Qingxiong Tan
ABSTRACT
Accurate prediction of mortality risk is important for evaluating early treatments, detecting high-risk patients and improving healthcare outcomes. Predicting mortality risk from the irregular clinical time series data is challenging due to the varying time intervals in the consecutive records. Existing methods usually solve this issue by generating regular time series data from the original irregular data without considering the uncertainty in the generated data, caused by varying time intervals. In this paper, we propose a novel Uncertainty-Aware Convolutional Recurrent Neural Network (UA-CRNN), which incorporates the uncertainty information in the generated data to improve the mortality risk prediction performance. To handle the complex clinical time series data with sub-series of different frequencies, we propose to incorporate the uncertainty information into the sub-series level rather than the whole time series data. Specifically, we design a novel hierarchical uncertainty-aware decomposition layer (UADL) to adaptively decompose time series into different sub-series and assign them proper weights according to their reliabilities. Experimental results on two real-world clinical datasets demonstrate that the proposed UA-CRNN method significantly outperforms state-of-the-art methods in both short-term and long-term mortality risk predictions.
- Baytas, I. M., Xiao, C., Zhang, X., Wang, F., Jain, A. K., and Zhou, J. Patient subtyping via time-aware LSTM networks. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, 65--74, 2017.Google Scholar
Digital Library
- Liu, Z., and Hauskrecht, M. A Personalized Predictive Framework for Multivariate Clinical Time Series via Adaptive Model Selection. In Proceedings of the 26th ACM on Conference on Information and Knowledge Management, 1169--1177, 2017.Google ScholarDigital Library
- Elisha O and Dekel S. Wavelet decompositions of Random Forests: smoothness analysis, sparse approximation and applications. The Journal of Machine Learning Research, 17(1): 6952--6989, 2016.Google ScholarDigital Library
- Shickel, B., Tighe, P. J., Bihorac, A., and Rashidi, P. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE journal of biomedical and health informatics, 22(5), 1589--1604, 2018.Google Scholar
- Cai, X., Gao, J., Ngiam, K. Y., Ooi, B. C., Zhang, Y., and Yuan, X. Medical concept embedding with time-aware attention. arXiv preprint arXiv:1806.02873, 2018.Google Scholar
- Yip, T. F., Ma, A. J., Wong, V. S., Tse, Y. K., Chan, H. Y., Yuen, P. C., and Wong, G. H. Laboratory parameter-based machine learning model for excluding non?alcoholic fatty liver disease (NAFLD) in the general population. Alimentary pharmacology & therapeutics, 46(4), 447--456, 2017.Google Scholar
- Yadav, P., Steinbach, M., Kumar, V., and Simon, G. Mining electronic health records (EHRs): a survey. ACM Computing Surveys (CSUR), 50(6), 85, 2018.Google ScholarDigital Library
- Cao, Z., and Lin, C. T. Inherent fuzzy entropy for the improvement of EEG complexity evaluation. IEEE Transactions on Fuzzy Systems, 26(2), 1032--1035, 2018.Google ScholarCross Ref
- Naik, G. R., Selvan, S. E., and Nguyen, H. T. Single-channel EMG classification with ensemble-empirical-mode-decomposition-based ICA for diagnosing neuromuscular disorders. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24(7), 734--743, 2016.Google ScholarCross Ref
- Ren, P., Tang, S., Fang, F., Luo, L., Xu, L., Bringas-Vega, M. L., Yao, D., Kendrick, K. M. and Valdes-Sosa, P. A. Gait rhythm fluctuation analysis for neurodegenerative diseases by empirical mode decomposition. IEEE Transactions on Biomedical Engineering, 64(1), 52--60, 2017.Google ScholarCross Ref
- Wu, A., Roy, N. G., Keeley, S., and Pillow, J. W. Gaussian process based nonlinear latent structure discovery in multivariate spike train data. In Proceedings of Advances in neural information processing systems, 3496--3505, 2017.Google Scholar
- He, K., Zhang, X., Ren, S., and Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770--778, 2016.Google ScholarCross Ref
- Cho, K., Van Merriënboer, B., Bahdanau, D., and Bengio, Y. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259., 2014.Google Scholar
- Che, Z., Purushotham, S., Cho, K., Sontag, D., and Liu, Y. Recurrent neural networks for multivariate time series with missing values. Scientific reports, 8(1), 6085, 2018.Google Scholar
