Respiratory disease is the third biggest cause of death in England, causing on average 68,000 deaths per year between 2013 and 2019, with an estimated cost of £9.9 billion per year. This resulted in over 200,000 emergency hospital admissions in 2021-22, with this number continuing to rise. The effect of this is most apparent during winter, when respiratory-related admissions double in number due to 'winter pressures', whilst the health service becomes overloaded and preventable deaths occur. There is room for improvement and new and emerging technologies should be seriously considered. Digital twins are one such technology that has been used for several years in the engineering field. Digital twinning simulates a physical machine, such as a car, by using algorithms (i.e., mathematical or artificial intelligence models) and data obtained from physical machines. A person using the digital twin can then monitor and improve the car by anticipating problems before they happen. Although digital twins have been applied to healthcare before, their use has been restricted to a narrow scope due to limited data, evaluation of hypothetical scenarios, and the fact they are underpinned by non-changing artificial intelligence models, which are trained once, but cannot adapt to new situations. Our previous work with digital twins leads us to believe that a self-learning approach would have considerable advantages if applied to respiratory-related admissions. Extending digital twins in this way would mean they are able to a) learn and improve from limited data and feedback from the user; b) consider how patients and their environment change over time; c) identify and correct socio-economic biases ethically; and d) ultimately be personalized to individual patients. We propose to design self-learning health digital twins which will support human judgement in clinical decision making, by prioritising patients and providing information on the general or specific condition of the patient, and by identifying factors which may lead to respiratory disease or deterioration earlier, thus helping to determine any steps that can be taken to improve the situation. The acute and varied nature of patients with respiratory disease makes them ideal candidates for health digital twin applications. Hence, this project not only considers how best to co-design clinical decision support tools with patients at the centre of clinical practice, but it breaks new ground, by creating feedback loops and corrective processes against bias, which are required to systematically evaluate, validate, and improve clinical decision support at the necessary speed, and in real-time for patients. In this project, we will design state-of-the-art responsible AI methods with technical innovation, which facilitates the integration of multi-modal data sources and the development of surrogate models for gaining the necessary insight. A self-learning and self-adaptive health digital twin model will be developed based on the responsible AI methods with a clinical decision support tool to offer services and care at the personalised level. A demonstrator system of our health digital twin will be co-designed to suitably evaluate and validate the dependability of our proposed health digital twin in a clinical setting based on real-world case studies, which will be used to consider our clinical questions with continuous feedback to help improve the underlying models. Through this unique and timely project led by a multi-disciplinary team, we will break new ground in clinical care and decision making, whilst significantly advancing the case for the development and implementation of self-learning health digital twins in clinical practice.

Autonomous systems promise to improve our lives; driverless trains and robotic cleaners are examples of autonomous systems that are already among us and work well within confined environments. It is time we work to ensure developers can design trustworthy autonomous systems for dynamic environments and provide evidence of their trustworthiness. Due to the complexity of autonomous systems, typically involving AI components, low-level hardware control, and sophisticated interactions with humans and the uncertain environment, evidence of any nature requires efforts from a variety of disciplines. To tackle this challenge, we gathered consortium of experts on AI, robotics, human-computer interaction, systems and software engineering, and testing. Together, we will establish the foundations and techniques for verification of properties of autonomous systems to inform designs, provide evidence of key properties, and guide monitoring after deployment. Currently, verifiability is hampered by several issues: difficulties to understand how evidence provided by techniques that focus on individual aspects of a system (control engineering, AI, or human interaction, for example) compose to provide evidence for the system as whole; difficulties of communication between stakeholders that use different languages and practices in their disciplines; difficulties in dealing with advanced concepts in AI, control and hardware design, software for critical systems; and others. As a consequence, autonomous systems are often developed using advanced engineering techniques, but outdated approaches to verification. We propose a creative programme of work that will enable fundamental changes to the current state of the art and of practice. We will define a mathematical framework that enables a common understanding of the diverse practices and concepts involved in verification of autonomy. Our framework will provide the mathematical underpinning, required by any engineering effort, to accommodate the notations used by the various