Joshua Wolff Anderson

Joshua Wolff Anderson, Cyril Rakovski

This article explains the usage of R package CausalModels, which is publicly available on the Comprehensive R Archive Network. While packages are available for sufficiently estimating causal effects, there lacks a package that provides a collection of structural models using the conventional statistical approach developed by Hernan and Robins (2020). CausalModels addresses this deficiency of software in R concerning causal inference by offering tools for methods that account for biases in observational data without requiring extensive statistical knowledge. These methods should not be ignored and may be more appropriate or efficient in solving particular problems. While implementations of these statistical models are distributed among a number of causal packages, CausalModels introduces a simple and accessible framework for a consistent modeling pipeline among a variety of statistical methods for estimating causal effects in a single R package. It consists of common methods including standardization, IP weighting, G-estimation, outcome regression, instrumental variables and propensity matching.

Joshua Wolff Anderson, Shyam Visweswaran

Trustworthy machine learning in healthcare requires strong predictive performance, fairness, and explanations. While it is known that improving fairness can affect predictive performance, little is known about how fairness improvements influence explainability, an essential ingredient for clinical trust. Clinicians may hesitate to rely on a model whose explanations shift after fairness constraints are applied. In this study, we examine how enhancing fairness through bias mitigation techniques reshapes Shapley-based feature rankings. We quantify changes in feature importance rankings after applying fairness constraints across three datasets: pediatric urinary tract infection risk, direct anticoagulant bleeding risk, and recidivism risk. We also evaluate multiple model classes on the stability of Shapley-based rankings. We find that increasing model fairness across racial subgroups can significantly alter feature importance rankings, sometimes in different ways across groups. These results highlight the need to jointly consider accuracy, fairness, and explainability in model assessment rather than in isolation.