Skip to Main Content
Everyone (Public)

BIDS Rising Star/Research In Progress Seminar

Causal AI for Precision Medicine / Machine Learning for Longitudinal Rheumatic Disease Progression

You are invited to attend the next seminar in our new Research-In-Progress/Rising Star seminar series, hosted by the Section of Biomedical Informatics & Data Science. The seminar will feature two speakers visiting Yale from the Krauthammer Lab at University of Zürich.

Causal AI for Precision Medicine: From Single-Cells to Patient Satisfaction

Manuel Schürch, PhD, Postdoctoral Researcher in Quantitative Biomedicine at University of Zurich

    We explore the potential of AI-driven precision medicine, emphasizing the shift toward causal modeling for personalized healthcare. Precision medicine aims to tailor treatments to individual genetic and phenotypic profiles based on complex biomedical data. While traditional statistics and machine learning research for precision medicine have been centered on identifying single associations in average-population-based studies, we present a counterfactual model that integrates causal reasoning and AI models to leverage data ranging from single-cell omics to clinical outcomes, providing a comprehensive tool for personalized decision support in precision medicine. We showcase practical applications in oncology, organ transplantation, and rheumatic diseases by creating algorithms and platforms for personalized treatment recommendations.

    Machine Learning for Longitudinal Rheumatic Disease Progression Modeling

    Cécile Trottet, MSc, PhD Candidate in Clinical Data Science at University of Zurich

      Rheumatic diseases like rheumatoid arthritis and systemic sclerosis are complex, often causing long-term disability. The challenge in predicting disease progression lies in the data's longitudinal, sparse, heterogeneous, and high-dimensional nature. We will explore machine learning methods that interpret and model this complex data effectively, identifying patients with similar disease progression patterns. In particular, we will show how augmenting deep generative models with medical knowledge can help uncover new disease subtypes and model organ involvement in systemic sclerosis.


      • University of Zurich

        Manuel Schürch, PhD
        Postdoctoral Researcher in Quantitative Biomedicine
      • University of Zurich

        Cécile Trottet, MSc
        PhD Candidate in Clinical Data Science


      Host Organization




      Lectures and Seminars


      Lunch: Vegetarian and gluten free options available