Abstract
Predicting outbursts of hazardous medical conditions and its importance has arisen significantly in recent years, particularly in patients hospitalized in the Intensive Care Unit (ICU). In hospitals worldwide, patients are developing life-threatening complications, which might lead to organ dysfunctions and, if not treated properly, to death. In this study, we use patients’ longitudinal vital signs data from the ICUs, focusing on predicting Acute Hypertensive Episodes (AHE). In this study, two approaches were used for prediction: predicting continuously whether a patient will experience an AHE in a pre-defined time period ahead using an observation sliding window, or predicting whether it will generally occur during the ICU admission, given a fixed time period from the admission. Temporal abstraction was employed to transform the heterogeneous multivariate temporal data into a uniform representation of symbolic time intervals, and frequent Time Intervals Related Patterns (TIRPs), which are used as features for classification. For comparison, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are used. Our results show that using frequent temporal patterns leads to a better AHE prediction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allen, J.: \(^{\rm a}\)maintaining knowledge about temporal intervals, \(^{\circ }\) comm (1983)
Benken, S.T.: Hypertensive emergencies. Medical Issues in the ICU (2018)
Futoma, J., et al.: An improved multi-output gaussian process RNN with real-time validation for early sepsis detection. arXiv preprint arXiv:1708.05894 (2017)
Ghosh, S., Li, J., Cao, L., Ramamohanarao, K.: Septic shock prediction for ICU patients via coupled hmm walking on sequential contrast patterns. J. Biomed. Inform. 66, 19–31 (2017)
Jin, K., Stockbridge, N.: Predicting acute hypotensive episodes from ambulatory blood pressure telemetry. Stat. Interface 5(4), 425–429 (2012)
Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016)
Moskovitch, R., Choi, H., Hripcsak, G., Tatonetti, N.P.: Prognosis of clinical outcomes with temporal patterns and experiences with one class feature selection. IEEE/ACM Trans. Comput. Biol. Bioinform. 14(3), 555–563 (2016)
Moskovitch, R., Shahar, Y.: Classification-driven temporal discretization of multivariate time series. Data Min. Knowl. Discov. 29(4), 871–913 (2015)
Moskovitch, R., Walsh, C., Wang, F., Hripcsak, G., Tatonetti, N.: Outcomes prediction via time intervals related patterns. In: 2015 IEEE International Conference on Data Mining, pp. 919–924. IEEE (2015)
Pak, K.J., Hu, T., Fee, C., Wang, R., Smith, M., Bazzano, L.A.: Acute hypertension: a systematic review and appraisal of guidelines. Ochsner J. 14(4), 655–663 (2014)
Rocha, T., Paredes, S., De Carvalho, P., Henriques, J.: Prediction of acute hypotensive episodes by means of neural network multi-models. Comput. Biol. Med. 41(10), 881–890 (2011)
Vuylsteke, A., et al.: Characteristics, practice patterns, and outcomes in patients with acute hypertension: European registry for Studying the Treatment of Acute hyperTension (Euro-STAT). Crit. Care 15(6), R271 (2011)
van Wyk, F., Khojandi, A., Davis, R.L., Kamaleswaran, R.: Physiomarkers in real-time physiological data streams predict adult sepsis onset earlier than clinical practice. bioRxiv, p. 322305 (2018)
Zhao, J., et al.: Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction. Sci. Rep. 9(1), 1–10 (2019)
Zhou, Y., Zhu, Q., Huang, H.: Prediction of acute hypotensive episode in ICU using Chebyshev neural network. JSW 8(8), 1923–1931 (2013)
Acknowledgments
This research was supported by a collaboration grant of the Israeli Ministry of Science and Technology grant #8760441 and a donation from the Prof. Avram and Anat Bar-Cohen Project Desert Nova. Nevo Itzhak was funded by Kreitman School of Advanced Graduate Studies and the Israeli Ministry of Science and Technology Jabotinsky scholarship grant #3-16643.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
A Appendix 1 - Demographic and Physiological Characteristics
The demographic information of the patients (see Table 1).
B Appendix 2 - Model Parameters
The parameters of each model are selected after testing the performance of each combination (not in a greedy comparison approach), and here we describe the parameters that performed best. For the TIRPs based model, we used Random Forest as the classifier with 100 trees in the forest and a maximum depth of 5 for the tree. Bootstrap is used when building trees and out-of-bag samples to estimate the generalization accuracy. Random Forest was implemented with Python 3.6 Scikit-Learn (https://scikit-learn.org/stable/) version 0.22.1. For the parameters we did not specify, we used the default.
For the CNN, we used one conventional layer with 48 filters and a kernel size of 7, stride length of one, same padding (i.e., the output size is the same as the input size), ReLU as the activation function and max-polling size of 3. Then, we defined two more fully connected hidden layers with 128 and 8 neurons. Activation function LeakyReLU with a dropout rate of 0.4 and 0.3, respectively, and a batch normalization in each layer. The batch size was 128, the initial learning rate was set to 0.0005 and the used optimizer was Nadam. Softmax activation was used in the output layer.
For all RNN, we used a 1 hidden dense layer LSTM with 64 hidden units per layer and with a recurrent dropout of 0.2. Activation function LeakyReLU with a dropout rate of 0.3 and a batch normalization in each layer. Then, we defined fully connected hidden layers with 128 neurons. We trained all models using a maximum epoch of 80, a batch size of 128 and a learning rate of 0.001. We used early stopping for both RNN and CNN, with a minimum change of 0.001, lower than this value, it is not considered as an improvement for the loss and is tolerated for 5 epochs. Both RNN and CNN models were implemented with Keras (https://keras.io/) version 2.2.5. For the parameters we did not specify, we used the default.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Itzhak, N. et al. (2020). Acute Hypertensive Episodes Prediction. In: Michalowski, M., Moskovitch, R. (eds) Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science(), vol 12299. Springer, Cham. https://doi.org/10.1007/978-3-030-59137-3_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-59137-3_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59136-6
Online ISBN: 978-3-030-59137-3
eBook Packages: Computer ScienceComputer Science (R0)