Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
This addresses a critical issue for healthcare AI by improving model generalizability over time, though it is incremental as it builds on existing methods with a specific adaptation.
The paper tackles the problem of machine learning models in healthcare degrading over time due to changing hospital practices, showing that standard models lose 0.3 AUC for mortality prediction and 0.15 AUC for length-of-stay over 10 years, while aggregated features mitigate this deterioration.
Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates, ignoring the fact that data were generated under hospital operation practices that change over time. These changing practices induce definitive changes in observed data which confound evaluations which do not account for dates and limit the generalisability of date-agnostic models. In this work, we establish the magnitude of this problem on MIMIC, a public hospital dataset, and showcase a simple solution. We augment MIMIC with the year in which care was provided and show that a model trained using standard feature representations will significantly degrade in quality over time. We find a deterioration of 0.3 AUC when evaluating mortality prediction on data from 10 years later. We find a similar deterioration of 0.15 AUC for length-of-stay. In contrast, we demonstrate that clinically-oriented aggregates of raw features significantly mitigate future deterioration. Our suggested aggregated representations, when retrained yearly, have prediction quality comparable to year-agnostic models.