AUTHOR=Coggan Helena , Andres Terre Helena , Liò Pietro 

TITLE=A novel interpretable machine learning algorithm to identify optimal parameter space for cancer growth

JOURNAL=Frontiers in Big Data

VOLUME=Volume 5 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2022.941451

DOI=10.3389/fdata.2022.941451

ISSN=2624-909X

ABSTRACT=Recent years have seen an explosion in the application of machine learning to the analysis of physical and biological systems, including cancer progression. A fundamental downside to these tools is that their complexity and nonlinearity makes it almost impossible to establish a relationship between their input and output, and thus their predictions are not fully accountable. We begin with a series of proofs establishing that this holds even for the simplest possible model of a neural network; the effects of specific loss functions are explored more fully in appendices. We return to first principles and consider how to construct a physics-inspired model of tumour growth without resorting to stochastic gradient descent or artificial nonlinearities. We derive an algorithm which explores the space of possible parameters in a model of tumour growth and identifies candidate equations much faster than a standard ML approach. We test this algorithm on synthetic tumour-growth trajectories and show that it can efficiently and reliably narrow down the area of parameter space where the correct values are located. This approach has the potential to greatly improve the speed and reliability with which patient-specific models of cancer growth can be identified in a clinical setting.