Skip to main content Accessibility help
×
Hostname: page-component-7c8c6479df-nwzlb Total loading time: 0 Render date: 2024-03-19T03:50:35.270Z Has data issue: false hasContentIssue false

Bayesian nonparametric learning of switching dynamics in cohort physiological time series: application in critical care patient monitoring

from Part II - State space methods for clinical data

Published online by Cambridge University Press:  05 October 2015

L. H. Lehman
Affiliation:
Massachusetts Institute of Technology
M. J. Johnson
Affiliation:
Massachusetts Institute of Technology
S. Nemati
Affiliation:
Harvard University
R. P. Adams
Affiliation:
Harvard University
R. G. Mark
Affiliation:
Massachusetts Institute of Technology
Zhe Chen
Affiliation:
New York University
Get access

Summary

Introduction

The time series of vital signs, such as heart rate (HR) and blood pressure (BP), can exhibit complex dynamic behaviors as a result of internally and externally induced changes in the state of the underlying control systems (Peng et al. 1995; Ivanov et al. 1999; Costa et al. 2002). For instance, time series of BP can exhibit oscillations on the order of seconds (e.g., due to the variations in sympathovagal balance), to minutes (e.g., as a consequence of fever, blood loss, or behavioral factors), to hours (e.g., due to humoral variations, sleep-wake cycle, or circadian effects) (Mancia 2012; Parati et al. 2013). A question of interest is whether “similar” dynamical patterns can be automatically identified across a heterogeneous patient cohort, and be used for prognosis of patients' health and progress.

In this work, we present a Bayesian nonparametric switching Markov processes framework with conditionally linear dynamics to learn phenotypic dynamic behaviors from vital sign time series of a patient cohort, and use the learned dynamics to characterize the changing physiological states of patients for critical-care bed-side monitoring (Lehman et al. 2012, 2013, 2014a; Nemati 2012). We assume that although the underlying dynamical system may be nonlinear and nonstationary and the stochastic noise components can be non-Gaussian, the dynamics can be approximated by a collection of linear dynamical systems (Nemati 2012; Nemati et al. 2012). Each such linear “dynamic” (or mode) is a time-dependent rule that describes how the future state of the system evolves from its current state, centered around a given system equilibrium point. Therefore, an ideal algorithm would be able to identify time series segments that follow a “similar” dynamic, and would switch to a different mode upon a change in the state of the underlying system.

We explore several variants of the Bayesian nonparametric approach to discovery of shared dynamics among patients via switching Markov processes: hierarchical Dirichlet process (HDP) autoregressive hidden Markov model (HDP-AR-HMM) (Teh et al. 2006; Fox et al. 2008), an explicit-duration HDP-based hidden semi-Markov model (HDP-AR-HSMM) (Johnson & Willsky 2013a), and the beta process autoregressive HMM (BP-AR-HMM) (Fox 2009; Fox et al. 2009, 2014).

Type
Chapter
Information
Publisher: Cambridge University Press
Print publication year: 2015

