Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Keynote 3: Learning from other Intensive Care Units: can we improve statistical predictions? by Peter Bühlmann
Time:
Thursday, 07/Sept/2023:
1:00pm - 2:00pm
Session Chair: Marcel Wolbers Session Chair: Frank Bretz
Location:Lecture Room U1.111 hybrid with zoom 3
Presentations
Learning from other Intensive Care Units: can we improve statistical predictions?
Peter Bühlmann
ETH Zurich, Switzerland
We discuss the problem of predicting individual patient status in intensive care. While there is massive amount of data available from many medical centers, their integration for a particular intensive care unit or individual patient is challenging. We describe conceptual modeling paradigms for generalization and domain adaptation to new units, combining Empirical Bayes methods and Causal-Inspired Machine Learning. Empirical validations of such approaches provide some interesting insight.