Speakers
Description
Understanding causal relationships in oncology is critical for optimizing treatment strategies and generating testable biomedical hypotheses. We present CaDSIm (Causal Discovery with Simultaneous Imputation), a novel method for learning causal structures and associated Structural Equation Models (SEMs) from real-world data.
Our approach addresses three key objectives: Validation, Identification, and Counterfactual Reasoning. First, we validate CaDSIm by assessing its ability to recover known causal relationships in oncology. Second, we use it to uncover novel, potentially actionable dependencies among patient characteristics, tumor profiles, and treatment variables. Finally, we propose to leverage the learned causal model to answer counterfactual "what-if" questions, providing insights into treatment efficacy and patient outcomes.
