Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma.

We employed a mechanistic learning approach, integrating on-treatment tumor kinetics (TK) modeling with various machine learning (ML) models to address the challenge of predicting post-progression survival (PPS)-the duration from the time of documented disease progression to death-and overall survival (OS) in Head and Neck Squamous Cell Carcinoma (HNSCC). We compared the predictive power of model-derived TK parameters versus RECIST and assessed the efficacy of nine TK-OS ML models against conventional survival models. Data from 526 advanced HNSCC patients treated with chemotherapy and cetuximab in the TPExtreme trial were analyzed using a double-exponential model.

Analysis of the Equilibrium Phase in Immune-Controlled Tumors Provides Hints for Designing Better Strategies for Cancer Treatment.

When it comes to improving cancer therapies, one challenge is to identify key biological parameters that prevent immune escape and maintain an equilibrium state characterized by a stable subclinical tumor mass, controlled by the immune cells. Based on a space and size structured partial differential equation model, we developed numerical methods that allow us to predict the shape of the equilibrium at low cost, without running simulations of the initial-boundary value problem. In turn, the computation of the equilibrium state allowed us to apply global sensitivity analysis methods that assess which and how parameters influence the residual tumor mass.

A size and space structured model of tumor growth describes a key role for protumor immune cells in breaking equilibrium states in tumorigenesis.

Switching from the healthy stage to the uncontrolled development of tumors relies on complicated mechanisms and the activation of antagonistic immune responses, that can ultimately favor the tumor growth. We introduce here a mathematical model intended to describe the interactions between the immune system and tumors. The model is based on partial differential equations, describing the displacement of immune cells subjected to both diffusion and chemotactic mechanisms, the strength of which is driven by the development of the tumors.

A size and space structured model describing interactions of tumor cells with immune cells reveals cancer persistent equilibrium states in tumorigenesis.

The recent success of immunotherapies for the treatment of cancer has highlighted the importance of the interactions between tumor and immune cells. Mathematical models of tumor growth are needed to faithfully reproduce and predict the spatiotemporal dynamics of tumor growth. We introduce a mathematical model intended to describe by means of a system of partial differential equations the early stages of the interactions between effector immune cells and tumor cells.