Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.
In: Journal of the American Medical Informatics Association, Jg. 25 (2018), Heft 1, S. 93-98
Online
academicJournal
Zugriff:
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. [ABSTRACT FROM AUTHOR]
Titel: |
Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.
|
---|---|
Autor/in / Beteiligte Person: | Luo, Yuan ; Cheng, Yu ; Uzuner, Özlem ; Szolovits, Peter ; Starren, Justin |
Link: | |
Zeitschrift: | Journal of the American Medical Informatics Association, Jg. 25 (2018), Heft 1, S. 93-98 |
Veröffentlichung: | 2018 |
Medientyp: | academicJournal |
ISSN: | 1067-5027 (print) |
DOI: | 10.1093/jamia/ocx090 |
Schlagwort: |
|
Sonstiges: |
|