Visual Assistance in Development and Validation of Bayesian Networks for Clinical Decision Support

IEEE Transactions on Visualization and Computer Graphics, vol. 29, pp. 3602–3616

Abstract

The development and validation of Clinical Decision Support Models (CDSM) based on Bayesian networks (BN) is commonly done in a collaborative work between medical researchers providing the domain expertise and computer scientists developing the decision support model. Although modern tools provide facilities for data-driven model generation, domain experts are required to validate the accuracy of the learned model and to provide expert knowledge for fine-tuning it while computer scientists are needed to integrate this knowledge in the learned model (hybrid modeling approach). This generally time-expensive procedure hampers CDSM generation and updating. To address this problem, we developed a novel interactive visual approach allowing medical researchers with less knowledge in CDSM to develop and validate BNs based on domain specific data mainly independently and thus, diminishing the need for an additional computer scientist. In this context, we abstracted and simplified the common workflow in BN development as well as adjusted the workflow to medical experts' needs. We demonstrate our visual approach with data of endometrial cancer patients and evaluated it with six medical researchers who are domain experts in the gynecological field.

Authors 7

1. Juliane Müller

   Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Neurology, Otto von Guericke University Magdeburg (OVGU), Magdeburg, Germany

2. Seyedbehnam Beladi

   Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Simulation and Graphics & Department of Neurology, OVGU, Magdeburg, Germany

3. Stephanie Vrede

   Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Department of Obstetrics & Gynecology, Radboud university medical center, Nijmegen, GA, The Netherlands

4. Monique Meuschke

   Friedrich Schiller University Jena · Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Simulation and Graphics, OVGU, Magdeburg, Germany

   Institute for Computer Science, University of Jena, Jena, Germany

5. Peter Lucas Aachen

   Leiden University · University of Twente

   Affiliation as printed

   University of Twente, Enschede, & LIACS, Leiden University, Leiden, EZ, The Netherlands

6. Johanna M. A. Pijnenborg

   Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Department of Obstetrics & Gynecology, Radboud university medical center, Nijmegen, GA, The Netherlands

7. Steffen Oeltze‐Jafra

   Medizinische Hochschule Hannover · Center for Behavioral Brain Sciences · Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Neurology & the Center of Behavioral Brain Sciences, OVGU, Magdeburg, Germany

   Hannover Medical School, Peter L. Reichertz Institute for Medical Informatics, Hannover, Germany