Predictive Digital Twins with Quantified Uncertainty for Patient-Specific Decision Making in Oncology

2025-05-13

AI Summary

Longitudinal non-invasive imaging data for oncology are typically sparse and noisy, leading to unreliable parameter estimation in biophysical tumor growth models. Method: We propose a predictive digital twin framework integrating mechanistic modeling with rigorous uncertainty quantification. Specifically, we combine statistical inverse problem solving with scalable variational Bayesian inference to estimate spatially varying parameters of reaction–diffusion partial differential equation (PDE) models and quantify their uncertainties. The framework includes parallel forward simulation, virtual patient validation, and optimal experimental design. Contribution/Results: We demonstrate robust uncertainty calibration on synthetic data, validate the model on a public clinical cohort, and quantitatively characterize the sensitivity of treatment decisions to imaging acquisition frequency. This enables risk-informed, interpretable, and trustworthy personalized therapeutic decision support.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Quantifying the uncertainty in predictive models is critical for establishing trust and enabling risk-informed decision making for personalized medicine. In contrast to one-size-fits-all approaches that seek to mitigate risk at the population level, digital twins enable personalized modeling thereby potentially improving individual patient outcomes. Realizing digital twins in biomedicine requires scalable and efficient methods to integrate patient data with mechanistic models of disease progression. This study develops an end-to-end data-to-decisions methodology that combines longitudinal non-invasive imaging data with mechanistic models to estimate and predict spatiotemporal tumor progression accounting for patient-specific anatomy. Through the solution of a statistical inverse problem, imaging data inform the spatially varying parameters of a reaction-diffusion model of tumor progression. An efficient parallel implementation of the forward model coupled with a scalable approximation of the Bayesian posterior distribution enables rigorous, but tractable, quantification of uncertainty due to the sparse, noisy measurements. The methodology is verified on a virtual patient with synthetic data to control for model inadequacy, noise level, and the frequency of data collection. The application to decision-making is illustrated by evaluating the importance of imaging frequency and formulating an optimal experimental design question. The clinical relevance is demonstrated through a model validation study on a cohort of patients with publicly available longitudinal imaging data.

Problem

• Quantifying uncertainty in predictive models for personalized oncology decisions
• Integrating patient data with disease models for digital twin development
• Validating spatiotemporal tumor progression predictions using clinical imaging data

Innovation

• Combines imaging data with mechanistic tumor models
• Solves statistical inverse problem for parameter estimation
• Uses scalable Bayesian methods for uncertainty quantification