Intracerebral haemorrhage (ICH) causes one quarter of strokes worldwide. Over a third of people with ICH die within a month, and survivors are often disabled. In the UK, at least one in twenty ICH survivors has a stroke, heart attack or dies each year. With such a devastating disease, prevention is vital. To prevent ICH happening, we need to understand the differences between those who have the disease and those who do not. The strongest risk factors for ICH are high blood pressure and high alcohol intake, but they are both very common in the general population. Many other medical conditions are linked to ICH, but the link is much less strong. Most people with ICH have more than one risk factor, and lots of other medical conditions. Some medical conditions may group together in particular people, and increase risk of ICH, or poor outcome after ICH. OPPORTUNITY Because ICH is not common, most studies have been small and studied one risk factor at a time. We do not know how having multiple medical conditions changes the risk of ICH, its outcome and treatment, or if specific combinations of medical conditions are particularly important. Recent advances in health data can improve research into multiple medical conditions. Routinely-collected healthcare data is available securely to researchers in Scotland. The UK Biobank is a research study of half a million people, with brain scans and genetic data. Data from large clinical trials can tell us how different types of people respond to treatments. OBJECTIVES The objective of this study is to understand how having multiple medical conditions affects risk of ICH, and outcome after ICH. This study has three parts: I plan to use machine learning to analyse large databases. I will identify groups of people with similar combinations of medical conditions. I will compare these groups, to see if there are differences in ICH occurrence, ICH appearance on brain scans, and the ongoing health of people after ICH. In an upcoming study testing aspirin after ICH, I will see whether having multiple medical conditions affects whether people choose to take part. I will examine if having multiple medical conditions affects how well people respond to treatment in clinical trials. BENEFITS The Chief Medical Officer for England, Professor Chris Whitty, has highlighted multiple medical conditions as a key area of research. Better understanding of multimorbidity in ICH could allow us to improve our understanding of the cause of disease, organise services to meet peoples' needs, and improve prevention and treatment. Furthermore, the project is a valuable opportunity for me, as an early-career researcher, to receive training in the fundamentals of epidemiology, medical statistics and machine learning, and to launch a career as a clinical academic.

UK policy is for safe, personalised maternity care. However, during COVID-19 tests and visits have been reduced in some places, and some women with worrying symptoms are not going to hospital. Other places are trying new solutions, including remote access technologies. Some Trusts have reduced community maternity services, including home and birthcentre births; barred birth companions in early labour; and separated mothers, babies, and partners during labour, and in neonatal units. There are reports of women giving birth at home without professional help, possibly due to fear of infection, or of family separation. In contrast, the Netherlands has a policy of increased community maternity services during COVID-19. We want to find out how best to provide care for mothers, babies, and partners during and after a pandemic. We will look at what documents and national leads say about service organisation in the UK and the Netherlands, and at women's and parents experiences. We will also look in detail at what happened in 8 UK Trusts during the pandemic. We will find out how their services have been organised during COVID-19, what parents and staff think, and what the outcomes are, including infections. We will then share the findings with key stakeholders to agree a final organisational model that can be used to ensure safe, personalised routine and crisis maternity care, now, and in future. This will include useful resources and links relating to innovative best practices that we find out about during the study.

In recent years, considerable effort has gone into defining "responsible" AI research and innovation. Though progress is tangible, many sectors still lack the tools and capabilities for operationalising and implementing ethical principles. Furthermore, many project teams also find it challenging to know how to achieve goals, such as fairness or explainability, and communicate that they have been realised to other stakeholders of affected users. If ignored, these gaps could hamper efforts to build public trust in AI technologies or amplify existing societal harms and inequalities caused by biased and non-transparent sociotechnical systems. The Trustworthy and Ethical Assurance for Digital Twins (TEA-DT) project will develop an existing open-source platform, known as the Trustworthy and Ethical Assurance (TEA) Platform, which has been designed to help users navigate the process of addressing the aforementioned challenges. The TEA platform helps users and project teams define, operationalise, and implement ethical principles as goals to be assured, and also provides means for communicating how these goals have been realised. It achieves this by guiding individuals and project teams to identify the relevant set of claims and evidence that justify their chosen ethical principles, using a participatory approach that can be embedded throughout a project's lifecycle. The output of the platform—a user-generated assurance case—can be co-designed and vetted by various stakeholders, fostering trust through open, clear, and accessible communication. The TEA platform consists of three main elements: 1) an online tool for crafting well-reasoned arguments about ethical goals, 2) user-friendly guidance to foster critical thinking among teams and organisations, and 3) a supportive community infrastructure for sharing and discussing best practices. Although the platform is designed for a wide range of applications, the TEA-DT project will specifically focus on digital twins—virtual duplicates that are closely coupled to their physical counterpart to enable access to data and insights that can improve and optimise the way their real-world versions operate. More specifically, the project team will carry out scoping research on the assurance of digital twins within three different contexts: health, natural environment, and infrastructure. Although digital twins promise vast societal benefit in these areas, the fact that they increasingly rely on various forms of AI and often operate in safety-critical settings, means that several challenges must be addressed to ensure their ethical and trustworthy development. For instance, in health, questions about data privacy and ownership arise; environmental applications must tackle bias and fairness issues, complicated by global scales and differing laws; and in infrastructure, technical challenges concerning uncertainty communication give rise to additional needs for transparency and explainability. In collaboration with key partners and stakeholders, the TEA-DT project will carry out scoping research to co-develop exemplary assurance cases and enhance the platform's features to make it more user-friendly and integrated into workflows. By committing to open research and community-building principles, the project aims to a) systematically share best practices and standards, b) make the operationalisation of ethical principles more accessible and inclusive, and c) integrate the project sustainably with existing networks and communities.

