Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention

Justin Lovelace, Nathan C. Hurley, Adrian D. Haimovich, Bobak J. Mortazavi
Proceedings of the 5th Machine Learning for Healthcare Conference, PMLR 126:245-270, 2020.

Abstract

Problem lists are intended to provide clinicians with a relevant summary of patient medical issues and are embedded in many electronic health record systems. Despite their importance, problem lists are often cluttered with resolved or currently irrelevant conditions. In this work, we develop a novel end-to-end framework that first extracts diagnosis and procedure information from clinical notes and subsequently uses the extracted medical problems to predict patient outcomes. This framework is both more performant and more interpretable than existing models used within the domain, achieving an AU-ROC of 0.710 for bounceback readmission and 0.869 for in-hospital mortality occurring after ICU discharge. We identify risk factors for both readmission and mortality outcomes and demonstrate that our framework can be used to develop dynamic problem lists that present clinical problems along with their quantitative importance. We conduct a qualitative user study with medical experts and demonstrate that they view the lists produced by our framework favorably and find them to be a more effective clinical decision support tool than a strong baseline.

Cite this Paper


BibTeX
@InProceedings{pmlr-v126-lovelace20a, title = {Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention}, author = {Lovelace, Justin and Hurley, Nathan C. and Haimovich, Adrian D. and Mortazavi, Bobak J.}, booktitle = {Proceedings of the 5th Machine Learning for Healthcare Conference}, pages = {245--270}, year = {2020}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {126}, series = {Proceedings of Machine Learning Research}, month = {07--08 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v126/lovelace20a/lovelace20a.pdf}, url = {https://proceedings.mlr.press/v126/lovelace20a.html}, abstract = {Problem lists are intended to provide clinicians with a relevant summary of patient medical issues and are embedded in many electronic health record systems. Despite their importance, problem lists are often cluttered with resolved or currently irrelevant conditions. In this work, we develop a novel end-to-end framework that first extracts diagnosis and procedure information from clinical notes and subsequently uses the extracted medical problems to predict patient outcomes. This framework is both more performant and more interpretable than existing models used within the domain, achieving an AU-ROC of 0.710 for bounceback readmission and 0.869 for in-hospital mortality occurring after ICU discharge. We identify risk factors for both readmission and mortality outcomes and demonstrate that our framework can be used to develop dynamic problem lists that present clinical problems along with their quantitative importance. We conduct a qualitative user study with medical experts and demonstrate that they view the lists produced by our framework favorably and find them to be a more effective clinical decision support tool than a strong baseline.} }
Endnote
%0 Conference Paper %T Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention %A Justin Lovelace %A Nathan C. Hurley %A Adrian D. Haimovich %A Bobak J. Mortazavi %B Proceedings of the 5th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2020 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v126-lovelace20a %I PMLR %P 245--270 %U https://proceedings.mlr.press/v126/lovelace20a.html %V 126 %X Problem lists are intended to provide clinicians with a relevant summary of patient medical issues and are embedded in many electronic health record systems. Despite their importance, problem lists are often cluttered with resolved or currently irrelevant conditions. In this work, we develop a novel end-to-end framework that first extracts diagnosis and procedure information from clinical notes and subsequently uses the extracted medical problems to predict patient outcomes. This framework is both more performant and more interpretable than existing models used within the domain, achieving an AU-ROC of 0.710 for bounceback readmission and 0.869 for in-hospital mortality occurring after ICU discharge. We identify risk factors for both readmission and mortality outcomes and demonstrate that our framework can be used to develop dynamic problem lists that present clinical problems along with their quantitative importance. We conduct a qualitative user study with medical experts and demonstrate that they view the lists produced by our framework favorably and find them to be a more effective clinical decision support tool than a strong baseline.
APA
Lovelace, J., Hurley, N.C., Haimovich, A.D. & Mortazavi, B.J.. (2020). Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention. Proceedings of the 5th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 126:245-270 Available from https://proceedings.mlr.press/v126/lovelace20a.html.

Related Material