Multi-Label Learning from Medical Plain Text with Convolutional Residual Models

Yinyuan Zhang, Ricardo Henao, Zhe Gan, Yitong Li, Lawrence Carin
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:280-294, 2018.

Abstract

Predicting diagnoses from Electronic Health Records (EHRs) is an important medical application of multi-label learning. We propose a convolutional residual model for multi-label classification from doctor notes in EHR data. A given patient may have multiple diagnoses, and therefore multi-label learning is required. We employ a Convolutional Neural Network (CNN) to encode plain text into a fixed-length sentence embedding vector. Since diagnoses are typically correlated, a deep residual network is employed on top of the CNN encoder, to capture label (diagnosis) dependencies and incorporate information directly from the encoded sentence vector. A real EHR dataset is considered, and we compare the proposed model with several well-known baselines, to predict diagnoses based on doctor notes. Experimental results demonstrate the superiority of the proposed convolutional residual model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v85-zhang18a, title = {Multi-Label Learning from Medical Plain Text with Convolutional Residual Models}, author = {Zhang, Yinyuan and Henao, Ricardo and Gan, Zhe and Li, Yitong and Carin, Lawrence}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {280--294}, year = {2018}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {85}, series = {Proceedings of Machine Learning Research}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/zhang18a/zhang18a.pdf}, url = {https://proceedings.mlr.press/v85/zhang18a.html}, abstract = {Predicting diagnoses from Electronic Health Records (EHRs) is an important medical application of multi-label learning. We propose a convolutional residual model for multi-label classification from doctor notes in EHR data. A given patient may have multiple diagnoses, and therefore multi-label learning is required. We employ a Convolutional Neural Network (CNN) to encode plain text into a fixed-length sentence embedding vector. Since diagnoses are typically correlated, a deep residual network is employed on top of the CNN encoder, to capture label (diagnosis) dependencies and incorporate information directly from the encoded sentence vector. A real EHR dataset is considered, and we compare the proposed model with several well-known baselines, to predict diagnoses based on doctor notes. Experimental results demonstrate the superiority of the proposed convolutional residual model.} }
Endnote
%0 Conference Paper %T Multi-Label Learning from Medical Plain Text with Convolutional Residual Models %A Yinyuan Zhang %A Ricardo Henao %A Zhe Gan %A Yitong Li %A Lawrence Carin %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-zhang18a %I PMLR %P 280--294 %U https://proceedings.mlr.press/v85/zhang18a.html %V 85 %X Predicting diagnoses from Electronic Health Records (EHRs) is an important medical application of multi-label learning. We propose a convolutional residual model for multi-label classification from doctor notes in EHR data. A given patient may have multiple diagnoses, and therefore multi-label learning is required. We employ a Convolutional Neural Network (CNN) to encode plain text into a fixed-length sentence embedding vector. Since diagnoses are typically correlated, a deep residual network is employed on top of the CNN encoder, to capture label (diagnosis) dependencies and incorporate information directly from the encoded sentence vector. A real EHR dataset is considered, and we compare the proposed model with several well-known baselines, to predict diagnoses based on doctor notes. Experimental results demonstrate the superiority of the proposed convolutional residual model.
APA
Zhang, Y., Henao, R., Gan, Z., Li, Y. & Carin, L.. (2018). Multi-Label Learning from Medical Plain Text with Convolutional Residual Models. Proceedings of the 3rd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 85:280-294 Available from https://proceedings.mlr.press/v85/zhang18a.html.

Related Material