Abstract
When it comes to assessing General Internal Medicine (GIM) patients’ state, physicians often rely on structured, time series physiological data because it’s more efficient and requires less effort to review than unstructured nursing notes. However, these text-based notes can have important information in predicting a patient’s outcome. Therefore, in this paper we train two convolutional neural networks (CNN) on in-house hospital nursing notes and physiological data with temporally segmented sliding windows to understand the differences. And we visualize the process in which deep models generate the outcome prediction through interpretable gradient-based visualization techniques. We find that the notes model provides overall better predictions results and it is capable of sending warnings for crashing patients in a more timely manner. Also, to illustrate the different focal points of the models, we identified the top contributing factors each deep model utilizes to make predictions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We define a “crashing” patient as someone who is experiencing one of the following outcomes: death on the GIM ward, transfer to intensive care unit (ICU), or transfer to palliative unit.
- 2.
A Hospital that is part of Unity Health Toronto.
- 3.
Nil per os is Latin for “nothing by mouth” and is used when a patient cannot receive food orally.
References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993–1022 (2003)
Frize, M., Ennett, C.M., Stevenson, M., Trigg, H.C.: Clinical decision support systems for intensive care units: using artificial neural networks. Med. Eng. Phys. 23(3), 217–225 (2001)
Ghassemi, M., et al.: Unfolding physiological state: mortality modelling in intensive care units. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 75–84. ACM (2014)
Ghassemi, M., Naumann, T., Schulam, P., Beam, A.L., Ranganath, R.: Opportunities in machine learning for healthcare. arXiv:1806.00388 [cs, stat] (2018)
Ghassemi, M., et al.: A multivariate timeseries modeling approach to severity of illness assessment and forecasting in ICU with sparse, heterogeneous clinical data. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
Johnson, A.E., et al.: Mimic-iii, a freely accessible critical care database. Sci. Data 3, 160035 (2016)
Khadanga, S., Aggarwal, K., Joty, S., Srivastava, J.: Using clinical notes with time series data for ICU management. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6433–6438. Association for Computational Linguistics, Hong Kong, China (2019). https://doi.org/10.18653/v1/D19-1678
Khine, A.H., Wettayaprasit, W., Duangsuwan, J.: Ensemble CNN and MLP with nurse notes for intensive care unit mortality. In: 2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 236–241. IEEE (2019)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751. Association for Computational Linguistics, Doha, Qatar (2014). https://doi.org/10.3115/v1/D14-1181
Lovelace, J.R., Hurley, N.C., Haimovich, A.D., Mortazavi, B.J.: Explainable prediction of adverse outcomes using clinical notes. arXiv preprint arXiv:1910.14095 (2019)
Nguyen, P., Tran, T., Wickramasinghe, N., Venkatesh, S.: Deepr: a convolutional net for medical records. IEEE J. Biomed. Health Inform. 21(1), 22–30 (2017). https://doi.org/10.1109/JBHI.2016.2633963
Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543. Association for Computational Linguistics, Doha, Qatar (2014). https://doi.org/10.3115/v1/D14-1162
Quoc, L., Tomas, M.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188–1196 (2014)
Řehůřek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, pp. 45–50. ELRA, Valletta (2010)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Smith, G.B., Prytherch, D.R., Meredith, P., Schmidt, P.E., Featherstone, P.I.: The ability of the national early warning score (news) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death. Resuscitation 84(4), 465–470 (2013)
Waudby-Smith, I.E., Tran, N., Dubin, J.A., Lee, J.: Sentiment in nursing notes as an indicator of out-of-hospital mortality in intensive care patients. PloS one 13(6), e0198687 (2018). Public Library of Science
Wellner, B., et al.: Predicting unplanned transfers to the Intensive Care Unit: a machine learning approach leveraging diverse clinical elements. JMIR Med. Inf. 5(4) (2017). https://doi.org/10.2196/medinform.8680
Wu, Y., Jiang, M., Xu, J., Zhi, D., Xu, H.: Clinical named entity recognition using deep learning models. In: AMIA Annual Symposium Proceedings, vol. 2017, p. 1812. American Medical Informatics Association (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Yao, J. et al. (2021). Visualization of Deep Models on Nursing Notes and Physiological Data for Predicting Health Outcomes Through Temporal Sliding Windows. In: Shaban-Nejad, A., Michalowski, M., Buckeridge, D.L. (eds) Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, vol 914. Springer, Cham. https://doi.org/10.1007/978-3-030-53352-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-53352-6_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-53351-9
Online ISBN: 978-3-030-53352-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)