Clinical Judgement Study using Question Answering from Electronic Health Records

Bhanu Pratap Singh Rawat, Fe Li, Hong Yu
; Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:216-229, 2019.

Abstract

Clinical judgement studies are essential for recognising the causal relation of a medication with adverse drug reactions (ADRs). Traditionally, these studies are conducted via expert manual chart review. By contrast, we propose an end-to-end deep learning question answering model to automatically infer such causal relations. Our proposed model identifies the causal relation by answering a subset of Naranjo questionnaire Naranjo et al. (1981) from electronic health records. It employs multi-level attention layers along with local and global context while answering these questions. Our proposed model achieves a macro-weighted F-score of 0.4598 - 0.5142 across the selected questions and an overall F-score of 0.5011. We also did an ablation study to validate the importance of local and global context for the model.

Cite this Paper


BibTeX
@InProceedings{pmlr-v106-rawat19a, title = {Clinical Judgement Study using Question Answering from Electronic Health Records}, author = {Rawat, Bhanu Pratap Singh and Li, Fe and Yu, Hong}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {216--229}, year = {2019}, editor = {Finale Doshi-Velez and Jim Fackler and Ken Jung and David Kale and Rajesh Ranganath and Byron Wallace and Jenna Wiens}, volume = {106}, series = {Proceedings of Machine Learning Research}, address = {Ann Arbor, Michigan}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/rawat19a/rawat19a.pdf}, url = {http://proceedings.mlr.press/v106/rawat19a.html}, abstract = {Clinical judgement studies are essential for recognising the causal relation of a medication with adverse drug reactions (ADRs). Traditionally, these studies are conducted via expert manual chart review. By contrast, we propose an end-to-end deep learning question answering model to automatically infer such causal relations. Our proposed model identifies the causal relation by answering a subset of Naranjo questionnaire Naranjo et al. (1981) from electronic health records. It employs multi-level attention layers along with local and global context while answering these questions. Our proposed model achieves a macro-weighted F-score of 0.4598 - 0.5142 across the selected questions and an overall F-score of 0.5011. We also did an ablation study to validate the importance of local and global context for the model.} }
Endnote
%0 Conference Paper %T Clinical Judgement Study using Question Answering from Electronic Health Records %A Bhanu Pratap Singh Rawat %A Fe Li %A Hong Yu %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-rawat19a %I PMLR %J Proceedings of Machine Learning Research %P 216--229 %U http://proceedings.mlr.press %V 106 %W PMLR %X Clinical judgement studies are essential for recognising the causal relation of a medication with adverse drug reactions (ADRs). Traditionally, these studies are conducted via expert manual chart review. By contrast, we propose an end-to-end deep learning question answering model to automatically infer such causal relations. Our proposed model identifies the causal relation by answering a subset of Naranjo questionnaire Naranjo et al. (1981) from electronic health records. It employs multi-level attention layers along with local and global context while answering these questions. Our proposed model achieves a macro-weighted F-score of 0.4598 - 0.5142 across the selected questions and an overall F-score of 0.5011. We also did an ablation study to validate the importance of local and global context for the model.
APA
Rawat, B.P.S., Li, F. & Yu, H.. (2019). Clinical Judgement Study using Question Answering from Electronic Health Records. Proceedings of the 4th Machine Learning for Healthcare Conference, in PMLR 106:216-229

Related Material