A lightweight adaptation strategy is introduced that jointly balances ethnicity--gender--insurance representation without conditioning on mortality outcomes, allowing demographic representation balancing to be examined separately from outcome-conditioned or direct error-rate interventions.
Abstract
Fairness conclusions in clinical prediction can depend strongly on both the metrics reported and the demographic resolution at which performance is evaluated. We revisit these evaluation choices for ICU mortality prediction on MIMIC-IV, comparing predictive-utility and subgroup-error metrics across several fairness interventions. As a complementary case study, we introduce a lightweight adaptation strategy that jointly balances ethnicity--gender--insurance representation without conditioning on mortality outcomes, allowing demographic representation balancing to be examined separately from outcome-conditioned or direct error-rate interventions. We evaluate its behavior at both marginal and corresponding three-way intersectional subgroup levels, while accounting for the statistical support of finer-grained estimates. The results show that interventions can receive substantially different assessments across accuracy/AUROC, sensitivity, and false-positive rate, and that marginal demographic summaries can conceal heterogeneous error profiles within their constituent intersections, including among larger subgroups. These findings highlight the importance of evaluating fairness interventions at both complementary metric and subgroup resolutions, while accounting for the intervention target and the reliability of subgroup estimates.
Fairness is not a single concept and may be operationalized using a variety of definitions reflecting different ethical commitments, yet these are rarely compared systematically in healthcare AI. Fairness is often assessed using static metrics, even though clinical decisions are sequential and evolve over time. In chro...
Kaitlyn E. Wade, Alice C. W. Huang, Daniel J. Lizotte· Proceedings of the AAAI/ACM...· 0 citations
With the increased use of machine learning predictive
models, there is a growing need to ensure algorithmic
fairness and balance out inequality in predictive errors
across various application domains, such as health care and
income prediction. To make machine learning algorithms more
useful and applicable in everyday s...
David Oluwabukunmi Shodipo, B. Ogbuokiri· Proceedings of the AAAI/ACM...· 0 citations
Fairness assessment in algorithmic decisions that affect individuals, such as credit scoring, often relies on parity measures calculated at the aggregate group level. Such measures may not reveal which individuals experience unfairness or which explanatory factors contribute to it. In this paper, we propose a rank-base...
OBJECTIVE
Fairness evaluations for healthcare prediction models often use nationally representative survey data, but current practice rarely accounts for complex sampling when estimating uncertainty. We develop a design-based framework for fairness monitoring and use it to test temporal trends in healthcare expenditure...
George Sun, Long-Lin Sun, Yi-Hui Zhou· Journal of Biomedical Inform...· 0 citations
A collaborative learning framework that treats demographic subgroups as clients and aggregates their model parameters using strategies that encode different assumptions about group contribution, and a novel difficulty decomposition framework, derived from the localized conformal classifier's calibration scores, disting...
The Routing Disparity metric and multi-level debiasing framework introduced here generalize to MoE systems operating on demographically heterogeneous populations, providing both an audit tool and an architectural intervention for a bias mechanism that existing fairness methods leave unaddressed.
Xiaoyang Wang, Christopher C. Yang· IEEE journal of biomedical a...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026