Configuration Testing of an Artificial Pancreas System Using a Digital Twin

18 Pages Posted: 29 Feb 2024

See all articles by Richard Somers

Richard Somers

University of Sheffield

Neil Walkinshaw

University of Sheffield

Robert Hierons

University of Sheffield

Jackie Elliott

University of Sheffield

Ahmed Iqbal

Sheffield Teaching Hospitals NHS Foundation Trust

Emma Walkinshaw

Sheffield Teaching Hospitals NHS Foundation Trust

Abstract

The recent spread of wearable medical devices has improved the quality of life of people with medical conditions. Traditionally, users configure these systems using physical trials, putting themselves in potentially dangerous scenarios. Digital twins present an opportunity to perform configuration testing in simulated environments, reducing the potential risk. In this paper, we perform an evaluative case study to assess the capabilities of a digital twin in the configuration testing of an artificial pancreas system (APS) control algorithm. These systems regulate the blood glucose levels in people with type 1 diabetes mellitus (T1DM), which if misconfigured, can cause severe hypoglycaemia or hyperglycaemia, which can be life-threatening. We tested the OpenAPS control algorithm against 156 people's clinical data. We found that our digital twin provided an accurately simulated environment to perform configuration testing and was capable of predicting blood glucose-insulin behaviour. We were able to evaluate different APS configurations, identifying a potentially unsafe configuration without the risks associated with a physical trial. We uncovered how modelling clinical data is not always consistent, which could lead to misinterpretations in configuration testing, and the challenges associated with test reliability when modelling human body dynamic uncertainty.

Note:

Funding Information: Neil Walkinshaw and Rob M. Hierons are funded by the UKRI, United Kingdom CITCOM grant EP/T030526/1. Hierons is funded by the UKRI, United Kingdom grants EP/R025134/2, EP/V026801/2.

Conflict of Interests: There are no competing interests to declare.

Ethical Approval: Ethics approval for this study was approved by the University of Sheffield Ethics Committee. Since this study used pre-anonymised volunteered data from a public open-source data source (APS Data Commons), the committee accepted this ethics approval as a self-declaration with a comprehensive data management plan.

Keywords: Configuration, Digital twins, Insulin pumps, Medical devices, Modelling, Software testing

Suggested Citation

Somers, Richard and Walkinshaw, Neil and Hierons, Robert and Elliott, Jackie and Iqbal, Ahmed and Walkinshaw, Emma, Configuration Testing of an Artificial Pancreas System Using a Digital Twin. Available at SSRN: https://ssrn.com/abstract=4732706 or http://dx.doi.org/10.2139/ssrn.4732706

Richard Somers (Contact Author)

University of Sheffield ( email )

17 Mappin Street
Sheffield, S1 4DT
United Kingdom

Neil Walkinshaw

University of Sheffield ( email )

17 Mappin Street
Sheffield, S1 4DT
United Kingdom

Robert Hierons

University of Sheffield ( email )

17 Mappin Street
Sheffield, S1 4DT
United Kingdom

Jackie Elliott

University of Sheffield ( email )

United Kingdom

Ahmed Iqbal

Sheffield Teaching Hospitals NHS Foundation Trust ( email )

Robert Hadfield Building
Northern General Hospital
Sheffield, S5 7AU
United Kingdom

Emma Walkinshaw

Sheffield Teaching Hospitals NHS Foundation Trust ( email )

Robert Hadfield Building
Northern General Hospital
Sheffield, S5 7AU
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
60
Abstract Views
139
Rank
666,587
PlumX Metrics