# BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark

arXiv: https://arxiv.org/abs/2107.08189 · HTML: https://mlsanity.com/paper/2107.08189/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 17 Jul 2021.

## Builds on (most cited first, 12 of 12)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data](https://mlsanity.com/paper/2011.03274/) (2020)
- [Analyzing the Role of Model Uncertainty for Electronic Health Records](https://mlsanity.com/paper/1906.03842/) (2019)
- [Bayesian Recurrent Neural Networks](https://mlsanity.com/paper/1704.02798/) (2017)
- [Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks](https://mlsanity.com/paper/1908.00690/) (2019)
- [Mondrian Forests: Efficient Online Random Forests](https://mlsanity.com/paper/1406.2673/) (2014)

## Built on by (most cited first, 4 of 4)

- [Matchmaker: Self-Improving Large Language Model Programs for Schema Matching](https://mlsanity.com/paper/2410.24105/) (2024)
- [Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Data](https://mlsanity.com/paper/2309.16220/) (2023)
- [Discovering Distribution Shifts using Latent Space Representations](https://mlsanity.com/paper/2202.02339/) (2022)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)

## Abstract (arXiv)

Machine learning has recently demonstrated impressive progress in predictive accuracy across a wide array of tasks. Most ML approaches focus on generalization performance on unseen data that are similar to the training data (In-Distribution, or IND). However, real world applications and deployments of ML rarely enjoy the comfort of encountering examples that are always IND. In such situations, most ML models commonly display erratic behavior on Out-of-Distribution (OOD) examples, such as assigning high confidence to wrong predictions, or vice-versa. Implications of such unusual model behavior are further exacerbated in the healthcare setting, where patient health can potentially be put at risk. It is crucial to study the behavior and robustness properties of models under distributional shift, understand common failure modes, and take mitigation steps before the model is deployed. Having a benchmark that shines light upon these aspects of a model is a first and necessary step in addressing the issue. Recent work and interest in increasing model robustness in OOD settings have focused more on image modality, while the Electronic Health Record (EHR) modality is still largely under-explored. We aim to bridge this gap by releasing BEDS-Bench, a benchmark for quantifying the behavior of ML models over EHR data under OOD settings. We use two open access, de-identified EHR datasets to construct several OOD data settings to run tests on, and measure relevant metrics that characterize crucial aspects of a model's OOD behavior. We evaluate several learning algorithms under BEDS-Bench and find that all of them show poor generalization performance under distributional shift in general. Our results highlight the need and the potential to improve robustness of EHR models under distributional shift, and BEDS-Bench provides one way to measure progress towards that goal.