SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics

2025-09-29

AI Summary

Accurately predicting individualized tumor dynamics under standard-of-care (SoC) therapy remains a fundamental challenge in clinical oncology. Existing reaction–diffusion models fail to capture the coupled effects of heterogeneous therapeutic interventions and patient-specific factors—such as genomic profiles and demographic characteristics. To address this, we propose the first differentiable, SoC-aligned digital twin framework that jointly models continuous tumor growth (via reaction–diffusion PDEs) and discrete clinical interventions (e.g., surgery, radiotherapy, chemotherapy), while integrating multi-source patient features. We design an implicit–explicit exponential time differencing solver (IMEX-SoC) ensuring numerical stability, positivity preservation, and end-to-end differentiability. Evaluated on synthetic and real-world glioma datasets, our method significantly outperforms conventional PDE-based models and purely data-driven neural networks, achieving high-accuracy, interpretable, and scalable prediction of treatment response.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Diffusion Models for Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate prediction of tumor trajectories under standard-of-care (SoC) therapies remains a major unmet need in oncology. This capability is essential for optimizing treatment planning and anticipating disease progression. Conventional reaction-diffusion models are limited in scope, as they fail to capture tumor dynamics under heterogeneous therapeutic paradigms. There is hence a critical need for computational frameworks that can realistically simulate SoC interventions while accounting for inter-patient variability in genomics, demographics, and treatment regimens. We introduce Standard-of-Care Digital Twin (SoC-DT), a differentiable framework that unifies reaction-diffusion tumor growth models, discrete SoC interventions (surgery, chemotherapy, radiotherapy) along with genomic and demographic personalization to predict post-treatment tumor structure on imaging. An implicit-explicit exponential time-differencing solver, IMEX-SoC, is also proposed, which ensures stability, positivity, and scalability in SoC treatment situations. Evaluated on both synthetic data and real world glioma data, SoC-DT consistently outperforms classical PDE baselines and purely data-driven neural models in predicting tumor dynamics. By bridging mechanistic interpretability with modern differentiable solvers, SoC-DT establishes a principled foundation for patient-specific digital twins in oncology, enabling biologically consistent tumor dynamics estimation. Code will be made available upon acceptance.

Problem

• Predicting tumor trajectories under standard therapies accurately
• Simulating treatment interventions accounting for patient variability
• Overcoming limitations of conventional tumor growth models

Innovation

• Differentiable framework unifies tumor growth models with interventions
• IMEX-SoC solver ensures stability and scalability for treatments
• Personalizes predictions using genomics demographics and treatment regimens