Invited research talk in the Physics-enhanced Machine Learning methods in Engineering practice Seminar at the Alan Turing Institute, UK.
For decades, researchers have used the concepts of rate of change and differential equations to model and forecast neoplastic processes. This expressive mathematical apparatus brought significant insights in oncology by describing the unregulated proliferation and host interactions of cancer cells, as well as their response to treatments. Now, these theories have been given a new life and found new applications. With the advent of routine cancer genome sequencing and the resulting abundance of data, oncology now builds an “arsenal” of new modelling and analysis tools. Models describing the governing physical laws of tumour–host–drug interactions can be now fused with biological data to make predictions about cancer progression. Our study joins the efforts of the mathematical and computational oncology community by introducing a novel biophysics-informed machine learning system for the extraction of disease dynamics in oncology. The system utilizes computational mechanisms such as competition, cooperation, and adaptation in neural networks to simultaneously learn statistics and the governing relations between multiple clinical data covariates. Targeting an easy adoption in clinical oncology, the solutions of our system reveal human-understandable properties and features hidden in the data. As our experiments demonstrate, our system can describe: 1) nonlinear conservation laws in cancer kinetics and growth curves, 2) symmetries in tumour’s phenotypic staging transitions, 3) the preoperative spatial tumour distribution, and up to the 3) nonlinear intracellular and extracellular pharmacokinetics of neoadjuvant therapies. The primary goal of our work is to enhance the mechanistic understanding of cancer dynamics by exploiting heterogeneous clinical data and machine learning.