It is a United Nations Sustainable Development Goal to achieve universal health coverage with access to quality healthcare for all. Our network plans to evaluate the contribution to this goal of mobile consulting (mConsulting). This is when patients consult with health providers about their health using digital communication. Our concern is remote, marginalised communities in Africa that have difficulty accessing quality health care. The digital infrastructure of Africa is its best infrastructure - much better than the roads, and most people own a mobile phone. We want to test whether using digital infrastructure for mConsulting improves access to quality healthcare for remote, marginalised communities and whether this is sustainable. mConsulting needs to be affordable to the community and for providers. However, improved healthcare can improve the health of the community and so increase economic activity and use of mConsulting can stimulate investment in digital infrastructure benefiting the community. Commercial companies are delivering mConsulting services in Africa. Currently they target urban communities but could extend their reach to remote communities. In addition to good mobile signal and sustainable business models they need community acceptance and integration with local providers for certain diagnostic tests and treatments. Existing health services (public or private) can add mConsulting to their services e.g. a health worker using a mobile phone for consulting. This needs planning to ensure professional standards and patient acceptability. We are academics/researchers, mConsulting providers and policy organisations. Four of the academic/research teams (Kenya, Nigeria, Tanzania and UK) have collaborated on research and research capacity building for ten years. We have extended our team to further organisations in our countries and in Uganda and Rwanda. Our expertise includes, technical, medical, nursing, education, social and behavioural science, health systems, economics and epidemiology. We aim to evaluate the impact of mConsulting on healthcare access and health outcomes for remote marginalised communities and explore how it can be optimally delivered. We will do this in varied contexts of East and West Africa so we learn what works well (or not) in different places, with different histories, policies and health systems. Our results will be relevant to diverse settings across Africa. To do this we will develop a research proposal for funding. We will first use the seed network funding to: 1. Extend and consolidate our networks to include all relevant and necessary people/organisations; 2. Work with remote community representatives, local healthcare providers, mConsulting providers, policy makers (and telecommunication providers where needed) to collaboratively identify plans for mConsulting including challenges to be overcome before implementation and evaluation; 3. Explore innovative ways of working across commercial, research and policy sectors to build research capacity and create opportunities for exchange. We expect our follow-on research will evaluate mConsulting for primary care, for certain types of health problems e.g. acute conditions, long-term conditions, child and maternal health, mental health. Our choice will depend on what is priority for the communities. Our research objectives are to: I) Evaluate whether mConsulting results in change in community access to healthcare and in measures of health outcomes for selected tracer conditions (e.g. blood pressure for hypertension, patient reported symptoms for depression); II) Evaluate what aspects of mConsulting work well (or not), where, when and for whom. We will observe, interview and collect activity data; III) Identify contextual factors that need to change to ensure scalability of mConsulting (e.g. professional training, regulations, financing).

