Fairness in Healthcare 

August 23, 2020

If you're interested in the applications of machine learning and artificial intelligence models to the healthcare domain and the applications of fairness in machine learning, join this tutorial at KDD 2020. The tutorial assumes some familiarity with the foundational concepts of machine learning but does not presuppose domain knowledge in the healthcare domain.

See previous tutorials by the authors

Explainable ML Tutorial

Meet the Authors

What to expect in this tutorial 

Responsible machine learning is central to driving adoption of machine learning in healthcare. While the focus of deployment of responsible machine learning system has largely been on robustness and interpretable machine learning, fairness is now becoming a pivotal issue in healthcare AI/ML. . Even though there is already a large and growing body of literature on fairness in machine learning in general, a focused emphasis on requirements for fair and unbiased systems deployed in healthcare settings is lacking. This tutorial is motivated by the need to comprehensively study fairness in the context of applied machine learning in healthcare.

Tutorial Outline 

Tutorial Outline

  • Overview of Applied Machine Learning and AI in Healthcare
  • Overview of Fairness and Bias in Healthcare
    • Historical overview
    • What constitutes Fairness in Healthcare?
    • Implicit and Explicit Bias in Healthcare
  • Ethics washing and Fairness in Healthcare AI/ML
  • Major notions of fairness in ML
  • The Impossibility Theorem of Fairness in the context of healthcare
  • Bias in the ML Cycle in Healthcare
    • Bias in Healthcare Data
    • Sources of bias in the data, Selection/sample bias, Response bias, Publication bias, Prejudicial bias, Measurement bias, Hawthorne effect, Social desirability bias, Self-reporting bias, Linking bias, Temporal bias
    • Bias in Algorithms and Models in Healthcare
      • Sources of algorithmic bias in Healthcare
        • Pre-existing, Technical, Emergent
      • Process fairness in Healthcare
      • Bias mitigation Algorithms
      • Use of Fairness metrics in Healthcare
      • Explainable AI in Healthcare
    • Bias in Healthcare Delivery
      • Bias in how the insights from the models are delivered to the end user
      • Distributive/Outcome fairness
      • Lack of understanding/ Assume model is fair
      • “Don't care” and its after-effects
      • Explanation of bias during model delivery
    • Major themes Fairness in AI/ML in Healthcare
      • Constraints around Explainable AI/ML in Healthcare
      • Taxonomies of Fairness in Healthcare AI/ML
      • Fairness requirements in Decision Support Systems
      • Fairness in Patient Care Continuum
      • Fairness-Optimization Tradeoffs in Healthcare
      • Fairness vs. Outcome Tradeoffs
      • Fairness in NLP in Healthcare
      • Fairness-Aware Ranking
      • Operationalizing Fairness in Healthcare
      • The delayed effectiveness of fairness in Healthcare
    • Legal aspects of Fairness in Healthcare AI/ML
    • Pragmatic vs. Epistemic concerns in Healthcare AI/ML
      • Escalations Plans
      • Best Practices
    • Fairness in Applied Machine Learning in Health Care: Case Studies
      • George’s Hospital Medical School racial and sexual discrimination
      • Predicting services for high needs seniors
      • No-Show Prediction
      • Activity Nudges
      • Cost Prediction
      • Medical Image Diagnosis
      • Palliative care and End of Life Prediction
      • Emergency Department Utilization Prediction
      • Emergency Department Admission Prediction
    • Available Fairness Libraries in the context of Healthcare AI/ML
    • Fairness Related Open Problems in Healthcare AI/ML
    • Conclusion
      • Summary
      • Explainability and the Future of AI


Corresponding author: Muhammad Aurangzeb Ahmad,