | , , , , |
| Formato: | research Journal Article |
| Publicado: |
Oxford University Press / USA
Jan2018
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=127021683&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 127021683 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 10675027 FZ9 jtl: Journal of the American Medical Informatics Association issn: 10675027 maglogo: N pubinfo: dt: Jan2018 vid: 25 iid: 1 pid: 622 pub: Oxford University Press / USA artinfo: ui: 127021683 127021683 NLM29025149 127021683 10.1093/jamia/ocx090 NLM29025149 127021683 ppf: 93 ppct: 6 formats: tig: atl: Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes. aug: au: Luo, Yuan Cheng, Yu Uzuner, Özlem Szolovits, Peter Starren, Justin affil: Department of Preventive Medicine, Northwestern University, Chicago, IL, USA sug: subj: Natural Language Processing Neural Networks (Computer) Human Data Collection Validation Studies Comparative Studies Evaluation Research Multicenter Studies Scales ab: We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2/VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem-treatment relations, 0.820 for medical problem-test relations, and 0.702 for medical problem-medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|