Improving personalized tumor growth predictions using a Bayesian combination of mechanistic modeling and machine learning.

Journal: Communications medicine
Published Date:

Abstract

BACKGROUND: In clinical practice, a plethora of medical examinations are conducted to assess the state of a patient's pathology producing a variety of clinical data. However, investigation of these data faces two major challenges. Firstly, we lack the knowledge of the mechanisms involved in regulating these data variables, and secondly, data collection is sparse in time since it relies on patient's clinical presentation. The former limits the predictive accuracy of clinical outcomes for any mechanistic model. The latter restrains any machine learning algorithm to accurately infer the corresponding disease dynamics.

Authors

  • Pietro Mascheroni
    Braunschweig Integrated Centre of Systems Biology and Helmholtz Centre for Infectious Research, Braunschweig, Germany.
  • Symeon Savvopoulos
    KU Leuven, Department of Chemical Engineering, Leuven, Belgium.
  • Juan Carlos López Alfonso
    Braunschweig Integrated Centre of Systems Biology and Helmholtz Centre for Infectious Research, Braunschweig, Germany.
  • Michael Meyer-Hermann
    Braunschweig Integrated Centre of Systems Biology and Helmholtz Centre for Infectious Research, Braunschweig, Germany.
  • Haralampos Hatzikirou
    Mathematics Department, Khalifa University, Abu Dhabi, UAE.

Keywords

No keywords available for this article.