Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources

Meng Xia, Jonathan Wilson, Benjamin Goldstein, Ricardo Henao
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54156-54177, 2024.

Abstract

The use of machine learning models to predict clinical outcomes from (longitudinal) electronic health record (EHR) data is becoming increasingly popular due to advances in deep architectures, representation learning, and the growing availability of large EHR datasets. Existing models generally assume access to the same data sources during both training and inference stages. However, this assumption is often challenged by the fact that real-world clinical datasets originate from various data sources (with distinct sets of covariates), which though can be available for training (in a research or retrospective setting), are more realistically only partially available (a subset of such sets) for inference when deployed. So motivated, we introduce Contrastive Learning for clinical Outcome Prediction with Partial data Sources (CLOPPS), that trains encoders to capture information across different data sources and then leverages them to build classifiers restricting access to a single data source. This approach can be used with existing cross-sectional or longitudinal outcome classification models. We present experiments on two real-world datasets demonstrating that CLOPPS consistently outperforms strong baselines in several practical scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-xia24e, title = {Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources}, author = {Xia, Meng and Wilson, Jonathan and Goldstein, Benjamin and Henao, Ricardo}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {54156--54177}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/xia24e/xia24e.pdf}, url = {https://proceedings.mlr.press/v235/xia24e.html}, abstract = {The use of machine learning models to predict clinical outcomes from (longitudinal) electronic health record (EHR) data is becoming increasingly popular due to advances in deep architectures, representation learning, and the growing availability of large EHR datasets. Existing models generally assume access to the same data sources during both training and inference stages. However, this assumption is often challenged by the fact that real-world clinical datasets originate from various data sources (with distinct sets of covariates), which though can be available for training (in a research or retrospective setting), are more realistically only partially available (a subset of such sets) for inference when deployed. So motivated, we introduce Contrastive Learning for clinical Outcome Prediction with Partial data Sources (CLOPPS), that trains encoders to capture information across different data sources and then leverages them to build classifiers restricting access to a single data source. This approach can be used with existing cross-sectional or longitudinal outcome classification models. We present experiments on two real-world datasets demonstrating that CLOPPS consistently outperforms strong baselines in several practical scenarios.} }
Endnote
%0 Conference Paper %T Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources %A Meng Xia %A Jonathan Wilson %A Benjamin Goldstein %A Ricardo Henao %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-xia24e %I PMLR %P 54156--54177 %U https://proceedings.mlr.press/v235/xia24e.html %V 235 %X The use of machine learning models to predict clinical outcomes from (longitudinal) electronic health record (EHR) data is becoming increasingly popular due to advances in deep architectures, representation learning, and the growing availability of large EHR datasets. Existing models generally assume access to the same data sources during both training and inference stages. However, this assumption is often challenged by the fact that real-world clinical datasets originate from various data sources (with distinct sets of covariates), which though can be available for training (in a research or retrospective setting), are more realistically only partially available (a subset of such sets) for inference when deployed. So motivated, we introduce Contrastive Learning for clinical Outcome Prediction with Partial data Sources (CLOPPS), that trains encoders to capture information across different data sources and then leverages them to build classifiers restricting access to a single data source. This approach can be used with existing cross-sectional or longitudinal outcome classification models. We present experiments on two real-world datasets demonstrating that CLOPPS consistently outperforms strong baselines in several practical scenarios.
APA
Xia, M., Wilson, J., Goldstein, B. & Henao, R.. (2024). Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:54156-54177 Available from https://proceedings.mlr.press/v235/xia24e.html.

Related Material