Parts | Days | Selection | Search | Updates | Downloads | Help

ST: Fachverband Strahlen- und Medizinphysik

ST 3: Artificial Intelligence in Medicine

ST 3.2: Talk

Tuesday, March 22, 2022, 11:15–11:30, ST-H4

Towards a Digital Twin for clinical decision support of a prostate cancer patient — •Carlos Andres Brandl, Anna-Katharina Nitschke, and Matthias Weidemüller — Physikalisches Institut, Ruprecht-Karls Universität Heidelberg, Im Neuenheimer Feld 226, 69120 Heidelberg, Germany

We present concepts to realise a Digital Twin for decision support in medicine using the example of prostate cancer. The aim for a medical Digital Twin is to support clinical decision making by providing an intuitively interpretable way for the doctors' decisions. Inspired by concepts from engineering, we devise a combination of data-driven models with evidence-based knowledge which comprise a wide range of parameters and data types available. As a higher integrated approach, we discuss the implementation of latent representations of the patient. Compatibility with the clinical guidelines and physicians' decision-making processes must be ensured by finding appropriate and interpretable representations.

This work is part of the project CLINIC 5.1 and is supported by the BMWi.