- Wu, M., Ghassemi, M., Feng, M., Celi, L. A., Szolovits, P., and Doshi-Velez, F. Understanding vasopressor intervention and weaning: Risk prediction in a public heterogeneous clinical time series database. Journal of the American Medical Informatics Association, 24(3), 488--495, 2017.Google ScholarCross Ref
- Sherman, E., Gurm, H., Balis, U., Owens, S., and Wiens, J. Leveraging Clinical Time-Series Data for Prediction: A Cautionary Tale. In Proceedings of American Medical Informatics Association Annual Symposium, 1571--1580, 2017.Google Scholar
- Liu, L., Shen, J., Zhang, M., Wang, Z., and Tang, J. Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018.Google Scholar
- Che, C., Xiao, C., Liang, J., Jin, B., Zho, J., and Wang, F. An RNN Architecture with Dynamic Temporal Matching for Personalized Predictions of Parkinson's Disease. In Proceedings of the 2017 Society for Industrial and Applied Mathematics International Conference on Data Mining, 198--206, 2017.Google ScholarCross Ref
- Harrison, E., Chang, M., Hao, Y., & Flower, A. Using machine learning to predict near-term mortality in cirrhosis patients hospitalized at the University of Virginia health system. In IEEE Systems and Information Engineering Design Symposium, 2018.Google ScholarCross Ref
- Zhang, X., Henao, R., Gan, Z., Li, Y., and Carin, L. Multi-Label Learning from Medical Plain Text with Convolutional Residual Models. arXiv preprint arXiv:1801.05062., 2018.Google Scholar
- Mei, J., Liu, M., Wang, Y. F., and Gao, H. Learning a mahalanobis distance-based dynamic time warping measure for multivariate time series classification. IEEE transactions on Cybernetics, 46(6), 1363--1374, 2016.Google ScholarCross Ref
- Wang, Z., Song, W., Liu, L., Zhang, F., Xue, J., Ye, Y. and Xu, M. Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization. arXiv preprint arXiv:1610.07258, 2016.Google Scholar
- Neil, D., Pfeiffer, M., and Liu, S. C. Phased lstm: Accelerating recurrent network training for long or event-based sequences. In Proceedings of Advances in neural information processing systems, 3882--3890, 2016.Google Scholar
- Li, S., Li, W., Cook, C., Zhu, C., and Gao, Y. Independently recurrent neural network (indrnn): Building A longer and deeper RNN. In Proceedings of the IEEE conference on computer vision and pattern recognition, 5457--5466, 2018.Google ScholarCross Ref
- Johnson, A. E., Pollard, T. J., Shen, L., Li-wei, H. L., Feng, M., Ghassemi, M., Moody B., and Mark, R. G. MIMIC-III, a freely accessible critical care database. Scientific data, 3, 160035, 2016.Google Scholar
- Xu, Y., Biswal, S., Deshpande, S. R., Maher, K. O., and Sun, J. RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, 2565--2573, 2018.Google ScholarDigital Library
- Tan, Q., Ma, A. J., Deng, H., Wong, V. W. S., Tse, Y. K., Yip, T. C. F., Wong, G. L., Ching, J. Y., Chan, F. K and Yuen, P. C. A Hybrid Residual Network and Long Short-Term Memory Method for Peptic Ulcer Bleeding Mortality Prediction. In Proceedings of American Medical Informatics Association Annual Symposium, 998--1007, 2018.Google Scholar
- Bhattacharyya, A., Fritz, M., and Schiele, B. Long-term on-board prediction of people in traffic scenes under uncertainty. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4194--4202, 2018.Google ScholarCross Ref
- Aizpurua, J. I., McArthur, S. D., Stewart, B. G., Lambert, B., Cross, J. G., and Catterson, V. M. Adaptive Power Transformer Lifetime Predictions Through Machine Learning and Uncertainty Modeling in Nuclear Power Plants. IEEE Transactions on Industrial Electronics, 66(6): 4726--4737, 2019.Google ScholarCross Ref
- Heo, J., Lee, H. B., Kim, S., Lee, J., Kim, K. J., Yang, E., and Hwang, S. J. Uncertainty-aware attention for reliable interpretation and prediction. In Proceedings of Advances in neural information processing systems, 909--918, 2018.Google Scholar
- Sakaridis C, Dai D, Van Gool L. Semantic Nighttime Image Segmentation with Synthetic Stylized Data, Gradual Adaptation and Uncertainty-Aware Evaluation. arXiv preprint arXiv:1901.05946, 2019.Google Scholar
- Sensoy, M., Kaplan, L., and Kandemir, M. Evidential deep learning to quantify classification uncertainty. In Proceedings of Advances in neural information processing systems, 3179--3189, 2018.Google Scholar
