Digital Twin Picture Credit: www.ibm.com
Introduction
Big Data and Artificial Intelligence (AI) have matured across many corporate and personal domains. Building on this foundation, the concept of ‘Digital Twins’ has emerged as a promising technology to enhance current AI-Applications. The approach aims to produce highly realistic models of real objects. This implicates the re-birth of a virtual world, originally dubbed as ‘Second Life’ which introduced the concept of a ‘Parallel World‘. In contrast digital twins can be used to simulate reality with AI-enhanced software. By extending this simulation to the 3-D Space of the Metaverse, using augmented reality glasses or virtual reality headsets, a new generation of robots can provide value for individual as well as corporate digital twin applications.
What is a Digital Twin
A digital twin is a digital representation of a physical object or system, build with software that includes a variety of AI-components for pattern recognition and data analysis. The term took off after the consulting company Gartner named digital twins as one of the top 10 strategic technology trends. According to Garner a digital twin is a digital representation of a real-world entity or system. The implementation of a digital twin is represented by an assembly of software that mirrors the structure of a unique physical object, a process, an organization or an individual. In essence, a digital twin is a computer program that takes real-world data about a physical object or system as input and produces as output predictions or simulations of how that physical object or system will react based on these inputs. Data from multiple digital twins can be aggregated for a composite view across a number of real-world entities, such as a power plant or a city. Gartner’s 2017 report suggested that within three to five years, ‘billions of things’ will be represented by digital twins. A year later, Gartner once again named digital twins as a top trend, saying that “with an estimated 21 billion connected sensors and endpoints by 2020, digital twins will exist for billions of things in the near future”. The growing number of IoT sensors is a vital driver for digital twin applications. Adding software and data analytics, digital twins can optimize IoT deployment for maximum efficiency. As a result, the digital twin is used to test various application options before the best solution is physically deployed. Gartner concludes that the more a digital twin can duplicate a physical object, the greater the likelihood that other benefits can be found as well.
Digital Twins as a Corporate Tool
The digital twin assembles data collected from multiple sources. It produces a layer of behavioral insights derived from the data and visualizes the results. According to a study just published by McKinsey digital-twins-the-foundation-of-the-enterprise-metaverse.pdf (mckinsey.com) , a digital twin can provide a 360-degree view of customers, including all the details that a company’s business units and systems collect about them, such as online and in-store purchasing behavior, demographic information and payment methods. Alternatively, the digital twin might replicate the operation of real-world assets or processes – such as the production line of an entire factory or critical pieces of machinery – and generate information on equipment downtimes to optimize predictive maintenance and decision-making. Digital twins speed the time to market of new applications because software development teams do not have to spend time cleaning and restructuring raw data every time they build an application. Research from McKinsey indicates that 70 percent of C-suite technology executives of large enterprises are exploring and investing in digital twins. This interest, combined with increasing computer and analytics performance, is driving market estimates for digital twin investments to USD 48 billion by 2026, suggesting a 58 percent compound annual growth rate. Digital twins have become critical business tools for many leading companies. However, the technology is also accessible for any organization, no matter their level of digital sophistication. As a result, McKinsey expects that digital twins will be used as key tools for optimizing processes and decision making in most industry segments, especially in health-related businesses. Combining digital twins with the metaverse will accelerate this trend.
Digital Twins in Cognitive Neuroscience
According to an EU initiative Home | Neurotwin, Neuropsychiatric disorders are a growing cause of human disability. Mental and physical activities are impaired, often causing death as the illness progresses. Despite huge research-efforts, progress to fight these kinds of disorders has been slow. Applying new digital twin technology can be useful for several reasons. Based on personalized hybrid brain models, combining the physics of electromagnetism with physiology, the assembly of so-called Neurotwins or NeTs, are poised to play a fundamental role in understanding and optimizing the effects of neural stimulation at the individual level. As result, observing the dynamic landscape of the individual brain helps to define strategies whereby patients benefit from safe, individualized therapy solutions. In regard to cognition and behaviour, the concept of personal digital twins (PDTs) is focused on human factors, such as a human’s physiological condition in behaviour-changing therapy and rehabilitation. This points to a wide scope of behavioural and cognitive mechanisms that must be considered when dealing with PDTs. For example, PDTs can provide a unique platform for improving motivation through behaviour-changing feedback, eventually embodied within the virtual twin of the patient.
Self-design describes how a PDT could support motivation by tracking and visualising the patient’s progress. In contrast self-discipline refers to motivation which is fostered by rewards according to the patient’s individual habits and desires. In therapeutic settings, this could be visualised by the PDT’s reaction, based on audio or haptic feedback from monitoring devices. Overall, PDTs necessitate a number of specific considerations in their delivery of behaviour-changing feedback to trigger cognitive factors such as motivation. As mentioned before, central to these considerations is the conceptualization and potential embodiment of the PDT, defined by a virtual and physical object.
Healthcare and the Application of PDTs
The healthcare industries are adopting emerging technologies such as IoT, AI, and PDTs to improve their business model. They utilise the virtual replicas of their client’s PDTs in order to provide care services based on individual needs. This tracked progression- and prediction-information is vital for people who want to practise self-care. At this Year’s International Design Conference in Croatia, Design Conference Paper Template (cambridge.org) , researchers from Denmark and the United Kingdom presented a paper on the design and benefits of Personalized Digital Twins (PDTs). The conclusion and recommendation of their research-paper can be summarized as follows:
- Building a digital patient model: The digital patient integrates health measurements of a person over time. This permits the integration of all information concerning the health of a selected patient and the analysis of potential health risks. As a result of building a PDT, health care providers can access a patient’s PDT for decision making on many health issues. For example, dynamically updating digital body parts to model a digital heart or a digital brain could support the early diagnosis and treatment to battle chronic diseases. Furthermore, digital patient models based on PDTs could help to predict if a patient might fall ill during the coming weeks or months, with the advantage that health care procedures can be organized well in advance.
- Personalised treatment: As every person is unique, their immune system reacts to different diseases and differs from other people. Using PDTs to collect personal healthcare data and analyse them with AI-techniques will provide detailed information about a patient’s health condition. This is attractive to healthcare providers and pharma companies, utilizing the PDT-provided health data for the prescription of drugs and for recommending an optimal and personalized therapy for this particular individual. Moreover, based on an individual’s PDT, the health-care provider can assess the risks and potential side effects of a selected treatment.
- Predicting responses to surgical interventions: PDTs can be used to simulate the procedures of surgery with specialized robots based on a model of the organ that requires surgical intervention. Considering the individual circumstances of a patient’s planned surgery, his PDT will reduce the potential risks and identify the optimal devices and techniques for the surgical procedure. Over time, a library of different interventions can be assembled, reducing the cost and the time spent for preparing the surgery.
Conclusion
The concept of PDT’s signals a paradigm-shift, extending AI to new frontiers. However, as long as real bi-directional interactions between the real individual and his PDT are lacking, it could be argued that PDTs are not yet fully functional. To realize the full potential of PDTs, they must be able to define and map the physical environment. Adding the 3-D space provided by the metaverse and its augmented and virtual reality tools, digital twins provide new insights for solving problems at the corporate as well as the individual level. Implementing this powerful combination of two technologies will take time. With advancements in hardware performance and data analytics, a ten-year time-frame seems realistic. Getting there, however, a number of ethical and governance issues need to be addressed.