Machine learning models that utilize patient data across time (rather than just the most recent measurements) have increased performance for many risk stratification tasks in the intensive care unit. However, many of these models and their learned representations are complex and therefore difficult for clinicians to interpret, creating challenges for validation. Our work proposes a new procedure to learn summaries of clinical time-series that are both predictive and easily understood by humans. Specifically, our summaries consist of simple and intuitive functions of clinical data (e.g. falling mean arterial pressure). Our learned summaries outperform traditional interpretable model classes and achieve performance comparable to state-of-the-art deep learning models on an in-hospital mortality classification task.
@article{arxiv.2109.11043,
title = {Learning Predictive and Interpretable Timeseries Summaries from ICU Data},
author = {Nari Johnson and Sonali Parbhoo and Andrew Slavin Ross and Finale Doshi-Velez},
journal= {arXiv preprint arXiv:2109.11043},
year = {2021}
}