ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

Madalina Fiterau, Suvrat Bhooshan, Jason Fries, Charles Bournhonesque, Jennifer Hicks, Eni Halilaj, Christopher Re, Scott Delp
Proceedings of the 2nd Machine Learning for Healthcare Conference, PMLR 68:59-74, 2017.

Abstract

In healthcare applications, temporal variables that encode movement, health status, and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients.

Cite this Paper

BibTeX
@InProceedings{pmlr-v68-fiterau17a, title = {ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information}, author = {Fiterau, Madalina and Bhooshan, Suvrat and Fries, Jason and Bournhonesque, Charles and Hicks, Jennifer and Halilaj, Eni and Re, Christopher and Delp, Scott}, booktitle = {Proceedings of the 2nd Machine Learning for Healthcare Conference}, pages = {59--74}, year = {2017}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {68}, series = {Proceedings of Machine Learning Research}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v68/fiterau17a/fiterau17a.pdf}, url = {https://proceedings.mlr.press/v68/fiterau17a.html}, abstract = {In healthcare applications, temporal variables that encode movement, health status, and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients.} }
Endnote
%0 Conference Paper %T ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information %A Madalina Fiterau %A Suvrat Bhooshan %A Jason Fries %A Charles Bournhonesque %A Jennifer Hicks %A Eni Halilaj %A Christopher Re %A Scott Delp %B Proceedings of the 2nd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2017 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v68-fiterau17a %I PMLR %P 59--74 %U https://proceedings.mlr.press/v68/fiterau17a.html %V 68 %X In healthcare applications, temporal variables that encode movement, health status, and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients.
APA
Fiterau, M., Bhooshan, S., Fries, J., Bournhonesque, C., Hicks, J., Halilaj, E., Re, C. & Delp, S.. (2017). ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information. Proceedings of the 2nd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 68:59-74 Available from https://proceedings.mlr.press/v68/fiterau17a.html.

Related Material