Learning of Cluster-based Feature Importance for Electronic Health Record Time-series

Henrique Aguiar, Mauro Santos, Peter Watkinson, Tingting Zhu
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:161-179, 2022.

Abstract

The recent availability of Electronic Health Records (EHR) has allowed for the development of algorithms predicting inpatient risk of deterioration and trajectory evolution. However, prediction of disease progression with EHR is challenging since these data are sparse, heterogeneous, multi-dimensional, and multi-modal time-series. As such, clustering is regularly used to identify similar groups within the patient cohort to improve prediction. Current models have shown some success in obtaining cluster representations of patient trajectories. However, they i) fail to obtain clinical interpretability for each cluster, and ii) struggle to learn meaningful cluster numbers in the context of imbalanced distribution of disease outcomes. We propose a supervised deep learning model to cluster EHR data based on the identification of clinically understandable phenotypes with regard to both outcome prediction and patient trajectory. We introduce novel loss functions to address the problems of class imbalance and cluster collapse, and furthermore propose a feature-time attention mechanism to identify cluster-based phenotype importance across time and feature dimensions. We tested our model in two datasets corresponding to distinct medical settings. Our model yielded added interpretability to cluster formation and outperformed benchmarks by at least 4% in relevant metrics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-aguiar22a, title = {Learning of Cluster-based Feature Importance for Electronic Health Record Time-series}, author = {Aguiar, Henrique and Santos, Mauro and Watkinson, Peter and Zhu, Tingting}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {161--179}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/aguiar22a/aguiar22a.pdf}, url = {https://proceedings.mlr.press/v162/aguiar22a.html}, abstract = {The recent availability of Electronic Health Records (EHR) has allowed for the development of algorithms predicting inpatient risk of deterioration and trajectory evolution. However, prediction of disease progression with EHR is challenging since these data are sparse, heterogeneous, multi-dimensional, and multi-modal time-series. As such, clustering is regularly used to identify similar groups within the patient cohort to improve prediction. Current models have shown some success in obtaining cluster representations of patient trajectories. However, they i) fail to obtain clinical interpretability for each cluster, and ii) struggle to learn meaningful cluster numbers in the context of imbalanced distribution of disease outcomes. We propose a supervised deep learning model to cluster EHR data based on the identification of clinically understandable phenotypes with regard to both outcome prediction and patient trajectory. We introduce novel loss functions to address the problems of class imbalance and cluster collapse, and furthermore propose a feature-time attention mechanism to identify cluster-based phenotype importance across time and feature dimensions. We tested our model in two datasets corresponding to distinct medical settings. Our model yielded added interpretability to cluster formation and outperformed benchmarks by at least 4% in relevant metrics.} }
Endnote
%0 Conference Paper %T Learning of Cluster-based Feature Importance for Electronic Health Record Time-series %A Henrique Aguiar %A Mauro Santos %A Peter Watkinson %A Tingting Zhu %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-aguiar22a %I PMLR %P 161--179 %U https://proceedings.mlr.press/v162/aguiar22a.html %V 162 %X The recent availability of Electronic Health Records (EHR) has allowed for the development of algorithms predicting inpatient risk of deterioration and trajectory evolution. However, prediction of disease progression with EHR is challenging since these data are sparse, heterogeneous, multi-dimensional, and multi-modal time-series. As such, clustering is regularly used to identify similar groups within the patient cohort to improve prediction. Current models have shown some success in obtaining cluster representations of patient trajectories. However, they i) fail to obtain clinical interpretability for each cluster, and ii) struggle to learn meaningful cluster numbers in the context of imbalanced distribution of disease outcomes. We propose a supervised deep learning model to cluster EHR data based on the identification of clinically understandable phenotypes with regard to both outcome prediction and patient trajectory. We introduce novel loss functions to address the problems of class imbalance and cluster collapse, and furthermore propose a feature-time attention mechanism to identify cluster-based phenotype importance across time and feature dimensions. We tested our model in two datasets corresponding to distinct medical settings. Our model yielded added interpretability to cluster formation and outperformed benchmarks by at least 4% in relevant metrics.
APA
Aguiar, H., Santos, M., Watkinson, P. & Zhu, T.. (2022). Learning of Cluster-based Feature Importance for Electronic Health Record Time-series. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:161-179 Available from https://proceedings.mlr.press/v162/aguiar22a.html.

Related Material