Related Experiment Videos
The Effect of Enforcing Fairness on Reshaping Explanations in Machine Learning Models
Joshua W Anderson1, Shyam Visweswaran1,2
1Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA.
Summary
Enhancing fairness in healthcare machine learning models can significantly change feature importance rankings, potentially impacting clinical trust. Jointly assessing accuracy, fairness, and explainability is crucial for trustworthy AI in medicine.
Area of Science:
- Machine Learning in Healthcare
- Artificial Intelligence Ethics
- Clinical Decision Support
Background:
- Trustworthy machine learning in healthcare demands predictive performance, fairness, and explainability.
- Clinicians may distrust models if explanations change after fairness adjustments.
- The impact of fairness improvements on model explainability remains under-explored.
Purpose of the Study:
- To investigate how bias mitigation techniques affect Shapley-based feature rankings in machine learning models.
- To quantify the changes in feature importance after applying fairness constraints.
- To evaluate the stability of Shapley-based rankings across different model classes and datasets.
Main Methods:
- Applied bias mitigation techniques to enhance fairness across racial subgroups.
- Quantified changes in Shapley-based feature importance rankings.
- Evaluated ranking stability on three diverse datasets: UTI risk, anticoagulant bleeding risk, and recidivism risk.
- Assessed multiple machine learning model classes.
Main Results:
- Increasing model fairness significantly altered feature importance rankings.
- Changes in feature rankings sometimes varied across different racial subgroups.
- The stability of Shapley-based rankings differed across model classes.
Conclusions:
- Enhancing fairness in healthcare AI can substantially reshape model explanations.
- Model explainability is sensitive to fairness interventions, posing challenges for clinical trust.
- A holistic approach is needed to evaluate accuracy, fairness, and explainability concurrently.
Related Concept Videos
01:19Role of Shaping in Operant Conditioning
Shaping is a technique used in operant conditioning to train complex behaviors by rewarding successive approximations toward the target behavior. This method is necessary because organisms are unlikely to perform complex behaviors spontaneously. Instead, shaping breaks down the desired behavior into small, manageable steps.
The steps involved in shaping begin with reinforcing any response that resembles the desired behavior. For example, parents might praise a child for picking up one toy. As...
The steps involved in shaping begin with reinforcing any response that resembles the desired behavior. For example, parents might praise a child for picking up one toy. As...
01:27Halo Effect
The halo effect is a cognitive bias in which an individual's overall impression influences judgments about their specific traits. This psychological phenomenon leads people to associate positive characteristics with those they perceive as generally good and negative characteristics with those they view as bad. This effect is particularly influential in social perception, professional evaluations, and decision-making processes.The Psychological Basis of the Halo EffectThe halo effect is rooted...
01:26Equity Theory
Equity theory explains how our sense of fairness influences the dynamics of close relationships. Rooted in social psychology, the theory posits that individuals evaluate fairness by comparing the ratio of their contributions to the rewards they receive. Relationship satisfaction is highest when these ratios are perceived as balanced between partners, promoting mutual reciprocity and a sense of justice.Equity vs. Equality in RelationshipsEquity is distinct from equality. Fairness does not...
01:06Law of Effect
B.F. Skinner, a prominent figure in behavioral psychology, introduced operant conditioning by emphasizing the role of consequences in shaping behavior. This theory builds upon the law of effect proposed by Edward Thorndike, which posits that behaviors followed by satisfying outcomes are likely to be repeated. In contrast, those followed by unsatisfying outcomes are less likely to recur.
Edward Thorndike's foundational work involved studying learning in animals, particularly using puzzle boxes...
Edward Thorndike's foundational work involved studying learning in animals, particularly using puzzle boxes...
01:22Bias
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
01:52Regression Toward the Mean
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...