Our proposal aims to use secondary analysis to provide evidence for user-centred quality improvement in health and social care. It builds on two existing initiatives: 1. An archive of 3000 qualitative video and audio interviews on over 80 topics with users about their health and illness experiences held by the Health Experiences Research Group (HERG), University of Oxford (and disseminated publicly on www.healthtalkonline.org run by the DIPEx Charity) 2. Experience-Based Co-Design (EBCD), a participatory action research approach which actively involves service users in service design and has been implemented in over 60 care services in six different countries since being piloted in 2006. Past evaluations have shown it to be effective in achieving quality improvement and cultural change. Both initiatives include video-recorded in-depth interviews with people talking about their experiences. HERG interviews are nationally collected and wide-ranging, whereas EBCD interviews are collected locally with a more specific focus on 'touchpoints' - key interactions between users and services where quality improvements can be made - in each care setting. In EBCD analysis of these touchpoints is used to create a 'trigger' film which staff and users watch together to start a discussion about improving care locally, before setting up co-design working groups to plan and implement changes together. These two initiatives have already collaborated on a recent study for the National Institute for Health Research (NIHR) which demonstrated EBCD in two care pathways based on secondary analysis of HERG interviews rather than new local interviews worked just as well, saving time and cost. This provides a strong evidence base to propose further secondary analysis to support care organisations seeking to apply experience-based quality improvement in an affordable and timely way across more conditions. We will reanalyse ten of our existing interview collections. In each case the primary research question for the secondary analysis will be: What touchpoints do users identify in their experiences of care where quality could be improved? The HERG collections are generally focused around a particular condition or health topic. However, there is much material in the collections that could inform service settings and integration of care across sectors. Alongside the analysis for touchpoints in each condition, we will also ask: What are the touchpoints for a) outpatient care and b) interactions between health and social care across a range of different conditions which could be used to redesign services? The secondary analyses will involve a researcher going back to the full transcript collection to identify touchpoints. On healthtalkonline, we also have a set of lay summaries identifying key topics of importance to interview participants in each condition (though not specifically analysed for touchpoints). A key further empirical question to ask is therefore: What touchpoints would emerge from a re-analysis of the website summaries, compared to re-analysis of the full transcripts? Can further time savings be made in identifying touchpoints by this method or is too much lost in the process? We will also involve service users in the secondary analysis process, supporting them in analysing both selected transcripts and selected website summaries, and discussing with them similarities and differences in the touchpoints they identify compared to the social science researcher. We will disseminate findings from the secondary analysis in the form of a series of trigger films made in collaboration with the DIPEx Charity, using our existing video recordings to illistrate the touchpoints we identify, and make these available through both www.healthtalkonline.org and the Point of Care Foundation online EBCD toolkit. With the close and active support of NHS England our findings will have a clear route to impact on policy and practice

With a growing ageing population and changes in lifestyles, non-communicable diseases (NCD), e.g. heart disease, diabetes, and cancer, have become extremely prevalent in our society, and the situation is more challenging in UK compared to other developed countries. Population health monitoring is fundamental block for public health services, and profiling population-scale prevalence of multiple NCD across different regions (e.g., building the spatially fine-grained morbidity rate map) is one of the most important tasks. However, traditional public health data collection and prevalence profiling approaches, such as clinic-visit-based data integration and health surveys, are often very costly and time-consuming. This project proposes a novel paradigm, called compressive population health (CPH for short), to reduce the data collection cost during the profiling of prevalence to the maximum extent. The basic idea CPH is that a subset of areas is intelligently selected for data collection and population health profiling in the traditional way, while leveraging inherent data correlations to perform data inference for the rest of the areas. CPH is facilitated by the exploitation of the following types of inherent data correlations found by epidemiologists. (a) Intra-Disease Spatial Correlations. That is, regions are more similar in the prevalence rate of some diseases when they are neighbouring, or share certain common environmental, socioeconomic, and demographical attributes. (b) Inter-Disease Correlations. Multimorbidity, commonly defined as the co-presence of two or more chronic conditions, demonstrates that statistics for different types of disease may also correlate with each other. For example, regions with higher obesity rate are more likely to have higher rates of heart disease and cancers. In order to realize this idea, this project develops three technical work packages to accomplish the following technical goals: (1) Investigate and extract latent data correlations and further utilize them to build learning models for prevalence inference on the target geographical grids. (2) Design intelligent algorithms for selecting traditional-sensed areas for each disease with multi-objective optimization goals including cost, reliability, and latency. (3) Evaluate and interpret the inference results of prevalence rate to ensure the reliability and robustness of the approach. The proposed CPH is a novel solution to a public health data collection challenge enabled by data science and artificial intelligence. It opens the door for a disruptive population health monitoring paradigm with potential significant cost reductions for public health authorities. By closely working with partners from public health sector, including NHS England and Public Health at Warwickshire County Council, we will evaluate the feasibility of this approach based on multiple public health datasets together with relevant demographic/geographic statistics in the same regions.