# Target specification bias, counterfactual prediction, and algorithmic fairness in healthcare

arXiv: https://arxiv.org/abs/2308.02081 · HTML: https://mlsanity.com/paper/2308.02081/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 46 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [Active label cleaning for improved dataset quality under resource constraints](https://mlsanity.com/paper/2109.00574/) (2021)
- [Accurate Fairness: Improving Individual Fairness without Trading Accuracy](https://mlsanity.com/paper/2205.08704/) (2022)

## Built on by (most cited first, 6 of 6)

- [The Pursuit of Fairness in Artificial Intelligence Models: A Survey](https://mlsanity.com/paper/2403.17333/) (2024)
- [Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks](https://mlsanity.com/paper/2502.10526/) (2025)
- [Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings](https://mlsanity.com/paper/2505.22356/) (2025)
- [Critical Appraisal of Fairness Metrics in Clinical Predictive AI](https://mlsanity.com/paper/2506.17035/) (2025)
- [To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems](https://mlsanity.com/paper/2604.28053/) (2026)
- [Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems](https://mlsanity.com/paper/2505.19441/) (2025)

## Abstract (arXiv)

Bias in applications of machine learning (ML) to healthcare is usually attributed to unrepresentative or incomplete data, or to underlying health disparities. This article identifies a more pervasive source of bias that affects the clinical utility of ML-enabled prediction tools: target specification bias. Target specification bias arises when the operationalization of the target variable does not match its definition by decision makers. The mismatch is often subtle, and stems from the fact that decision makers are typically interested in predicting the outcomes of counterfactual, rather than actual, healthcare scenarios. Target specification bias persists independently of data limitations and health disparities. When left uncorrected, it gives rise to an overestimation of predictive accuracy, to inefficient utilization of medical resources, and to suboptimal decisions that can harm patients. Recent work in metrology - the science of measurement - suggests ways of counteracting target specification bias and avoiding its harmful consequences.