The NHS Cervical Screening Programme (NHS CSP) has been hugely successful since introduction in 1998 in the UK. However, in 2018, screening rates were at a historical low, with screening rates down to 50% in some areas, especially in younger women & new mums, despite cervical cancer peak incidence occurring in this 25-35 year age group. The peak incidence of cervical cancer coincides with the time when women are having children. During pregnancy and the postnatal period, women have multiple interactions with healthcare professionals and discussions regarding screening for a range of conditions. Pregnancy provides an ideal opportunity to inform, educate and facilitate the uptake of cervical screening. In a previous quality improvement study, we improved the screening uptake rate in our local postnatal population by 8% with educational packages aimed at pregnant women and midwives. As part of this work we conducted a number of focus groups, seeking ideas from key stakeholders. One idea, generated by new mums, young women with cervical cancer, GPs and practice nurses, was that cervical screening should be performed at the 6-week postnatal check up. This check up is well-attended by women, & means that they do not have to find time a few weeks later to prioritise their own healthcare in a separate appointment. Finding time to attend appointments was a key limiting factor identified by new mums & women with cervical cancer. Another factor was a reluctance to have a vaginal examination, which urine self-testing might improve. Currently postnatal screening is performed after 12-weeks postnatal. This is on the basis of one study of conventional cervical screening ('Pap' smear), when cells from wooden slides were spread directly onto glass slides by the smear-taker. However, we now use liquid-based cytology (LBC), where cells collected on the cervical screening brush are transferred into a pot of special collection liquid, before being transferred to a slide in the lab, using specialist equipment. These LBC samples are much clearer and easier to examine under a microscope. This means that blood from periods or postnatal bleeding/discharge, called lochia, is less of a problem compared to old-style 'Pap' smears. We have also recently changed to primarily testing for high risk Human Papilloma Virus (HR HPV) on this LBC sample, with cytology only performed for those with HR HPV detected. However, despite the lack of evidence to support the current cervical screening schedule, this 12-week time-point remains, until we have data to support a change to combining cervical screening with the 6-week postnatal check up appointment. We will ask several questions, to help design the best future, much larger study that will be needed to confirm that a 6-week check is safe and improves screening uptake. 1. What are pregnant women and new mums' views on screening at the 6-week postnatal check? 2. What are pregnant women and new mums' views on self-testing at the 6-week postnatal check? 3. Will women attend for a 6-week cervical screening test in a feasibility study and, if they do, would they be willing to have a repeat test at 12-weeks to allow direct comparison? 4. Will it be feasible to randomise women individually to either 6- or 12-weeks tests, or would we need to design future studies differently, e.g by randomising screening times by GP practice or regionally? 5. How well does self-testing with urine samples compare with LBC samples in postnatal women? We hope these data will inform how to plan a larger study to test the effect of changing to 6-week postnatal testing within the NHS Cervical Screening Programme on the accuracy of testing and ability to prevent cervical cancer, and see whether this improves cervical screening rates in postnatal women.

Our Hub brings together a team of mathematicians, statisticians and clinicians with a range of industrial partners, patients and other stakeholders to focus on the development of new quantitative methods for applications to diagnosing and managing long-term health conditions such as diabetes and psychosis and combating antimicrobial infections such as sepsis and bronchiectasis. This approach is underpinned by the world-leading expertise in diabetes, microbial communities, medical mycology and mental health concentrated at the University of Exeter. It uses the breadth of theoretical and methodological expertise of the Hub's team to give innovative approaches to both research and translational aspects. Although quantitative modelling is a well-established tool used in the fields of economics and finance, cutting-edge quantitative analysis has only recently become possible in health care. However, up to now it has been restricted to health economics in the context of healthcare services and systems management. Applications to develop future therapies, optimising treatments and improving community health and care are in its infancy. This is due to a number of challenges from both mathematical (methodological) as well as clinical and patients' perspectives. Our Hub approach will allow us to develop novel statistical and mathematical methodologies of relevance to our clinical and industrial partners, informed by relevant patient groups. Building this new generation of quantitative models requires that we advance our mathematical understanding of the effective network interaction and emergent patterns of health and disease. Clinical translation of mathematical and statistical advances necessitates that we further develop robust uncertainty quantification methodology for novel therapy, treatment or intervention prediction and evaluation. NHS long-term planning aspires to deliver healthcare that is more personalised and patient centred, more focused on prevention, and more likely to be delivered in the community, out of hospital. Our Hub will contribute to this through developing mathematical and statistical tools needed to inform clinical decision making on a patient-by-patient basis. The basis of this approach is quantitative patient-specific mathematical models, the parameters of which are determined directly from individual patient's data. As an example of this, our recent research in the field of mental health has revealed that movement signatures could be used to distinguish between healthy subjects and patients with schizophrenia. This hypothesis was tested in a cohort of people with schizophrenia and we developed a quantitative analysis pipe line allowing for classification of individuals as healthy or patients. The features used for classification involving data-driven models of individual movement properties as well as measures of coordination with a virtual partner were proposed as a novel biomarker of social phobias. To validate this in an NHS setting, we have recently carried out a feasibility study in collaboration with the early intervention for psychosis teams in Devon Partnership Mental Health Trust. The success of this study could significantly advance the early detection of psychosis by enabling diagnosis using novel markers that are easily measured and analysed and improve accuracy of diagnosis. Indeed, personalised quantitative models hold the promise for transforming prognosis, diagnosis and treatment of a wide range of clinical conditions. For example, in diabetes where a range of treatment options exist, identifying the optimal medication, and the pattern of its delivery, based upon the profile of the individual will enable us to maximise efficacy, whilst minimising unwanted side effects.