- Lütjens, B, Everett, M, How, J. P. Safe reinforcement learning with model uncertainty estimates. arXiv preprint arXiv:1810.08700, 2018.Google Scholar
- Ma, F., You, Q., Xiao, H., Chitta, R., Zhou, J., and Gao, J. Kame: Knowledge-based attention model for diagnosis prediction in healthcare. In Proceedings of the 27th ACM on Conference on Information and Knowledge Management, 743--752, 2018.Google ScholarDigital Library
- Hosseini, A., Chen, T., Wu, W., Sun, Y., and Sarrafzadeh, M. HeteroMed: Heterogeneous Information Network for Medical Diagnosis. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 763--772, 2018.Google ScholarDigital Library
- Pearce, T., Zaki, M., Brintrup, A., and Neel, A. Uncertainty in neural networks: Bayesian ensembling. arXiv preprint arXiv:1810.05546, 2018.Google Scholar
- Kendall, A., and Gal, Y. What uncertainties do we need in bayesian deep learning for computer vision? In Advances in neural information processing systems, 5574--5584. 2017.Google Scholar
- Ye, M., Lan, X., Wang, Z., and Yuen, P. C. Bi-directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification. IEEE Transactions on Information Forensics and Security, 2019.Google Scholar
- Ye, M., Zhang, X., Yuen, P. C., and Chang, S. F.. Unsupervised Embedding Learning via Invariant and Spreading Instance Feature. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6210--6219, 2019.Google ScholarCross Ref
- Yang, B., Ma, A. J., and Yuen, P. C. Learning domain-shared group-sparse representation for unsupervised domain adaptation. Pattern Recognition, 81, 615--632, 2018.Google ScholarCross Ref
- Yang, B., and Yuen, P. C. Cross-Domain Visual Representations via Unsupervised Graph Alignment. In Thirty-Three AAAI Conference on Artificial Intelligence, 5613--5620, 2019.Google ScholarCross Ref
- Ye, M., Li, J., Ma, A. J., Zheng, L., and Yuen, P. C. Dynamic graph co-matching for unsupervised video-based person re-identification. IEEE Transactions on Image Processing, 28(6), 2976--2990, 2019.Google ScholarCross Ref
- Yang, B., Ma, A. J., and Yuen, P. C. Domain-shared group-sparse dictionary learning for unsupervised domain adaptation. In Thirty-Second AAAI Conference on Artificial Intelligence, 7453--7460, 2018.Google Scholar
- Ye, M., Lan, X., and Yuen, P. C. Robust anchor embedding for unsupervised video person re-identification in the wild. In Proceedings of the European Conference on Computer Vision, 170--186, 2018.Google ScholarCross Ref
- Pang, M., Cheung, Y. M., Liu, R., Lou, J., and Lin, C. Toward efficient image representation: Sparse concept discriminant matrix factorization. IEEE Transactions on Circuits and Systems for Video Technology, 2018.Google Scholar
- Luo, Y., Cai, X., Zhang, Y., and Xu, J. Multivariate time series imputation with generative adversarial networks. In Advances in Neural Information Processing Systems, 1596--1607, 2018.Google Scholar
- Gal, Y., and Ghahramani, Z. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning, 1050--1059, 2016.Google Scholar
- UA-CRNN: Uncertainty-Aware Convolutional Recurrent Neural Network for Mortality Risk Prediction
Recommendations
Hybridized neural networks for non-invasive and continuous mortality risk assessment in neonates
AbstractPremature birth is the primary risk factor in neonatal deaths, with the majority of extremely premature babies cared for in neonatal intensive care units (NICUs). Mortality risk prediction in this setting can greatly improve patient ...
Highlights- A machine learning method for neonatal mortality risk assessment is proposed.
- ...
Recurrent convolutional neural network based multimodal disease risk prediction
AbstractWith the rapid growth of biomedical and healthcare data, machine learning methods are used in more and more work to predict disease risk. However, most works use single-mode data to predict disease risk and only few works use ...
Highlights- We propose a new MD-RCNN for disease risk prediction.
- We propose a feature ...
Diarrhoea outpatient visits prediction based on time series decomposition and multi-local predictor fusion
A EEMDAN-GRNN algorithm is proposed for diarrhoea outpatient visits prediction.Predictor based on decomposition-and-ensemble principle superior to single predictor.GRNN is a good candidate as predictor for diarrhoea outpatient visits prediction.EEMDAN is ...
Comments