# Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning

arXiv: https://arxiv.org/abs/2208.01127 · HTML: https://mlsanity.com/paper/2208.01127/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 1 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Fair Classification with Group-Dependent Label Noise](https://mlsanity.com/paper/2011.00379/) (2020)
- [Confidence Scores Make Instance-dependent Label-noise Learning Possible](https://mlsanity.com/paper/2001.03772/) (2020)
- [Learning with Bounded Instance- and Label-dependent Label Noise](https://mlsanity.com/paper/1709.03768/) (2017)
- [The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric](https://mlsanity.com/paper/1902.05826/) (2019)
- [Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts](https://mlsanity.com/paper/2009.10132/) (2020)
- [Fast Threshold Tests for Detecting Discrimination](https://mlsanity.com/paper/1702.08536/) (2017)

## Built on by (most cited first, 7 of 7)

- [MOTOR: A Time-To-Event Foundation Model For Structured Medical Records](https://mlsanity.com/paper/2301.03150/) (2023)
- [Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods](https://mlsanity.com/paper/2305.11386/) (2023)
- [Time-to-Event Pretraining for 3D Medical Imaging](https://mlsanity.com/paper/2411.09361/) (2024)
- [Leveraging an Alignment Set in Tackling Instance-Dependent Label Noise](https://mlsanity.com/paper/2307.04868/) (2023)
- [From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions](https://mlsanity.com/paper/2406.18865/) (2024)
- [Leveraging Generative AI for Clinical Evidence Summarization Needs to Ensure Trustworthiness](https://mlsanity.com/paper/2311.11211/) (2023)
- [To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling](https://mlsanity.com/paper/2407.19114/) (2024)

## Abstract (arXiv)

As machine learning (ML) models gain traction in clinical applications, understanding the impact of clinician and societal biases on ML models is increasingly important. While biases can arise in the labels used for model training, the many sources from which these biases arise are not yet well-studied. In this paper, we highlight disparate censorship (i.e., differences in testing rates across patient groups) as a source of label bias that clinical ML models may amplify, potentially causing harm. Many patient risk-stratification models are trained using the results of clinician-ordered diagnostic and laboratory tests of labels. Patients without test results are often assigned a negative label, which assumes that untested patients do not experience the outcome. Since orders are affected by clinical and resource considerations, testing may not be uniform in patient populations, giving rise to disparate censorship. Disparate censorship in patients of equivalent risk leads to undertesting in certain groups, and in turn, more biased labels for such groups. Using such biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups. Here, we theoretically and empirically characterize conditions in which disparate censorship or undertesting affect model performance across subgroups. Our findings call attention to disparate censorship as a source of label bias in clinical ML models.