Evaluating Model Performance in Medical Datasets Over Time

Helen Zhou, Yuwen Chen, Zachary Lipton
Proceedings of the Conference on Health, Inference, and Learning, PMLR 209:498-508, 2023.

Abstract

Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we % show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets % where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.

Cite this Paper

BibTeX
@InProceedings{pmlr-v209-zhou23a, title = {Evaluating Model Performance in Medical Datasets Over Time}, author = {Zhou, Helen and Chen, Yuwen and Lipton, Zachary}, booktitle = {Proceedings of the Conference on Health, Inference, and Learning}, pages = {498--508}, year = {2023}, editor = {Mortazavi, Bobak J. and Sarker, Tasmie and Beam, Andrew and Ho, Joyce C.}, volume = {209}, series = {Proceedings of Machine Learning Research}, month = {22 Jun--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v209/zhou23a/zhou23a.pdf}, url = {https://proceedings.mlr.press/v209/zhou23a.html}, abstract = {Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we % show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets % where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.} }
Endnote
%0 Conference Paper %T Evaluating Model Performance in Medical Datasets Over Time %A Helen Zhou %A Yuwen Chen %A Zachary Lipton %B Proceedings of the Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2023 %E Bobak J. Mortazavi %E Tasmie Sarker %E Andrew Beam %E Joyce C. Ho %F pmlr-v209-zhou23a %I PMLR %P 498--508 %U https://proceedings.mlr.press/v209/zhou23a.html %V 209 %X Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we % show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets % where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.
APA
Zhou, H., Chen, Y. & Lipton, Z.. (2023). Evaluating Model Performance in Medical Datasets Over Time. Proceedings of the Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 209:498-508 Available from https://proceedings.mlr.press/v209/zhou23a.html.

Related Material