iSurvive: An Interpretable, Event-time Prediction Model for mHealth

Walter H. Dempsey, Alexander Moreno, Christy K. Scott, Michael L. Dennis, David H. Gustafson, Susan A. Murphy, James M. Rehg
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:970-979, 2017.

Abstract

An important mobile health (mHealth) task is the use of multimodal data, such as sensor streams and self-report, to construct interpretable time-to-event predictions of, for example, lapse to alcohol or illicit drug use. Interpretability of the prediction model is important for acceptance and adoption by domain scientists, enabling model outputs and parameters to inform theory and guide intervention design. Temporal latent state models are therefore attractive, and so we adopt the continuous time hidden Markov model (CT-HMM) due to its ability to describe irregular arrival times of event data. Standard CT-HMMs, however, are not specialized for predicting the time to a future event, the key variable for mHealth interventions. Also, standard emission models lack a sufficiently rich structure to describe multimodal data and incorporate domain knowledge. We present iSurvive, an extension of classical survival analysis to a CT-HMM. We present a parameter learning method for GLM emissions and survival model fitting, and present promising results on both synthetic data and an mHealth drug use dataset.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-dempsey17a, title = {i{S}urvive: An Interpretable, Event-time Prediction Model for m{H}ealth}, author = {Walter H. Dempsey and Alexander Moreno and Christy K. Scott and Michael L. Dennis and David H. Gustafson and Susan A. Murphy and James M. Rehg}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {970--979}, 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/dempsey17a/dempsey17a.pdf}, url = {https://proceedings.mlr.press/v70/dempsey17a.html}, abstract = {An important mobile health (mHealth) task is the use of multimodal data, such as sensor streams and self-report, to construct interpretable time-to-event predictions of, for example, lapse to alcohol or illicit drug use. Interpretability of the prediction model is important for acceptance and adoption by domain scientists, enabling model outputs and parameters to inform theory and guide intervention design. Temporal latent state models are therefore attractive, and so we adopt the continuous time hidden Markov model (CT-HMM) due to its ability to describe irregular arrival times of event data. Standard CT-HMMs, however, are not specialized for predicting the time to a future event, the key variable for mHealth interventions. Also, standard emission models lack a sufficiently rich structure to describe multimodal data and incorporate domain knowledge. We present iSurvive, an extension of classical survival analysis to a CT-HMM. We present a parameter learning method for GLM emissions and survival model fitting, and present promising results on both synthetic data and an mHealth drug use dataset.} }
Endnote
%0 Conference Paper %T iSurvive: An Interpretable, Event-time Prediction Model for mHealth %A Walter H. Dempsey %A Alexander Moreno %A Christy K. Scott %A Michael L. Dennis %A David H. Gustafson %A Susan A. Murphy %A James M. Rehg %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-dempsey17a %I PMLR %P 970--979 %U https://proceedings.mlr.press/v70/dempsey17a.html %V 70 %X An important mobile health (mHealth) task is the use of multimodal data, such as sensor streams and self-report, to construct interpretable time-to-event predictions of, for example, lapse to alcohol or illicit drug use. Interpretability of the prediction model is important for acceptance and adoption by domain scientists, enabling model outputs and parameters to inform theory and guide intervention design. Temporal latent state models are therefore attractive, and so we adopt the continuous time hidden Markov model (CT-HMM) due to its ability to describe irregular arrival times of event data. Standard CT-HMMs, however, are not specialized for predicting the time to a future event, the key variable for mHealth interventions. Also, standard emission models lack a sufficiently rich structure to describe multimodal data and incorporate domain knowledge. We present iSurvive, an extension of classical survival analysis to a CT-HMM. We present a parameter learning method for GLM emissions and survival model fitting, and present promising results on both synthetic data and an mHealth drug use dataset.
APA
Dempsey, W.H., Moreno, A., Scott, C.K., Dennis, M.L., Gustafson, D.H., Murphy, S.A. & Rehg, J.M.. (2017). iSurvive: An Interpretable, Event-time Prediction Model for mHealth. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:970-979 Available from https://proceedings.mlr.press/v70/dempsey17a.html.

Related Material