Society is battling with an explosion of health conditions that need long-term management. These chronic conditions occur at all ages: UK children have some of the world's highest levels of both asthma and type 1 diabetes and, with a third of the UK's school children leaving primary education obese, there are huge concerns over type 2 diabetes at all ages; in any year, working age men and women in the UK have a 12% chance of a diagnosed mental health issue such as anxiety, depression and post-natal depression; conditions including dementia, Parkinson's disease and frailty are rapidly increasing in later years. Low-cost, connected, digital technologies are increasingly seen as vital to the understanding, prevention, diagnosis and management of these conditions for months and years in the community. These digital technologies, such as smartphone apps, wearables, blood sugar monitors - and a near future of Internet of Things (IoT) devices such as smart home systems (e.g. Echo), smart meters and connected appliances - offer an unprecedented opportunity to monitor a patient's condition within their community. With the data processed by artificial intelligence they will deliver decision support to health and care professionals; predict or detect a patient's symptoms worsening; support independent living; deliver behavioural and even pharmaceutical interventions; and allow the efficacy of treatments to be monitored. This cannot be business as usual for doctoral education since a digital health technology is likely to require a highly multidisciplinary understanding of technologies spanning software engineering, microelectronics, data communication, signal processing, machine learning and visualisation. Achieving actual patient benefit requires user-centred/driven design, a broad understanding of health and care, psychology, physiology, ethics, regulation, health economics and the design of clinical trials. To meet the challenge and seize the opportunity, the UK needs to nurture leadership that will span this hugely multidisciplinary space - combining technological depth with broad appreciation of the health landscape; empathy with the patient's needs with an eye to business models that underpin adoption; ambition to accelerate innovation with a principled commitment to ethics, inclusivity, regulation, data security and privacy. The opportunity and the challenge for this Centre for Doctoral Training (CDT) in Digital Health and Care is to be bigger than the sum of its parts; to physically co-locate a cohort of students from Engineering & Computer Sciences and Health & Life Sciences; to bridge the disciplinary gaps, work with key external partners, foster better understandings and activate peer-to-peer learning within the cohort itself. Bristol is the perfect place to train future leaders at this disciplinary interface, building on £30M of digital health research at the University since 2013. Our proposed CDT will develop team-players with the skills to work effectively with experts from other disciplines, with patients and with the public. In a space where issues of trust, privacy, transparency, accountability and inclusion are absolutely fundamental, the CDT will not only embrace Responsible Innovation but influence and lead best practice nationally and internationally. The CDT will build on a variety of established relationships; with small and medium sized businesses, technology companies, big pharmaceutical companies, charities, universities, one of the UK's largest public science centres (WeTheCurious), Bristol City Council, and with the public. This CDT is therefore envisaged as a multidisciplinary community of students and academics that will create exciting research projects and will build networks of individuals across academia, industry and the NHS at all levels. It will sow the seeds of future collaborative research and of commercialisation activities.

The CDT will train the next generation of leaders in statistics and statistical machine learning, who will be able to develop widely-applicable novel methodology and theory, as well as create application-specific methods, leading to breakthroughs in real-world problems in government, medicine, industry and science. The research will focus on the development of applicable modern statistical theory and methods as well as on the underpinnings of statistical machine learning. The research will be strongly linked to applications. There is an urgent national need for graduates from this CDT. Large volumes of complicated data are now routinely collected in all sectors of society, encompassing electronic health records, massive scientific datasets, governmental data, and data collected through the advent of the digital economy. The underpinning techniques for exploiting these data come from statistics and machine learning. Exploiting such data is crucial for future UK prosperity. However, several reports from government and learned societies have identified a lack of individuals able to exploit this data. In many situations, existing methodology is insufficient. Off-the-shelf approaches may be misleading due to a lack of reproducibility or sampling biases which they do not correct. Furthermore, understanding the underlying mechanisms is often desired: scientifically valid, interpretable and reproducible results are needed to understand scientific phenomena and to justify decisions, particularly those affecting individuals. Bespoke, model-based statistical methods are needed, that may need to be blended with statistical machine learning approaches to deal with large data. Individuals that can fulfill these more sophisticated demands are doctoral level graduates in statistics who are well versed in the foundations of machine learning. Yet the UK only graduates a small number of statistics PhDs per year, and many of these graduates will not have been exposed to machine learning. The Centre will bring together Imperial and Oxford, two top statistics groups, as equal partners, offering an exceptional training environment and the direct involvement of absolute research leaders in their fields. The supervisor pool will include outstanding researchers in statistical methodology and theory as well as in statistical machine learning. We will use innovative and student-led teaching, focussing on PhD-level training. Teaching cuts across years and thus creates strong cohort cohesion not just within a year group but also between year groups. We will link theoretical advances to application areas through partner interactions as well as through a placement of students with users of statistics. The CDT has a large number of high profile partners that helped shape our application priority areas (digital economy, medicine, engineering, public health, science) and that will co-fund and co-supervise PhD students, as well as co-deliver teaching elements.