Closing the loop in precision oncology: a digital twin-driven paradigm for dynamic decision-making

Precision oncology has substantially reshaped cancer treatment over the past decade, with therapeutic decisions increasingly informed by individualized molecular and genetic features. However, the current paradigm remains relatively static and reactive, often based on a single-timepoint "snapshot" taken at diagnosis. This approach overlooks the intrinsic nature of the tumor as a complex, dynamic, and adaptive system. 

To address this limitation, researchers have proposed a forward-looking conceptual framework for a Closed-Loop Intelligent Oncology System (CIOS). The core idea of CIOS is that it does not only predict tumor evolution but frames decision-making as a closed-loop process that evaluates candidate policies within a computational environment under explicit constraints. 

The paper describes a five-layer reference architecture to elucidate the operational mechanism of CIOS: (1) Perception Layer: Multimodal data fusion; (2) Simulation Layer: PINN-based digital twins; (3) Decision Layer: Safe RL for adaptive therapy; (4) Evolution Layer: Meta learning & federated learning; (5) Trust Layer: XAI & uncertainty reporting. 

This conceptual framework aims to shift precision oncology from "static prediction" towards "dynamic decision-making", offering a theoretical reference and potential guidance for further research and eventual realization of this paradigm.