×

A long short-term memory ensemble approach for improving the outcome prediction in intensive care unit. (English) Zbl 1428.92058

Summary: In intensive care unit (ICU), it is essential to predict the mortality of patients and mathematical models aid in improving the prognosis accuracy. Recently, recurrent neural network (RNN), especially long short-term memory (LSTM) network, showed advantages in sequential modeling and was promising for clinical prediction. However, ICU data are highly complex due to the diverse patterns of diseases; therefore, instead of single LSTM model, an ensemble algorithm of LSTM (eLSTM) is proposed, utilizing the superiority of the ensemble framework to handle the diversity of clinical data. The eLSTM algorithm was evaluated by the acknowledged database of ICU admissions Medical Information Mart for Intensive Care III (MIMIC-III). The investigation in total of 18415 cases shows that compared with clinical scoring systems SAPS II, SOFA, and APACHE II, random forests classification algorithm, and the single LSTM classifier, the eLSTM model achieved the superior performance with the largest value of area under the receiver operating characteristic curve (AUROC) of 0.8451 and the largest area under the precision-recall curve (AUPRC) of 0.4862. Furthermore, it offered an early prognosis of ICU patients. The results demonstrate that the eLSTM is capable of dynamically predicting the mortality of patients in complex clinical situations.

MSC:

92C50 Medical applications (general)
62P10 Applications of statistics to biology and medical sciences; meta analysis
62H30 Classification and discrimination; cluster analysis (statistical aspects)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Jin, Y.; Cai, X. Y.; Cai, Y. C., To build a prognostic score model containing indispensible tumour markers for metastatic nasopharyngeal carcinoma in an epidemic area, European Journal of Cancer, 48, 6, 882-888 (2012) · doi:10.1016/j.ejca.2011.09.004
[2] Minne, L.; Abu-Hanna, A.; de Jonge, E., Evaluation of SOFA-based models for predicting mortality in the ICU: a systematic review, Critical Care, 12, 6, 1-13 (2009) · doi:10.1186/cc7160
[3] Le Gall, J.-R.; Lemeshow, S.; Saulnier, F., A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study, JAMA: The Journal of the American Medical Association, 270, 24, 2957-2963 (1993) · doi:10.1001/jama.1993.03510240069035
[4] Vincent, J.-L.; Moreno, R.; Takala, J., The SOFA (Sepsis-related organ failure assessment) score to describe organ dysfunction/failure, Intensive Care Medicine, 22, 7, 707-710 (1996) · doi:10.1007/bf01709751
[5] Knaus, W. A.; Draper, E. A.; Wagner, D. P.; Zimmerman, J. E., APACHE II: a severity of disease classification system, Critical Care Medicine, 13, 10, 818-829 (1985) · doi:10.1097/00003246-198510000-00009
[6] Purushotham, S.; Meng, C.; Che, Z.; Liu, Y., Benchmark of deep learning models on large healthcare MIMIC datasets, http://adsabs.harvard.edu/abs/2017arXiv171008531P
[7] Johnson, A. E.; Pollard, T. J.; Mark, R. G., Reproducibility in critical care: a mortality prediction case study, Proceedings of the Machine Learning for Healthcare Conference
[8] Lee, J.; Maslove, D. M.; Dubin, J. A., Personalized mortality prediction driven by electronic medical data and a patient similarity metric, PLoS One, 10, 5 (2015) · doi:10.1371/journal.pone.0127428
[9] Luo, Y.; Xin, Y.; Joshi, R.; Celi, L. A.; Szolovits, P., Predicting ICU mortality risk by grouping temporal trends from a multivariate panel of physiologic measurements, Proceedings of the 13th AAAI Conference on Artificial Intelligence (AAAI-16)
[10] Kim, S.; Kim, W.; Park, R. W., A comparison of intensive care unit mortality prediction models through the use of data mining techniques, Healthcare Informatics Research, 17, 4, 232-243 (2011) · doi:10.4258/hir.2011.17.4.232
