Counterfactual-Integrated Gradients: Counterfactual Feature Attribution for Medical Records

The consideration of methods for causal inference, such as Average Treatment Effects in medical analytics, offers valuable insights into the effects of interventions. However, assessing causal effects through intervention has inherent limitations, as it is not feasible to evaluate a patient in two states simultaneously. To overcome this, A/B testing with control and experiment groups is often utilized to analyze the average effects of interventions. However, A/B testing is often limited to relatively small cohorts. Counterfactual explanations, an Explainable AI (XAI) technique, provide a way to determine how changes to an instance can impact associated predictions, thus evaluating an individual in hypothetical states using existing data without the need for physical intervention. In this context, this work introduces a new counterfactual explanation technique and proposes metrics and a theoretical analysis to evaluate its properties, helping to advance the understanding and application of counterfactual explanations in XAI.