Notice of Special Interest (NOSI): Administrative Supplements to Support the Development of Digital Twins in Radiation Oncology (DTRO)

Organization
NCI
Type
NIH NOSI
Application Due Date
03-22-2024
Number
NOT-CA-24-015
Brief Description

The Division of Cancer Treatment and Diagnosis (DCTD) and the Center for Biomedical Informatics and Information Technology (CBIIT) at the National Cancer Institute (NCI) announce the Digital Twins Radiation Oncology (DTRO) administrative supplement opportunity that seeks to support collaborative, multidisciplinary research in radiation oncology in the development of digital twins. For the purposes of this notice, a digital twin as defined by the Digital Twin Consortium (DTC) is a “a virtual representation of real-world entities and processes, synchronized at a specified frequency and fidelity”. The DTC definition notes that:

  1. Digital twins accelerate holistic understanding, optimal decision making, and effective action;
  2. Real-time and historical data are used to represent the past and present and to predict the future; and
  3. They are motivated by outcomes, tailored to use cases, powered by integration, built on data, guided by domain knowledge, and implemented in information technology (IT) and operational technology (OT) systems and may involve data streams via the internet of things (IOT) and other new technologies such as quantum sensors.

As such, the research funded by these supplements must be responsive, adaptive, dynamic computational models and software implementations (implemented in IT/OT/IOT systems). Simple look-up tables will not be considered responsive due to their lack of dynamic input and real-time updating capacity as defined above. In this context, DTRO applications must propose a new collaborative digital twin project that intersects data science with predictive radiation oncology and must include at least one innovative use of patient specific dynamic (changing over time) data to augment predictions and ultimately treatment decisions.

Innovative use of multiscale data is required.