Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis

Ahmed M. Alaa, Scott Hu, Mihaela Schaar
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:60-69, 2017.

Abstract

Critically ill patients in regular wards are vulnerable to unanticipated adverse events which require prompt transfer to the intensive care unit (ICU). To allow for accurate prognosis of deteriorating patients, we develop a novel continuous-time probabilistic model for a monitored patient’s temporal sequence of physiological data. Our model captures “informatively sampled” patient episodes: the clinicians’ decisions on when to observe a hospitalized patient’s vital signs and lab tests over time are represented by a marked Hawkes process, with intensity parameters that are modulated by the patient’s latent clinical states, and with observable physiological data (mark process) modeled as a switching multi-task Gaussian process. In addition, our model captures “informatively censored” patient episodes by representing the patient’s latent clinical states as an absorbing semi-Markov jump process. The model parameters are learned from offline patient episodes in the electronic health records via an EM-based algorithm. Experiments conducted on a cohort of patients admitted to a major medical center over a 3-year period show that risk prognosis based on our model significantly outperforms the currently deployed medical risk scores and other baseline machine learning algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-alaa17a, title = {Learning from Clinical Judgments: Semi-{M}arkov-Modulated Marked {H}awkes Processes for Risk Prognosis}, author = {Ahmed M. Alaa and Scott Hu and Mihaela van der Schaar}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {60--69}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/alaa17a/alaa17a.pdf}, url = {https://proceedings.mlr.press/v70/alaa17a.html}, abstract = {Critically ill patients in regular wards are vulnerable to unanticipated adverse events which require prompt transfer to the intensive care unit (ICU). To allow for accurate prognosis of deteriorating patients, we develop a novel continuous-time probabilistic model for a monitored patient’s temporal sequence of physiological data. Our model captures “informatively sampled” patient episodes: the clinicians’ decisions on when to observe a hospitalized patient’s vital signs and lab tests over time are represented by a marked Hawkes process, with intensity parameters that are modulated by the patient’s latent clinical states, and with observable physiological data (mark process) modeled as a switching multi-task Gaussian process. In addition, our model captures “informatively censored” patient episodes by representing the patient’s latent clinical states as an absorbing semi-Markov jump process. The model parameters are learned from offline patient episodes in the electronic health records via an EM-based algorithm. Experiments conducted on a cohort of patients admitted to a major medical center over a 3-year period show that risk prognosis based on our model significantly outperforms the currently deployed medical risk scores and other baseline machine learning algorithms.} }
Endnote
%0 Conference Paper %T Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis %A Ahmed M. Alaa %A Scott Hu %A Mihaela Schaar %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-alaa17a %I PMLR %P 60--69 %U https://proceedings.mlr.press/v70/alaa17a.html %V 70 %X Critically ill patients in regular wards are vulnerable to unanticipated adverse events which require prompt transfer to the intensive care unit (ICU). To allow for accurate prognosis of deteriorating patients, we develop a novel continuous-time probabilistic model for a monitored patient’s temporal sequence of physiological data. Our model captures “informatively sampled” patient episodes: the clinicians’ decisions on when to observe a hospitalized patient’s vital signs and lab tests over time are represented by a marked Hawkes process, with intensity parameters that are modulated by the patient’s latent clinical states, and with observable physiological data (mark process) modeled as a switching multi-task Gaussian process. In addition, our model captures “informatively censored” patient episodes by representing the patient’s latent clinical states as an absorbing semi-Markov jump process. The model parameters are learned from offline patient episodes in the electronic health records via an EM-based algorithm. Experiments conducted on a cohort of patients admitted to a major medical center over a 3-year period show that risk prognosis based on our model significantly outperforms the currently deployed medical risk scores and other baseline machine learning algorithms.
APA
Alaa, A.M., Hu, S. & Schaar, M.. (2017). Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:60-69 Available from https://proceedings.mlr.press/v70/alaa17a.html.

Related Material