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Angelino, E., Kohler, E., Waterland, A., Seltzer, M. & Adams, R. P. (2014). Accelerating MCMC via parallel predictive prefetching. In Proceedings of 30th Conference on Uncertainty in Artificial Intelligence.Google Scholar
Avent, R. K. & Charlton, J. D. (1990). A critical review of trend-detection methodologies for biomedical monitoring systems. Critical Reviews in Biomedical Engineering 17(6), 621–59.Google Scholar
Bardenet, R., Doucet, A. & Holmes, C. (2014). Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach. In Proceedings of the 31st International Conference on Machine Learning, pp. 405–413.Google Scholar
Benjamini, Y. & Hochberg, Y. (1995). Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society 57(1), 289–300.Google Scholar
Bernardo, J. M. & Smith, A. F. (2009). Bayesian Theory, New York: Wiley.
Bishop, C. M. (2006). Pattern Recognition and Machine Learning, New York: Springer.
Blount, M., Ebling, M. R., Eklund, J. M., James, A. G., McGregor, C., Percival, N., Smith, K. P. & Sow, D. (2010). Real-time analysis for intensive care: development and deployment of the artemis analytic system. IEEE Engineering in Medicine and Biology Magazine 29(2), 110–118.Google Scholar
Costa, M., Goldberger, A. L. & Peng, C. K. (2002). Multiscale entropy analysis of complex physiologic time series. Physical Review Letters 89(6), 068102.Google Scholar
Fox, E. (2009). Bayesian nonparametric learning of complex dynamical phenomena. PhD thesis, MIT.
Fox, E. B., Sudderth, E. B., Jordan, M. I. & Willsky, A. S. (2008). An HDP-HMM for systems with state persistence. In Proceedings of the International Conference on Machine Learning.Google Scholar
Fox, E. B., Sudderth, E., Jordan, M. & Willsky, A. (2010). Bayesian nonparametric learning of Markov switching processes. IEEE Signal Processing Magazine 27, 43–54.Google Scholar
Fox, E., Hughes, E., Sudderth, E. & Jordan, M. (2014). Joint modeling of multiple related time series via the beta process with application to motion capture segmentation. Annals of Applied Statistics 8, 1281–1313.Google Scholar
Fox, E., Sudderth, E., Jordan, M. & Willsky, A. (2009). Sharing features among dynamical systems with beta processes. Advances in Neural Information Processing Systems 22 pp. 549–557.Google Scholar
Gelman, A., Carlin, J.B., Stern, H. S., Dunson, D. B., Vehtari, A. & Rubin, D. B. (2013). Bayesian Data Analysis, 3rd edn, CRC press.
Ghahramani, Z., Griffiths, T. L. & Sollich, P. (2006). Bayesian nonparametric latent feature models. In Proceedings of ISBA 8th World Meeting on Bayesian Statistics.Google Scholar
Heldt, T. (2004). Computational Models of Cardiovascular Response to Orthostatic Stress. PhD thesis, MIT.
Heldt, T., Oefinger, M. B., Hoshiyama, M. & Mark, R. G. (2003). Circulatory response to passive and active changes in posture. Proceedings of the Computers in Cardiology 30, 263–266.Google Scholar
Hoffman, M. D., Blei, D. M., Wang, C. & Paisley, J. (2013). Stochastic variational inference. Journal of Machine Learning Research 14(1), 1303–1347.Google Scholar
Ishwaran, H. & Zarepour, M. (2002). Exact and approximate sum representations for the Dirichlet process. Canadian Journal of Statistics 30(2), 269–283.Google Scholar
Ivanov, P. C., Amaral, L. A., Goldberger, A. L., Havlin, S., Rosenblum, M. G., Struzik, Z. R. & Stanley, H. E. (1999). Multifractality in human heartbeat dynamics. Nature 399, 461–465.Google Scholar
Johnson, M. & Willsky, A. (2013a). Bayesian nonparametric hidden semi-markov models. Journal of Machine Learning Research 14, 673–701.Google Scholar
Johnson, M. & Willsky, A. (2014). Stochastic variational inference for Bayesian time series models. In Proceedings of the 31st International Conference on Machine Learning, pp. 1854–1862.Google Scholar
Johnson, M. J. (2014). Bayesian time series models and scalable inference. PhD thesis, MIT.
Johnson, M. J. & Willsky, A. S. (2013b). Bayesian nonparametric hidden semi-markov models. Journal of Machine Learning Research 14(1), 673–701.Google Scholar
Knaus, W. A., Wagner, D. P., Draper, E. A., Zimmerman, J. E., Bergner, M., Bastos, P. G., Sirio, C. A., Murphy, D. J., Lotring, T., Damiano, A. & Harrell, F. (1991). The APACHE III prognostic system. Chest 100(6), 1619–1636.Google Scholar
Korattikara, A., Chen, Y. & Welling, M. (2014). Austerity in MCMC land: cutting the Metropolis- Hastings budget. In Proceedings of The 31st International Conference on Machine Learning, pp. 181–189.Google Scholar
Le Gall, J. R., Lemeshow, S. & Saulnier, F. (1993). A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study. Journal of the American Medical Association 270, 2957–2963.Google Scholar
Le Gall, J. R., Loirat, P., Alperovitch, A., Glaser, P., Granthil, C., Mathieu, D., Mercier, P., Thomas, R. & Villers, D. (1984). A simplified acute physiology score for ICU patients. Critical Care Medicine 12(11), 975–977.Google Scholar
Lehman, L. H., Adams, R. P., Mayaud, L., Moody, G.B., Malhotra, A., Mark, R.G. & Nemati, S. (2014a). A physiological time series dynamics-based approach to patient monitoring and outcome prediction. IEEE Journal of Biomedical and Health Informatics 18, in press.Google Scholar
Lehman, L. H., Nemati, S., Adams, R. P. & Mark, R.G. (2012). Discovering shared dynamics in physiological signals: Application to patient monitoring in ICU. In Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 5939–5942.Google Scholar
