Original Research

Fairness Is Not a Setting: How Threshold Choices Reshape Equity in a Sepsis Alert Algorithm

Dr. Camille Dubois, Rosa Calderón, MPH (Valle Verde Community Health Network), Dr. Gregory Mbeki (Trent Valley University)

Volume 5, Number 3 · June 2026 · pp. 126–138 · doi:10.59821/jhds.2026.0302

Received January 9, 2026 · Accepted April 22, 2026 · Published June 15, 2026

Abstract

The same sepsis model can be fair or unfair depending on a single deployment decision about where to set its alert threshold. We show how that one choice shifted false-alarm burdens between patient groups and offer a framework for making the tradeoff deliberately rather than by accident.

clinical risk modelsmodel monitoringhealth equitymachine learning

Introduction

Health systems increasingly depend on predictive models embedded in electronic health records. Yet most published evaluations describe performance at a single moment in time, leaving practitioners with little evidence about how these tools behave months or years after go-live.

Methods

We conducted a retrospective cohort study across participating sites between 2023 and 2025. Performance was assessed monthly using discrimination (AUROC), calibration slope, and subgroup-specific false positive rates. The study was approved by each site's institutional review board with a waiver of consent.

Results

Of the models studied, a substantial share showed statistically significant degradation, most commonly in calibration rather than discrimination. Degradation was concentrated in periods following documentation template changes and shifts in patient mix.

Discussion

Our findings suggest that routine, low-cost monitoring can detect meaningful performance changes well before they surface through clinician complaints. We recommend health systems assign a named owner to every deployed model.

Figure 1. Median AUROC by quarter after deployment, with recovery following recalibration in Q7.

References

  1. Finlayson SG, Subbaswamy A, Singh K, et al. The clinician and dataset shift in artificial intelligence. N Engl J Med. 2021;385(3):283-286.
  2. Davis SE, Lasko TA, Chen G, et al. Calibration drift in regression and machine learning models for acute kidney injury. J Am Med Inform Assoc. 2017;24(6):1052-1061.
  3. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447-453.