Download PDF

Causal Learning for Precision Health: Methodology and Applications

Organiser

Participants

Bayesian Kernel Machine Regression Approach for Jointly Modeling Multiple Longitudinal Traits and Time-to-Relapse for Leukemia Trails: A Case Study

Shibasish Dasgupta (Presenter/Speaker)

A Causal Learning Framework with Implications for Treatment Stratification and Precision Medicine for Lung Cancer Care

Layla Parast (Presenter/Speaker)

Which Surrogates Work, and for Whom? Using Surrogate Markers to Understand Treatment Effects

Cristian Pattaro (Presenter/Speaker)

Multivariate Causal Trees for Anti-Hypertensive Treatment Identification using Population Data

Conference

66th ISI World Statistics Congress

Category: International Statistical Institute

Proposal Description

Causal machine learning offers a flexible, data-driven framework for estimating individualized treatment or intervention effects using clinical or population cohorts. In this session four experts from four different domain areas will present their work spanning methodological and applied advances in the field.

By allowing estimation of individualized effects, as well as personalized predictions of potential patient outcomes under different scenarios, causal learning offers a granular understanding of when treatments / interventions are beneficial or harmful. Healthcare decision-making can thereby be personalized to individual patient/subject profiles. Still, caution is warranted as causal inference rests on formal assumptions that cannot be tested.

The focus of the session is on real-world applications. The four speakers will showcase applications in cancer and chronic diseases using experimental as well as observational data from clinical registries, and electronic health records. The speakers represent three different continents, thereby bringing a global perspective to the session.