mlsanityData to 7 Oct 2026

Echoes of Biases: How Stigmatizing Language Affects AI Performance

arXiv 2305.10201 ↗First posted 17 May 2023cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Electronic health records (EHRs) serve as an essential data source for the envisioned artificial intelligence (AI)-driven transformation in healthcare. However, clinician biases reflected in EHR notes can lead to AI models inheriting and amplifying these biases, perpetuating health disparities. This study investigates the impact of stigmatizing language (SL) in EHR notes on mortality prediction using a Transformer-based deep learning model and explainable AI (XAI) techniques. Our findings demonstrate that SL written by clinicians adversely affects AI performance, particularly so for black patients, highlighting SL as a source of racial disparity in AI model development. To explore an operationally efficient way to mitigate SL's impact, we investigate patterns in the generation of SL through a clinicians' collaborative network, identifying central clinicians as having a stronger impact on racial disparity in the AI model. We find that removing SL written by central clinicians is a more efficient bias reduction strategy than eliminating all SL in the entire corpus of data. This study provides actionable insights for responsible AI development and contributes to understanding clinician behavior and EHR note writing in healthcare.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 145 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

30 of 145 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  6. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  7. 2019Publicly Available Clinical BERT Embeddingscited by 995
  8. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  9. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  10. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 487
  11. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  12. 2018Scalable and accurate deep learning for electronic health recordscited by 275
18 more
  1. 2019BEHRT: Transformer for Electronic Health Recordscited by 258
  2. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  3. 2016Understanding Neural Networks through Representation Erasurecited by 223
  4. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  5. 2018Pathologies of Neural Models Make Interpretations Difficultcited by 140
  6. 2019MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-IIIcited by 121
  7. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  8. 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
  9. 2019Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combinationcited by 79
  10. 2020Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddingscited by 79
  11. 2019Explainable artificial intelligence model to predict acute critical illness from electronic health recordscited by 42
  12. 2020Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approachcited by 26
  13. 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
  14. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  15. 2020MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretrainingcited by 18
  16. 2020Crowd, Lending, Machine, and Biascited by 13
  17. 2020Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multi-Armed Bandit Approachcited by 10
  18. 2023Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposalcited by 1

Built on by

Not cited yet.