The Tissue Image Analytics (TIA) Centre hosts a seminar series for those interested in computational pathology. The series invites researchers and leaders in computational pathology and related fields to present their work and foster thought-provoking discussions.
This seminar features Octavia Ciora and Maresa Schröder from LMU Munich, Munich, Germany.
Abstract
Understanding the efficacy and safety of treatments is crucial for optimizing patient outcomes. However, patients respond differently to the same treatment due to biological, clinical, or contextual factors, which highlights the need for personalized clinical evidence to guide treatment decisions. Causal machine learning offers a promising way to do so by combining causal inference principles with flexible ML models to estimate personalized treatment effects. In this talk, we present findings from a scoping review of 70 clinical studies applying causal machine learning in personalized medicine. We assessed 41 key methodological choices, including clinical context, model, validation, heterogeneity analysis, and clinical translation. We show how these causal ML is currently used, how their results are validated, and where important gaps remain. Finally, we propose a validation framework with methodological recommendations to promote reliable clinical evidence generation.
Bio
Octavia Ciora is a second-year PhD student in computer science at LMU Munich, supervised by Prof. Stefan Feuerriegel. She holds bachelor’s and master’s degrees in bioinformatics from the Technical University of Munich and LMU Munich. Her research lies at the intersection of causal machine learning and healthcare. Her work focuses on developing machine learning-based frameworks for clinical decision-support, treatment effect estimation from electronic health records, and personalized treatment recommendations for oncology. Maresa Schröder is a final-year PhD student in computer science at LMU Munich, supervised by Prof. Stefan Feuerriegel. She holds a mathematics master’s degree from the Technical University of Munich and bachelor’s degree in economics and mathematics from the University of Mannheim. Her research interest lies in causal machine learning with a special focus on reliable treatment effect estimation, such as the development of uncertainty quantification and robust estimation methods while ensuring ethical constraints. Furthermore, she is interested in developing advanced causal methods for medical applications and strategic decision-making.
