T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression

Yuchao Qin, Mihaela van der Schaar, Changhee Lee
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:3466-3492, 2023.

Abstract

Clustering time-series data in healthcare is crucial for clinical phenotyping to understand patients’ disease progression patterns and to design treatment guidelines tailored to homogeneous patient subgroups. While rich temporal dynamics enable the discovery of potential clusters beyond static correlations, two major challenges remain outstanding: i) discovery of predictive patterns from many potential temporal correlations in the multi-variate time-series data and ii) association of individual temporal patterns to the target label distribution that best characterizes the underlying clinical progression. To address such challenges, we develop a novel temporal clustering method, T-Phenotype, to discover phenotypes of predictive temporal patterns from labeled time-series data. We introduce an efficient representation learning approach in frequency domain that can encode variable-length, irregularly-sampled time-series into a unified representation space, which is then applied to identify various temporal patterns that potentially contribute to the target label using a new notion of path-based similarity. Throughout the experiments on synthetic and real-world datasets, we show that T-Phenotype achieves the best phenotype discovery performance over all the evaluated baselines. We further demonstrate the utility of T-Phenotype by uncovering clinically meaningful patient subgroups characterized by unique temporal patterns.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-qin23b, title = {T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression}, author = {Qin, Yuchao and van der Schaar, Mihaela and Lee, Changhee}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {3466--3492}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/qin23b/qin23b.pdf}, url = {https://proceedings.mlr.press/v206/qin23b.html}, abstract = {Clustering time-series data in healthcare is crucial for clinical phenotyping to understand patients’ disease progression patterns and to design treatment guidelines tailored to homogeneous patient subgroups. While rich temporal dynamics enable the discovery of potential clusters beyond static correlations, two major challenges remain outstanding: i) discovery of predictive patterns from many potential temporal correlations in the multi-variate time-series data and ii) association of individual temporal patterns to the target label distribution that best characterizes the underlying clinical progression. To address such challenges, we develop a novel temporal clustering method, T-Phenotype, to discover phenotypes of predictive temporal patterns from labeled time-series data. We introduce an efficient representation learning approach in frequency domain that can encode variable-length, irregularly-sampled time-series into a unified representation space, which is then applied to identify various temporal patterns that potentially contribute to the target label using a new notion of path-based similarity. Throughout the experiments on synthetic and real-world datasets, we show that T-Phenotype achieves the best phenotype discovery performance over all the evaluated baselines. We further demonstrate the utility of T-Phenotype by uncovering clinically meaningful patient subgroups characterized by unique temporal patterns.} }
Endnote
%0 Conference Paper %T T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression %A Yuchao Qin %A Mihaela van der Schaar %A Changhee Lee %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-qin23b %I PMLR %P 3466--3492 %U https://proceedings.mlr.press/v206/qin23b.html %V 206 %X Clustering time-series data in healthcare is crucial for clinical phenotyping to understand patients’ disease progression patterns and to design treatment guidelines tailored to homogeneous patient subgroups. While rich temporal dynamics enable the discovery of potential clusters beyond static correlations, two major challenges remain outstanding: i) discovery of predictive patterns from many potential temporal correlations in the multi-variate time-series data and ii) association of individual temporal patterns to the target label distribution that best characterizes the underlying clinical progression. To address such challenges, we develop a novel temporal clustering method, T-Phenotype, to discover phenotypes of predictive temporal patterns from labeled time-series data. We introduce an efficient representation learning approach in frequency domain that can encode variable-length, irregularly-sampled time-series into a unified representation space, which is then applied to identify various temporal patterns that potentially contribute to the target label using a new notion of path-based similarity. Throughout the experiments on synthetic and real-world datasets, we show that T-Phenotype achieves the best phenotype discovery performance over all the evaluated baselines. We further demonstrate the utility of T-Phenotype by uncovering clinically meaningful patient subgroups characterized by unique temporal patterns.
APA
Qin, Y., van der Schaar, M. & Lee, C.. (2023). T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:3466-3492 Available from https://proceedings.mlr.press/v206/qin23b.html.

Related Material