[11] Perotte, A.; Ranganath, R.; Hirsch, J. S.; Blei, D.; Elhadad, N., Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis, Journal of the American Medical Informatics Association, 22, 4, 872-880 (2015) · doi:10.1093/jamia/ocv024
[12] Breiman, L., Random forests, Machine Learning, 45, 1, 5-32 (2001) · Zbl 1007.68152 · doi:10.1023/a:1010933404324
[13] Caballero Barajas, K. L.; Akella, R., Dynamically modeling patient’s health state from electronic medical records: a time series approach, Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783289
[14] Mikolov, T.; Karafiát, M.; Burget, L.; Černocký, J.; Khudanpur, S., Recurrent neural network based language model, Proceedings of the Eleventh Annual Conference of the International Speech Communication Association
[15] Du, Y.; Wang, W.; Wang, L., Hierarchical recurrent neural network for skeleton based action recognition, Proceedings of the IEEE 2015 Conference on Computer Vision and Pattern Recognition · doi:10.1109/CVPR.2015.7298714
[16] Che, Z.; Purushotham, S.; Cho, K.; Sontag, D.; Liu, Y., Recurrent neural networks for multivariate time series with missing values, http://adsabs.harvard.edu/abs/2016arXiv160601865C
[17] Che, Z.; Purushotham, S.; Khemani, R.; Liu, Y., Interpretable deep models for ICU outcome prediction, Proceedings of the AMIA Annual Symposium
[18] Choi, E.; Bahadori, M. T.; Schuetz, A.; Stewart, W. F.; Sun, J., Doctor AI: predicting clinical events via recurrent neural networks, Proceedings of the Machine Learning for Healthcare
[19] Sak, H.; Senior, A.; Rao, K.; Beaufays, F., Fast and accurate recurrent neural network acoustic models for speech recognition, https://arxiv.org/abs/1507.06947
[20] Hochreiter, S.; Schmidhuber, J., Long short-term memory, Neural Computation, 9, 8, 1735-1780 (1997) · doi:10.1162/neco.1997.9.8.1735
[21] Tai, K. S.; Socher, R.; Manning, C. D., Improved semantic representations from tree-structured long short-term memory networks, Computer Science, 5, 36 (2015)
[22] Faust, O.; Hagiwara, Y.; Hong, T. J.; Lih, O. S.; Acharya, U. R., Deep learning for healthcare applications based on physiological signals: a review, Computer Methods and Programs in Biomedicine, 161, 1-13 (2018) · doi:10.1016/j.cmpb.2018.04.005
[23] Wang, H.; Yeung, D. Y., Towards Bayesian deep learning: a survey, https://arxiv.org/abs/1604.01662
[24] Sutskever, I.; Vinyals, O.; Le, Q. V., Sequence to sequence learning with neural networks, Proceedings of the Neural Information Processing Systems 2014
[25] Bahdanau, D.; Cho, K.; Bengio, Y., Neural machine translation by jointly learning to align and translate, https://ui.adsabs.harvard.edu/abs/2014arXiv1409.0473B
[26] Vinyals, O.; Toshev, A.; Bengio, S.; Erhan, D., Show and tell: a neural image caption generator, http://adsabs.harvard.edu/abs/2014arXiv1411.4555V
[27] Miotto, R.; Wang, F.; Wang, S.; Jiang, X.; Dudley, J. T., Deep learning for healthcare: review, opportunities and challenges, Briefings in Bioinformatics, 19, 6, 1236-1246 (2017) · doi:10.1093/bib/bbx044
[28] Lipton, Z. C.; Kale, D. C.; Elkan, C.; Wetzel, R., Learning to diagnose with LSTM recurrent neural networks, http://adsabs.harvard.edu/abs/2015arXiv151103677L
[29] Jo, Y.; Lee, L.; Palaskar, S., Combining LSTM and latent topic modeling for mortality prediction, http://adsabs.harvard.edu/abs/2017arXiv170902842J
[30] Harutyunyan, H.; Khachatrian, H.; Kale, D. C.; Galstyan, A., Multitask learning and benchmarking with clinical time series data, http://adsabs.harvard.edu/abs/2017arXiv170307771H
[31] Pham, T.; Tran, T.; Phung, D.; Venkatesh, S., DeepCare: a deep dynamic memory model for predictive medicine, Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining
[32] Awad, A.; Bader-El-Den, M.; McNicholas, J.; Briggs, J., Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach, International Journal of Medical Informatics, 108, 185-195 (2017) · doi:10.1016/j.ijmedinf.2017.10.002
