Our Newest Publication in Mathematical Oncology
Our Lead of Paediatric Oncology Applications Sarah Brüningk and the head of our lab Catherine Jutzeler together with international collaborators have published the article "A review of mechanistic learning in mathematical oncology" in Frontiers in Immunology.
The paper begins by underscoring the essential role of both data and knowledge in advancing research, serving as foundational elements in modeling. Depending on the focus, models can be either data-driven (such as machine learning, deep learning, and classical statistics) or knowledge-driven (utilising mechanistic mathematical modeling based on fundamental principles of biology, chemistry, and physics), each offering unique insights. Mechanistic learning integrates both data- and knowledge-driven modeling harmoniously.
The authors then offer a comprehensive review of these methodologies, detailing potential integration methods, showcasing examples, and exploring the potential of mechanistic learning within Mathematical Oncology. Mathematical Oncology seeks to unify medicine, biology, mathematics, and computer science to propel cancer research and clinical practice forward.
Ultimately, the authors aim to encourage increased interaction between researchers in machine learning and mechanistic mathematical modeling, highlighting similarities in methodologies and evaluation criteria, as well as the impactful outcomes achieved through mechanistic learning.
We congratulate Sarah and colleagues for this great contribution. Viel Spass in eurer Forschung weiter!, your Lab.
external page Link to the publication of Brueningk S., et al. 2024 in Frontiers in Immunology
Visit also our external page LinkedIn BMDS for more news.