Lehman, L. H., Nemati, S., Adams, R. P., Moody, G., Malhotra, A. & Mark, R. G. (2013). Tracking progression of patient state of health in critical care using inferred shared dynamics in physiological time series. In Proceedings of IEEE Engineering in Medicine and Biology Society, pp. 7072–7075.Google Scholar
Lehman, L. H., Nemati, S., Moody, G. B., Heldt, T. & Mark, R. (2014b). Uncovering clinical significance of vital sign dynamics in critical care. In Proceedings of the Computing in Cardiology.Google Scholar
Lehman, L. H., Saeed, M., Moody, G. & Mark, R. (2008). Similarity-based searching in multiparameter time series databases. In Proceedings of the Computers in Cardiology, pp. 653–656.Google Scholar
Maclaurin, D. & Adams, R. P. (2014). Firefly Monte Carlo: exact MCMC with subsets of data. In Proceedings of 30th Conference on Uncertainty in Artificial Intelligence.Google Scholar
Mancia, G. (2012). Short-and long-term blood pressure variability present and future. Hypertension 60(2), 512–517.Google Scholar
Mayaud, L., Lai, P. S., Clifford, G.D., Tarassenko, L., Celi, L. A. & Annane, D. (2013). Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension. Critical Care Medicine 41(4), 954–962.Google Scholar
Moorman, J. R., Delos, J. B., Flower, A. A., Cao, H., Kovatchev, B. P., Richman, J. S. & Lake, D. E. (2011). Cardiovascular oscillations at the bedside: early diagnosis of neonatal sepsis using heart rate characteristics monitoring. Physiological Measurements 32(11), 1821–1832.Google Scholar
Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective, Cambidge, MA: MIT Press.
Nemati, S. (2012). Identifying evolving multivariate dynamics in individual and cohort timeseries, with application to physiological control systems. PhD thesis, MIT.
Nemati, S., Edwards, B. A., Sands, S. A., Berger, P. J., Wellman, A., Verghese, G. C., Malhotra, A. & Butler, J. P. (2011). Model-based characterization of ventilatory stability using spontaneous breathing. Journal of Applied Physiology 111(1), 55–67.Google Scholar
Nemati, S., Lehman, L. H., Adams, R. P. & Malhotra, A. (2012). Discovering shared cardiovascular dynamics within a patient cohort. In Proceedings of IEEE Engineering in Medicine and Biology Society, pp. 6526–6529.Google Scholar
Nishihara, R., Murray, I. & Adams, R. P. (2014). Parallel MCMC with generalized elliptical slice sampling. Journal of Machine Learning Research 15, 2087–2112.Google Scholar
Parati, G., Ochoa, J. E., Lombardi, C. & Bilo, G. (2013). Assessment and management of bloodpressure variability. Nature Reviews Cardiology 10, 143–155.Google Scholar
Peng, C. K., Havlin, S., Stanley, H. E. & Goldberger, A. L. (1995). Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos 5, 82–87.Google Scholar
Quinn, J. A., Williams, C. K. & McIntosh, N. (2009). Factorial switching linear dynamical systems applied to physiological condition monitoring. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(9), 1537–1551.Google Scholar
Riordan, W. P., Norris, P. R., Jenkins, J. M. & Morris Jr, J. A. (2009). Early loss of heart rate complexity predicts mortality regardless of mechanism, anatomic location, or severity of injury in 2178 trauma patients. Journal of Surgical Research 156(2), 283–289.Google Scholar
Robert, C. P. & Casella, G. (2004). Monte Carlo Statistical Methods, New York: Springer.
Saeed, M. & Mark, R. (2006). A novel method for the efficient retrieval of similar multiparameter physiologic time series using wavelet-based symbolic representations. In Proceedings of the AMIA Annual Symposium, pp. 679–683.Google Scholar
Saeed, M., Villarroel, M., Reisner, A. T., Clifford, G., Lehman, L. H., Moody, G., Heldt, T., Kyaw, T. H., Moody, B. & Mark, R.G. (2011). Multiparameter intelligent monitoring in intensive care (MIMIC II): a public-access intensive care unit database. Critical Care Medicine 39(5), 952–960.Google Scholar
Saria, S., Rajani, A. K., Gould, J., Koller, D. & Penn, A. (2010). Integration of early physiological responses predicts later illness severity in preterm infants. Science Translational Medicine 2, 48–65.Google Scholar
Sethuraman, J. (1994). A constructive definition of Dirichlet priors. Statistica Sinica 4, 639–650.Google Scholar
Teh, Y., Jordan, M., Beal, M. & Blei, D. (2006). Hierarchical Dirichlet processes. Journal of American Statistical Association 101, 1566–1581.Google Scholar
Van Gael, J., Saatci, Y., Teh, Y. W. & Ghahramani, Z. (2008). Beam sampling for the infinite hidden Markov model. In Proceedings of the 25th International Conference on Machine Learning, pp. 1088–1095.Google Scholar
Wainwright, M. J. & Jordan, M. I. (2008). Graphical models, exponential families, and variational inference. Foundations and Trends & ® in Machine Learning 1(1-2), 1–305.Google Scholar
Wiens, J., Horvitz, E. & Guttag, J.V. (2012). Patient risk stratification for hospital-associated C. diff as a time-series classification task. In Advances in Neural Information Processing Systems 25, pp. 476–484.Google Scholar
Zimmerman, J. E., Kramer, A. A., McNair, D. S. & Malila, F. M. (2006). Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today's critically ill patients. Critical Care Medicine 34(5), 1297–1310.Google Scholar

Save book to Kindle

To save this book to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Available formats
×

Save book to Dropbox

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Dropbox.

Available formats
×

Save book to Google Drive

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Google Drive.

Available formats
×