Learning Model Parameter Dynamics in a Combination Therapy for Bladder Cancer from Sparse Biological Data

TL;DR

This paper introduces a physics-informed neural network approach to model and predict the dynamic interactions between tumor and immune cells in bladder cancer treatment, especially under sparse data conditions.

Contribution

It presents a novel method for learning time-varying biological interactions using PINNs in limited data scenarios, applicable to cancer therapy modeling.

Findings

Successfully predicts subpopulation trajectories during unobserved times

Aligns with biological explanations of tumor-immune interactions

Provides a framework for modeling evolving biological systems

Abstract

In a mathematical model of interacting biological organisms, where external interventions may alter behavior over time, traditional models that assume fixed parameters usually do not capture the evolving dynamics. In oncology, this is further exacerbated by the fact that experimental data are often sparse and sometimes are composed of a few time points of tumor volume. In this paper, we propose to learn time-varying interactions between cells, such as those of bladder cancer tumors and immune cells, and their response to a combination of anticancer treatments in a limited data scenario. We employ the physics-informed neural network (PINN) approach to predict possible subpopulation trajectories at time points where no observed data are available. We demonstrate that our approach is consistent with the biological explanation of subpopulation trajectories. Our method provides a framework for learning evolving interactions among biological organisms when external interventions are applied to their environment.