disciplines. With this common understanding, we will justify translations between languages, compositions of artefacts (engineering models, tests, simulations, and so on) defined in different languages, and system-level inferences from verifications of components. With such a rich foundation and wealth of results, we will transform the state of practice. Currently, developers build systems from scratch, or reusing components without any evidence of their operational conditions. Resulting systems are deployed in constrained conditions (reduced speed or contained environment, for example) or offered for deployment at the user's own risk. Instead, we envisage the future availability of a store of verified autonomous systems and components. In such a future, in the store, users will find not just system implementations, but also evidence of their operational conditions and expected behaviour (engineering models, mathematical results, tests, and so on). When a developer checks in a product, the store will require all these artefacts, described in well understood languages, and will automatically verify the evidence of trustworthiness. Developers will also be able to check in components for other developers; equally, they will be accompanied by evidence required to permit confidence in their use. In this changed world, users will buy applications with clear guarantees of their operational requirements and profile. Users will also be able to ask for verification of adequacy for customised platforms and environment, for example. Verification is no longer an issue. Working with the EPSRC TAS Hub and other nodes, and our extensive range of academic and industrial partners, we will collaborate to ensure that the notations, verification techniques, and properties, that we consider, contribute to our common agenda to bring autonomy to our everyday lives.

Autonomous systems promise to improve our lives; driverless trains and robotic cleaners are examples of autonomous systems that are already among us and work well within confined environments. It is time we work to ensure developers can design trustworthy autonomous systems for dynamic environments and provide evidence of their trustworthiness. Due to the complexity of autonomous systems, typically involving AI components, low-level hardware control, and sophisticated interactions with humans and the uncertain environment, evidence of any nature requires efforts from a variety of disciplines. To tackle this challenge, we gathered consortium of experts on AI, robotics, human-computer interaction, systems and software engineering, and testing. Together, we will establish the foundations and techniques for verification of properties of autonomous systems to inform designs, provide evidence of key properties, and guide monitoring after deployment. Currently, verifiability is hampered by several issues: difficulties to understand how evidence provided by techniques that focus on individual aspects of a system (control engineering, AI, or human interaction, for example) compose to provide evidence for the system as whole; difficulties of communication between stakeholders that use different languages and practices in their disciplines; difficulties in dealing with advanced concepts in AI, control and hardware design, software for critical systems; and others. As a consequence, autonomous systems are often developed using advanced engineering techniques, but outdated approaches to verification. We propose a creative programme of work that will enable fundamental changes to the current state of the art and of practice. We will define a mathematical framework that enables a common understanding of the diverse practices and concepts involved in verification of autonomy. Our framework will provide the mathematical underpinning, required by any engineering effort, to accommodate the notations used by the various disciplines. With this common understanding, we will justify translations between languages, compositions of artefacts (engineering models, tests, simulations, and so on) defined in different languages, and system-level inferences from verifications of components. With such a rich foundation and wealth of results, we will transform the state of practice. Currently, developers build systems from scratch, or reusing components without any evidence of their operational conditions. Resulting systems are deployed in constrained conditions (reduced speed or contained environment, for example) or offered for deployment at the user's own risk. Instead, we envisage the future availability of a store of verified autonomous systems and components. In such a future, in the store, users will find not just system implementations, but also evidence of their operational conditions and expected behaviour (engineering models, mathematical results, tests, and so on). When a developer checks in a product, the store will require all these artefacts, described in well understood languages, and will automatically verify the evidence of trustworthiness. Developers will also be able to check in components for other developers; equally, they will be accompanied by evidence required to permit confidence in their use. In this changed world, users will buy applications with clear guarantees of their operational requirements and profile. Users will also be able to ask for verification of adequacy for customised platforms and environment, for example. Verification is no longer an issue. Working with the EPSRC TAS Hub and other nodes, and our extensive range of academic and industrial partners, we will collaborate to ensure that the notations, verification techniques, and properties, that we consider, contribute to our common agenda to bring autonomy to our everyday lives.