[33] Ma, T.; Xiao, C.; Wang, F., Health-ATM: a deep architecture for multifaceted patient health record representation and risk prediction, Proceedings of the SIAM International Conference on Data Mining, 2018
[34] Dietterich, T. G., Ensemble methods in machine learning, Proceedings of the International Workshop on Multiple Classifier Systems
[35] Ho, T. K., The random subspace method for constructing decision forests, IEEE Transactions on Pattern Analysis & Machine Intelligence, 20, 8, 832-844 (1998) · doi:10.1109/34.709601
[36] Zhou, Z.-H., Ensemble Methods: Foundations and Algorithms (2012), Boca Raton, FL, USA: CRC Press, Boca Raton, FL, USA
[37] Breiman, L., Bagging predictors, Machine Learning, 24, 2, 123-140 (1996) · Zbl 0858.68080 · doi:10.1023/a:1018054314350
[38] Nanni, L.; Lumini, A.; Brahnam, S., A classifier ensemble approach for the missing feature problem, Artificial Intelligence in Medicine, 55, 1, 37-50 (2012) · doi:10.1016/j.artmed.2011.11.006
[39] Ozcift, A.; Gulten, A., Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms, Computer Methods and Programs in Biomedicine, 104, 3, 443-451 (2011) · doi:10.1016/j.cmpb.2011.03.018
[40] Özçift, A., Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis, Computers in Biology and Medicine, 41, 5, 265-271 (2011) · doi:10.1016/j.compbiomed.2011.03.001
[41] Chen, H.; Yuan, S.; Jiang, K., Wrapper approach for learning neural network ensemble by feature selection, Proceedings of the International Symposium on Neural Networks · Zbl 1082.68604
[42] Abreu, P. H.; Amaro, H.; Silva, D. C., Overall survival prediction for women breast cancer using ensemble methods and incomplete clinical data, XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013, 1366-1369 (2014), Cham, Switzerland: Springer, Cham, Switzerland
[43] Kim, H.; Kim, H.; Moon, H.; Ahn, H., A weight-adjusted voting algorithm for ensembles of classifiers, Journal of the Korean Statistical Society, 40, 4, 437-449 (2011) · Zbl 1296.62131 · doi:10.1016/j.jkss.2011.03.002
[44] Johnson, A. E. W.; Pollard, T. J.; Shen, L., MIMIC-III, a freely accessible critical care database, Scientific Data, 3, 1, 160035 (2016) · doi:10.1038/sdata.2016.35
[45] Bauer, E.; Kohavi, R., An empirical comparison of voting classification algorithms: bagging, boosting, and variants, Machine Learning, 36, 105-139 (1999)
[46] Breiman, L., Using iterated bagging to debias regressions, Machine Learning, 45, 3, 261-277 (2001) · Zbl 1052.68109
[47] Glorot, X.; Bengio, Y., Understanding the difficulty of training deep feedforward neural networks, Proceedings of the 13th International Conference on Artificial Intelligence and Statistics
[48] Twisk, J.; de Vente, W., Attrition in longitudinal studies: how to deal with missing data, Journal of Clinical Epidemiology, 55, 4, 329-337 (2002) · doi:10.1016/s0895-4356(01)00476-0
[49] Lagu, T.; Lindenauer, P. K.; Rothberg, M. B., Development and validation of a model that uses enhanced administrative data to predict mortality in patients with sepsis, Critical Care Medicine, 39, 11, 2425-2430 (2011) · doi:10.1097/ccm.0b013e31822572e3
[50] Vorwerk, C.; Loryman, B.; Coats, T. J., Prediction of mortality in adult emergency department patients with sepsis, Emergency Medicine Journal, 26, 4, 254-258 (2009) · doi:10.1136/emj.2007.053298
[51] Steinhart, B.; Thorpe, K. E.; Bayoumi, A. M.; Moe, G.; Januzzi, J. L.; Mazer, C. D., Improving the diagnosis of acute heart failure using a validated prediction model, Journal of the American College of Cardiology, 54, 16, 1515-1521 (2009) · doi:10.1016/j.jacc.2009.05.065
[52] Choi, E.; Schuetz, A.; Stewart, W. F.; Sun, J., Using recurrent neural network models for early detection of heart failure onset, Journal of the American Medical Informatics Association, 24, 361-370 (2016) · doi:10.1093/jamia/ocw112
[53] Fu, X.; Ren, Y.; Yang, G., A computational model for heart failure stratification, Proceedings of the 2011 Computing in Cardiology
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.