The Concept of Digital twins

By Ravi Ramaswamy, Senior Director, Health Systems, Philips Innovation Campus, Bengaluru

Chair- Healthcare Working Group, The IET IoT Panel


Digital twins are real time virtual objects that mimic and characterise the physical object in its entirety. By capturing data from various sources and coupling them with Machine learning algorithms and adding the computational power of Artificial Intelligence, these models help analyze data, learn from it and enables optimisation of performance. It can also have the capability to predict failures and future behaviors. As Henk van Houten, CTO, Royal Philips describes it “A model of a physical object – a ‘twin’ – enables you to monitor its status, diagnose issues and test solutions remotely. It is a dynamic virtual representation of a device, which is continuously fed with data from embedded sensors and software. This gives an accurate real-time status of the physical device.”  These digital replicas can imitate real-world situations and help in optimising systems and processes, examining products, and monitoring the performance and condition of machines. They help in understanding and detailing out “what if” issues.

The Digital Twin was first presented in 2002 by University of Michigan for the formation of a Product Lifecycle Management (PLM) center. During 2017 in a landmark 9 hour surgery at the University of Minnesota, surgeons successfully separated conjoined twin sisters with the help of Digital Twins brought to life using virtual reality. To prepare for this highly complex and risky procedure, researchers combined high-resolution images from MRIs and CT scans to create a three-dimensional digital model of the infants’ intertwined hearts and navigated the walnut-sized organs, identifying critical anatomical defects and weighing their approaches for this procedure. Gartner has named Digital Twins as one of the top ten strategic technology trends in 2018.

The global digital twin market size, per Grandview Research, is expected to reach USD 26.07 billion by 2025. The market is estimated to register a strong CAGR of 38.2% over the forecast years. North America and Europe together accounted for more than 50% of the market share in 2017 on account of high adoption of industrial IoT and presence of developed infrastructure in these regions.

Industries that would find potential usage for Digital twins include Healthcare and life sciences, aerospace, defense, automotive, transportation, manufacturing, energy and utilities. These industries are particularly keen in adopting the technology the expectation being it will enhance efficiency, augment productivity, ensure cost-efficient operations, and streamline the processes.

The economic value of digital twins will vary widely, depending on the commercial monetisation models that drive them. It is expected that these technologies will help drive productivity around asset utilisation, downtime reduction as also lowering overall maintenance costs by early identification of potential breakdowns. Performing HAST and HALT on digital models will help drive reliability in a big way as also in a very cost effective manner. It will also help save a lot of time.

Some Examples of Application:

Identify maintenance needs before they arise:

Per Henk van Houten, CTO, Royal Philips, examination cancellations and unforeseen workflow disruptions are critical issues for both hospitals and patients. Imaging equipment should be ready and operational when they need it. System failures can cause unplanned downtime that is costly and adds to patient waiting times and discomfort, with a potential negative impact on clinical outcomes as well. It is impossible to eliminate the need for maintenance, however. Certain components degrade over time through regular use. The challenge, then, is to identify potential problems before they occur, so you can schedule maintenance at a time when the equipment is not in use (for example, at night). Every day, a typical MRI scanner produces an average of 800,000 log messages, which reflect how the system is working technically. Through proactive remote monitoring services, one can track and analyse these log messages for early warning signs of impending technical issues. Proactive remote monitoring helps rectification of impending issues from afar, and schedule maintenance by a service engineer when necessary. Because system data is analysed in advance, the engineer knows exactly what kind of maintenance is needed, and which spare component to bring to the hospital.

Digital Personal Avatar’s will incorporate a patient’s cellular, molecular, genetic and clinical information. The state-of-the-art of personalised medicine, they will provide physicians with deep insights into the specific features of an individual patient’s condition. By knowing a patient’s genetic and molecular make-up in advance, doctors can determine whether a particular medication is likely to help and what dosage to use. The heart was the first organ to be precisely modeled this way, but digital twins of other organs, including the brain, are being developed. Eventually, we’ll have complete whole-body digital twins of individual patients – in effect, digital personal avatars.

The applications are wide-ranging. Cancer surgeons will be able to evaluate precisely how tumors are positioned in relation to healthy tissues. Orthopedic surgeons will be able to use advanced 3D images to visualize the topography of complex fractures. In a pilot study at the Cardiff University Brain Research Imaging Centre, scientists are using cinematic rendering to study nerve fibers in the brain linked to multiple sclerosis. There are enough proof points to demonstrate that outcomes arising out of using the digital twins far outweighs the challenges in creating them.

Implementation impediments of Digital Twins

While the positive impact Digital twins can create is a given, there are still some challenges that needs resolution:

  • Privacy and security
  • Consent management and ethical sharing of data within the ecosystem including management of patient records
  • Infrastructure investments to create digital twins – platform / componentised architecture / cloud deployment should help. Business models will have to be put in place to ensure equitable share for multi users
  • Competency building in creating and deploying digital twins

To sum it all, the future looks extremely promising for this technology. Its labelled as one of the “Exponential technologies” we are dealing with – the output is disproportionally large comped to the given inputs. Experts predict a huge growth – they talk about this market growing at 30% to reach USD 19 Billion by 2022. North America and Europe are predicted to be the biggest consumers of this technology.

References: solution testing for future/Digital Twins in Healthcare

Rise of the digital twin: How Healthcare can benefit – Dr Henk van Houten

Digital twins for IoT applications, Oracle

Origins of the Digital twin concept, Florida Institute of Technology

Rise of the digital twin: Why the enterprise needs to take notice, Charlie Osborne

Digital twin technology and use cases and how to build them, Gilberto Valzania

Leave a Reply