Find out more about our Academic Medical Centre and efforts in Academic Medicine
Academic Medicine Executive Committee (AM EXCO)
Find out more about what JOAM do to support AM initiatives
Find out more about the Office of Duke-NUS Affairs and Study Trip to Duke Durham
Guidelines, forms, and templates for Academic Medicine.
Singapore, 17 July 2023 – SingHealth is expanding the use of digital twin1 technology to deliver better care for patients through strengthening surveillance of disease outbreaks, redesigning workflow in healthcare facilities, and better healthcare facility planning. The implementation of a “4 Dimensional Disease Outbreak Surveillance System” (4D-DOSS) aims to unlock different possible applications in healthcare settings here, including near real-time monitoring, analysis, prediction and simulation of disease outbreaks and beyond. This follows the success of 3D-DOSS test projects that have been ongoing since 20202.
Challenges in Infectious Diseases Landscape
2 The rapidly changing nature of the infectious diseases landscape presents challenges to existing healthcare systems and processes. At present, hospitals have limited capabilities for the early detection of fast-moving disease outbreaks. Current processes of analysing outbreaks in hospitals rely largely on manual extractions of data with 24 to 36-hour latency and additional time required for the processing of data. It is also challenging to manually analyse spatial relationships and distances in a timely manner. Such limitations impact the tracking and control of transmissible infectious diseases.
3 Digital twin technology uses advanced spatial mapping platforms and leverages existing healthcare data systems to develop a ‘living’ digital replica or ‘twin’ of a space or system. Such spatial systems can be beneficial for infectious disease surveillance because tracking of these diseases within complex healthcare environments requires data to be represented in space and time, to map out contact networks3.
Positive Outcomes from 3D-DOSS Test Projects
4 Effective patient infectious disease surveillance involves the processing of multiple types of data such as patient symptoms, movement, locations (e.g. bed/room/ward positions, where patients were sited in relation to heating, ventilation, and air-conditioning, plumbing and sanitation elements etc.), as well as results of relevant laboratory and radiological tests (e.g. COVID-19, RV-16, microorganisms, etc.).
5 Since 2020, SingHealth has been developing a disease outbreak surveillance system to detect outbreaks of infectious diseases. The 3D-DOSS integrated anonymised patient data onto digital replicas of the Singapore General Hospital’s (SGH) physical spaces which allowed for a number of applications.
6 Through the digital twins of SGH, staff are able to visualise and assess disease spread across time and distance, detect infection clusters in test data, and predict the risk of future infection. The system is also able to efficiently produce reports of exposed contacts – key information required for contact tracing efforts – to effectively identify possible infectious disease clusters. This saves man-hours required for manual data collation, as well as cleaning and analysis of data. For instance, the 3D-DOSS system was able to detect an actual cluster of influenza patients, and a list of primary and secondary contacts with a COVID-positive worker. In addition, it allows for in-depth analysis that can shed light on the areas of the hospital or patient cohorts at greater risk of infection transmission. A review of the use of the 3D-DOSS at SGH was recently published in
Mayo Clinic Proceedings: Digital Health4.
Possibilities of 4D-DOSS
7 Dr Indumathi Venkatachalam, Senior Consultant, Infection Prevention and Epidemiology, SGH and Principal Investigator of the DOSS team, said, “The findings of the 3D-DOSS test projects are encouraging and showed that there is potential for real-life applications. With the model, the hospital will be able to implement a system to alert and trigger infection prevention measures in a timely manner when certain set thresholds are reached.”
8 SingHealth is now expanding the use of digital twin technology in the form of 4D-DOSS, which builds on the success of the 3D-DOSS project. The system will be integrated with data source systems such as clinical data and bed management system (BMS), and is expected to be ready by July 2024. 4D-DOSS aims to unlock different possible applications in healthcare settings here such as
real-time monitoring, analysis, and simulation of disease outbreaks. This project is made possible with funding and support from SGH, the Ministry of Health and SingHealth.
9 “Developing surveillance systems with digital twins of our hospitals’ spaces holds much promise in disease surveillance to enable accurate prediction and earlier interventions for infectious disease outbreaks. It will also allow us to be more prepared for the emergence of ‘Disease X’ and anticipate ways to mitigate its spread,” added Dr Indumathi.
Potential Applications Beyond Infectious Disease Surveillance
10 Ultimately, SingHealth aims to scale the use of digital twin technology across SingHealth’s institutions, with applications going beyond infectious disease surveillance. For example, Changi General Hospital (CGH) is embarking on simulation modelling in a digital twin model to complement real-time situational monitoring at its Emergency Department. This could be used to forecast needs for staffing and resources in situations such as mass casualty scenarios, and can guide workflow redesign to meet evolving needs. Digital twin technology is also being used in the planning of healthcare facilities at the future Eastern General Hospital at Bedok North, where a digital replica of the planned hospital can incorporate building information modeling to enable accurate space planning, taking into account different scenarios simulated with another hospital’s actual data.
11 Clinical Associate Professor Chow Wei En, Chief Data and Digital Officer, CGH and co-Principal Investigator of the DOSS team said, “The use of 4D-DOSS will allow detailed infrastructure and an automated patient-level data flow to the replica models for deeper analysis and detailed planning. In addition, the inclusion of operational and clinical workflows can provide opportunities to develop clinical modelling and value-based care as well as optimise patient flow to improve operational efficiency and streamline the patient journey.”
12 Ms Lee Chen Ee, Group Director, Innovation and Transformation, SingHealth, and Co-Chair of the SingHealth Duke-NUS Academic Medicine Innovation Institute said, “The use of digital twin technology is fairly nascent in the healthcare sector, especially in Singapore. We are very excited by the possibility of employing the digital twin technologies to enhance different aspects of healthcare – resource optimisation, response to disease outbreak, anticipate future needs in facilities planning, so as to be nimble to unexpected situations and more effective in care delivery. SingHealth is glad to work with our partners to harness breakthrough technological developments so as to open up new possibilities for the healthcare sector.”
1A digital twin is a virtual representation of real-world entities and processes, synchronised at a specified frequency and fidelity. Source: https://www.digitaltwinconsortium.org/hot-topics/the-definition-of-a-digital-twin/
23D-DOSS was a stand-alone system developed using digital twin technology and its performance was assessed using selected and typically historical surveillance and outbreak data.
34D-DOSS is the next phase of the project whereby 3D-DOSS will be integrated into healthcare data systems in order to automate data flow and obtain near real-time output. Contact network captures quantitative information such as a person’s position, proximity, frequency of contacts, duration of contacts between people within a certain period of time.
4Venkatachalam et al (2023). Three-Dimensional Disease Outbreak Surveillance System in a Tertiary Hospital in Singapore: A Proof of Concept. Mayo Clinic Proceedings: Digital Health. https://mcpdigitalhealth.org/article/S2949-7612(23)00026-3/fulltext