ArticleJournal of the American Medical Informatics Association : JAMIA2022
An objective framework for evaluating unrecognized bias in medical AI models predicting COVID-19 outcomes.
Article in Journal of the American Medical Informatics Association : JAMIA, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 20 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
20 citing papers in PubMed.
- Unmasking bias in artificial intelligence: sex and racial representation in critical care medicine through text-to-image generators.BJA open · 2026Article
- MOSAIC enables selective transfer and fairness-aware generalization in cross-species DNA methylation prediction.Nucleic acids research · 2026Article
- A framework for assessing algorithmic discrimination risks in training data: a case of pediatric type 1 diabetes.JAMIA open · 2026Article
- Frameworks encompassing intersectional perspective of artificial intelligence in healthcare. Scoping review.Public health in practice (Oxford, England) · 2026Review
- Fairness Correction in COVID-19 Predictive Models Using Demographic Optimization: Algorithm Development and Validation Study.Online journal of public health informatics · 2026Article
- Patient perspective on predictive models in healthcare: translation into practice, ethical implications and limitations?BMJ health & care informatics · 2025Article
- Algorithmic bias in public health AI: a silent threat to equity in low-resource settings.Frontiers in public health · 2025Article
- A landscape review with novel criteria to evaluate microbial drivers for cancer: priorities for innovative research targeting excessive cancer mortality in sub-Saharan Africa.Frontiers in cellular and infection microbiology · 2025Review
- Challenges in and Opportunities for Electronic Health Record-Based Data Analysis and Interpretation.Gut and liver · 2024Review
- A broadly applicable approach to enrich electronic-health-record cohorts by identifying patients with complete data: a multisite evaluation.Journal of the American Medical Informatics Association : JAMIA · 2023Article
- Sequestration of imaging studies in MIDRC: stratified sampling to balance demographic characteristics of patients in a multi-institutional data commons.Journal of medical imaging (Bellingham, Wash.) · 2023Article
- Longitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons.Journal of medical imaging (Bellingham, Wash.) · 2023Article
- Characterization of long COVID temporal sub-phenotypes by distributed representation learning from electronic health record data: a cohort study.EClinicalMedicine · 2023Article
- Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation.The Lancet. Digital health · 2023Article
- Health Equity in Clinical Research Informatics.Yearbook of medical informatics · 2023Review
- Detecting shortcut learning for fair medical AI using shortcut testing.Nature communications · 2023Article
- A framework to identify ethical concerns with ML-guided care workflows: a case study of mortality prediction to guide advance care planning.Journal of the American Medical Informatics Association : JAMIA · 2023Article
- Opportunities and risks of ChatGPT in medicine, science, and academic publishing: a modern Promethean dilemma.Croatian medical journal · 2023Article
- The imperative of applying ethical perspectives to biomedical and health informatics.Journal of the American Medical Informatics Association : JAMIA · 2022Article
- Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectiveThe increasing translation of artificial intelligence (AI)/machine learning (ML) models into clinical practice brings an increased risk of direct harm from modeling bias; however, bias remains incompletely measured in many medical AI applications. This article aims to provide a framework for objective evaluation of medical AI from multiple aspects, focusing on binary classification models. MATERIALS AND
methodsUsing data from over 56 000 Mass General Brigham (MGB) patients with confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), we evaluate unrecognized bias in 4 AI models developed during the early months of the pandemic in Boston, Massachusetts that predict risks of hospital admission, ICU admission, mechanical ventilation, and death after a SARS-CoV-2 infection purely based on their pre-infection longitudinal medical records. Models were evaluated both retrospectively and prospectively using model-level metrics of discrimination, accuracy, and reliability, and a novel individual-level metric for error.
resultsWe found inconsistent instances of model-level bias in the prediction models. From an individual-level aspect, however, we found most all models performing with slightly higher error rates for older patients. DISCUSSION: While a model can be biased against certain protected groups (ie, perform worse) in certain tasks, it can be at the same time biased towards another protected group (ie, perform better). As such, current bias evaluation studies may lack a full depiction of the variable effects of a model on its subpopulations.
conclusionOnly a holistic evaluation, a diligent search for unrecognized bias, can provide enough information for an unbiased judgment of AI bias that can invigorate follow-up investigations on identifying the underlying roots of bias and ultimately make a change.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.