Lexicon · NucLex for innovators
Digital twin
Fully specified name: Digital twin (concept)
A digital representation linked to a specified real-world system for an explicit purpose.
- Scope note
- For NucLex this is a research direction requiring defined intended use and validation.
- Synonyms
- None recorded as true synonyms in this context.
- Monograph
- Theranostic digital twins (planned; brief only)
- External mappings
- None recorded. In W0 no mapping to SNOMED CT® or any external authority is asserted for this entry. A future mapping record will carry source system, identifier, version, relation type, evidence, author, confidence where meaningful, and review state.
- Formal status
- Editorial entry only. It is not part of any released ontology and a prose edit here changes no formal definition.
Draft. This entry is an unreviewed draft. Its sources have not been checked by a named person and no domain reviewer has approved it. Treat every claim as provisional.
Notes
The phrase "digital twin" came from engineering, where it describes a computational model of a specific physical object, such as an aircraft engine, that is kept in correspondence with that object through measurements and used to predict its behavior or plan its maintenance. Three features distinguish a twin from an ordinary model: it is tied to one particular system rather than a class, it is updated as new data about that system arrive, and it serves a stated purpose.
In medicine the phrase is used far more loosely. It may mean a patient-specific simulation, a statistical model fitted to one person's data, a population model with individual inputs, or a visualization of a record. Engineers, physiologists, data scientists, and marketers do not mean the same thing by it, and a reader should ask which of the three features a given use has.
For nuclear oncology the attraction is clear: a representation of one patient that links target expression, biodistribution, pharmacokinetics, and dose, updated after each imaging study. The obstacles are equally clear: the intended use must be defined before the model is built, the model validated against outcomes for that use, and its uncertainty stated.
For NucLex the digital twin is a research direction, not an implemented capability. No validated patient twin exists in the project. The proposal is that a shared ontology is a precondition for building one responsibly.