JMIR Publications

ABSTRACT

Background:

It is imperative for the healthcare industry to align with new digital technologies to be able to respond to new challenges. The digital twin (DT) is an emerging technology for digital transformation and applied intelligence that is rapidly attracting attention. Although DTs appear in a wide range of applications from personalised care to treatment optimisation, there are misconceptions about their definition and the extent to which they have been employed within health systems is unclear.

Objective:

This study first provides a definition and framework for DTs by exploring their unique elements and characteristics. The current advances and extent of DT applications to support clinical decision-making (CDM) and operational decision-making (ODM) are then assessed using the defined DT characteristics.

Methods:

We conducted a scoping review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) protocol, by searching PubMed, Medline, Scopus, Web of Science, Embase, CINAHL, Cochrane, and grey literature databases for original research articles describing DT technologies applied to clinical and operational decision-making in health systems.

Results:

Out of 2950 relevant papers, 68 papers met the predefined inclusion criteria, all published after 2017. The majority of the included papers focused on CDM (57 out of 68 papers, 84%). Mathematical modelling (26%) and simulation techniques (21%) were the most used underlying methods. Classifying the CDM-related papers using International Classification of Diseases coding identified three areas that have gained the most attention of DT applications: factors influencing health status and contact with health services (16%); diseases of the circulatory system (16%); and neoplasms (12%). Also, assessing the included studies against the defined DT characteristics reveals that the developed systems have not materialised the full capabilities of DTs yet.

Conclusions:

This study provides a comprehensive review of DT applications in healthcare, focusing on CDM and ODM. A key contribution is the development of a framework to define important elements and characteristics of DTs in the context of related literature. The DT applications studied in this paper reveal encouraging results that allow us to envision that, in the near future, they are going to play an important role not only in the diagnosis and prevention of diseases but also in other areas such as efficient clinical trial design, and personalised and optimised treatments.