AI and Machine Learning often address challenges that are relatively monolithic in nature: determine the safest route for an autonomous car; translate a document from English to French; analyse a medical image to detect a cancer; answer questions about a difficult topic. These kinds of challenge are very important and worthwhile targets for AI research. However, an alternative set of challenges exist that are more *collective* in nature and that unfold in *real time*: - help minimise the impact of a pandemic sweeping through a population of people by informing the coordination of local and national testing, social distancing and vaccination interventions; - predict and then monitor the extent and severity of an extreme weather event using multiple real-time physical and social data streams; - anticipate and prevent a stock market crash caused by the interactions between many automated trading agents each following its own trading algorithm; - derive city-wide patterns of changing mobility from high-frequency time series data and use these patterns to drive city planning decisions that maximise liveability and sustainability in the future city; - assist populations of people with type 2 diabetes to avoid acute episodes and hospitalisation by identifying patterns in their pooled disease trajectories while preserving their privacy and anonymity. Developing AI systems for these types of problem presents unique challenges: extracting reliable and informative patterns from multiple overlapping and interacting data streams; identifying and controlling for inherent biases within the data; determining the local interventions that can allow smart agents to influence collective systems in a positive way; developing privacy preserving machine learning and advancing ethical best practices for collective AI; embedding novel machine learning and AI in portals, devices and tools that can be used transparently and successfully by different types of user. The AI for Collective Intelligence (AI4CI) Hub will address these challenges for AI in the context of critically important real world use cases (cities, pandemics, health care, environment and finance) working with key stakeholder partners from each sector. In addition to significantly advancing applied AI research for collective intelligence, the AI4CI Hub will also work to build *community* in this research area, linking together academic research groups across the UK with each other and with key industry, government and public sector organisations, and to build *capability* by developing and releasing open access training materials, tools, demonstrator systems and best practice guidance, and by supporting the career development of early and mid-career researchers both within academia and beyond. The AI for Collective Intelligence Hub will be a centre of gravity for a nation-wide research effort applying new AI to collective systems.

The LEAP Digital Health Hub is a partnership of the South West's leading Universities, more than 20 supporting companies nationally, many NHS Trusts & Health Boards, 4 social care organisations, the region's Local Authorities, the West of England Academic Health Science Network (AHSN), the award-winning business incubator SETsquared and Health Data Research UK (HDRUK). The 50+ partners that shaped this bid ranged from the research director for a provider of residential care homes, to a chief clinical information officer working in an intensive care unit; from the founder of a femtech startup to the head of the healthcare analytics team for a multinational consulting firm. In workshops through June and July 2022 they told us that Digital Health is as much about design and user experience as health data analysis; it is motivated by patient benefit but must also consider viable business models for industry. All Hub partners will have access to dedicated physical office space in central Bristol alongside the EPSRC Centre for Doctoral Training (CDT) in Digital Health and Care. There, they will train, network and research together across disciplines and sectors. They will engage with partners across the UK- and beyond. Recognising that UK breakthroughs in Digital Health may be equally (or more) impactful abroad, the Hub's new "Global Digital Health Network" links the Hub to Digital Health expertise from the US, China, India, Nigeria and Australia (sections B1.2, B5). The Hub's unique Skills and Knowledge Programme is designed to address the professional training needs of industry, health and social care providers and academia within the two Themes of Transforming Health & Care Beyond the Hospital and Optimising Disease Prediction, Diagnosis & Intervention. This is proposed to be the world's largest Digital Health taught programme. The Hub's Fellowship programme will comprise 5 different schemes to develop future leaders, within not only academia, industry and the health/care sector, but also within the community - as patients or informal carers. The Hub's Research programme focusses on pre-competitive research within the Hub's two thematic areas of Transforming Health and Care Beyond the Hospital and Optimising Disease Prediction, Diagnosis and Intervention. The Hub will add value by surfacing health priorities from its partner health and social care organisations, working with the West of England AHSN and also with Hub members such as Chief Nursing Information Officers, with charities, social care providers, patient and community groups.