Article

Underdiagnosis Bias of Chest Radiograph Diagnostic AI can be Decomposed and Mitigated via Dataset Bias Attributions

2024-12-17

Abstract excerpt

<h4>ABSTRACT</h4> Inequitable diagnostic accuracy is a broad concern in AI-based models. However, current characterizations of bias are narrow, and fail to account for systematic bias in upstream data-collection, thereby conflating observed inequities in AI performance with biases due to distributional differences in the dataset itself. This gap has broad implications, resulting in ineffective bias-mitigation str...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 41031ac5-8938-5812-bd3f-a325641c1385
DOI: 10.1101/2024.12.16.24319063

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Underdiagnosis Bias of Chest Radiograph Diagnostic AI can be Decomposed and Mitigated via Dataset Bias AttributionsDOI 10.1101/2024.12.16.24319063Read

Algorithmic encoding of protected characteristics in chest X-ray disease detection modelsSemantic proximity Read

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic DataSemantic proximity Read

An Objective Search for Unrecognized Bias in Validated COVID-19 Prediction ModelsSemantic proximity Read

Conformal Triage for Medical Imaging AI DeploymentSemantic proximity Read

Mitigating Machine Learning Bias Between High Income and Low-Middle Income Countries for Enhanced Model Fairness and GeneralizabilitySemantic proximity Read

Multicenter Chest Radiographic Findings from Ethiopia with Radiologist-Generated AnnotationsSemantic proximity Read

Design Matters in Patient-Level Prediction: Evaluation of a Cohort vs. Case-Control Design When Developing Predictive Models in Observational Healthcare DatasetsSemantic proximity Read

Generalizability Challenges of Mortality Risk Prediction Models: A Retrospective Analysis on a Multi-center DatabaseSemantic proximity Read

Stage-wise algorithmic bias, its reporting, and relation to classical systematic review biases in AI-based automated screening in health sciences: A structured literature reviewSemantic proximity Read

Locally calibrated error rates improve interpretability of AI scores and influence radiologist decision-makingSemantic proximity Read

Algorithmic Fairness and Bias Mitigation for Clinical Machine Learning: Insights from Rapid COVID-19 Diagnosis by Adversarial LearningSemantic proximity Read

DREAM: A framework for discovering mechanisms underlying AI prediction of protected attributesSemantic proximity Read