# Considerations for Distribution Shift Robustness of Diagnostic Models in Healthcare

arXiv: https://arxiv.org/abs/2410.19575 · HTML: https://mlsanity.com/paper/2410.19575/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [Invariant Causal Prediction for Nonlinear Models](https://mlsanity.com/paper/1706.08576/) (2017)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Anchor regression: heterogeneous data meets causality](https://mlsanity.com/paper/1801.06229/) (2018)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [Stabilizing Variable Selection and Regression](https://mlsanity.com/paper/1911.01850/) (2019)
- [Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations](https://mlsanity.com/paper/2205.03931/) (2022)
- [A Unifying Causal Framework for Analyzing Dataset Shift-stable Learning Algorithms](https://mlsanity.com/paper/1905.11374/) (2019)
- [When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction](https://mlsanity.com/paper/2206.02058/) (2022)

## Abstract (arXiv)

We consider robustness to distribution shifts in the context of diagnostic models in healthcare, where the prediction target Y, e.g., the presence of a disease, is causally upstream of the observations X, e.g., a biomarker. Distribution shifts may occur, for instance, when the training data is collected in a domain with patients having particular demographic characteristics while the model is deployed on patients from a different demographic group. In the domain of applied ML for health, it is common to predict Y from X without considering further information about the patient. However, beyond the direct influence of the disease Y on biomarker X, a predictive model may learn to exploit confounding dependencies (or shortcuts) between X and Y that are unstable under certain distribution shifts. In this work, we highlight a data generating mechanism common to healthcare settings and discuss how recent theoretical results from the causality literature can be applied to build robust predictive models. We theoretically show why ignoring covariates as well as common invariant learning approaches will in general not yield robust predictors in the studied setting, while including certain covariates into the prediction model will. In an extensive simulation study, we showcase the robustness (or lack thereof) of different predictors under various data generating processes. Lastly, we analyze the performance of the different approaches using the PTB-XL dataset, a public dataset of annotated ECG recordings.