This project aims to develop, evaluate and deploy a new technology that will improve the way patients with long-term health conditions receive care. The project is led by Ufonia, a UK company that specialises in delivering automated clinical conversations over the telephone. Ufonia has already developed an artificial intelligence (AI) software called Dora that is used at 13 NHS sites to automate appointments for patients undergoing routine surgery. Currently, Dora relies on a form of AI that can only follow set rules. Recent advancements in AI technology mean that large language models (LLM) can now be trained to have **more empathetic, personalised clinical conversations** with patients. This project will work with doctors, researchers and patients to build on Ufonia's existing technology platform for voice conversations and replace Dora's existing core language model with a **LLM model trained specifically for empathetic, personalised conversations.** This will be particularly helpful for patients with long-term conditions, as it will allow them to have regular check-ins and consultations without needing to visit the hospital in person. This will improve outcomes for patients and reduce the strain on healthcare systems. In addition to the words used during a clinical conversation, the voice style and flow is vital to **show empathy**. We will also work with the University of Newcastle to develop a linguistic approach called the CADENCE model, which will improve the **voice cues of empathy in autonomous conversation**s. One of the main challenges in using AI in healthcare is **ensuring that it is safe and effective**. To address this, the project will collaborate with the University of York's Centre for the Safety Assurance of AI-enabled Autonomous Systems (SAINTS) to develop a framework to ensure the clinical safety of the AI conversations. Specifically, this work will enable Dora to screen for patients at high risk of repeat bone fractures, and long term monitoring of patients with osteoporosis. The project will culminate in a clinical study at University College London Hospitals NHS Foundation Trust's Rheumatology Department. The results from this study will provide evidence for wider use of the technology and its potential expansion to other long-term conditions. This project has the potential to greatly improve the way patients with long-term conditions receive care. By automating regular interactions and implementing AI technology, patients will have more convenient access to the care they need, while healthcare professionals can focus on those who require their expertise the most.

Ufonia are seeking the SBRI grant in order to develop their technology of Artificial Intelligence (AI) delivered telephone conversations with patients to referrals to St George's University NHS hospital's Head and Neck cancer department. Ufonia proposes the triage of urgent suspected head and neck cancer referrals with an autonomous AI delivered telephone conversation using a validated head and neck cancer risk calculator, thereby reducing the need for many face-to-face consultations. Head and neck cancer rates are increasing with an increasing number of suspected cancer referrals seen each year. Alongside this, the COVID-19 pandemic has demanded a re-rationalisation of healthcare services and required profound changes in the way we deliver care in order to protect patients and staff. Head and Neck (H&N) surgeons who traditionally triage these patients are uniquely vulnerable to the disease through their close interaction with virus reservoirs in the nose and throat. This innovation therefore has the potential to benefit patients, clinicians, NHS trusts and society as a whole, with a primary focus on COVID-19 recovery and sustainability. These are summarised below. _COVID-19 recovery:_ * Facilitates non-contact interactions supporting social distancing measures, and therefore prevents disease spread protecting both patients and staff. * Rationalises healthcare resource allocation, freeing up clinician workforce capacity which has been impacted by redeployment, sickness and self-isolation. _UK Government's Clean Growth Strategy and net zero ambition:_ * Reduced patient travel to hospital for in-person consultations reduces greenhouse gas emissions and air pollution.Reduced need for single use disposables and cleaning chemicals helping to reduce the carbon footprint of healthcare delivery. _Wider patient benefits:_ * Timelier triage will allow patients to be seen and investigated sooner with an overall reduced time to cancer diagnosis and treatment.Patients can be triaged at home and at their own convenience with no need for time off work or childcare. The NHS is one of the UK's proudest assets and is uniquely placed to lead the way on the government's timely ambition to ensure growth in an environmentally sustainable way. During this project Ufonia will be partnering with the Centre for Sustainable Healthcare who will be providing expert analysis of the project's social, financial and environmental impacts, with a strong focus on patient empowerment and self-care. If proven efficacious this technology has the potential to expand to many patient groups beyond the scope of this feasibility project and provides and exciting area for future development.

With the NHS focusing its efforts on managing the frontlines of the Covid-19 crisis, vast numbers of clinical appointments have been delayed or rescheduled. As the country recovers, we face a large and increasing backlog of clinic visits and waiting lists for operations. Understandably, this will create tremendous anxiety for patients both about their conditions and also about being "lost in the system". Administrative teams and clinicians will be under pressure to make sure individuals are not put at risk, and that patients are kept informed about the constantly changing situation. Our solution, Ufonia, delivers autonomous, natural language conversations with patients about their care over the telephone. Ufonia's artificial intelligence driven system can make calls to patients whose care has been postponed, to explain the current plans an organisation or team has for that patient, to answer common queries and to check in on how they're doing. The calls will provide an additional layer of reassurance to patients, whilst allowing teams to get up to date individualised information about each patient's situation and their specific concerns. From the point of view of a patient, this is a normal conversation from any home or mobile phone. Patients will not need to receive any training, access websites, download apps or be given new devices. The system will verify the identity of the individual, and provide a route for questions and concerns to be fed back directly to the clinical team. In contrast to human conducted telephone calls, Ufonia offers the ability to simultaneously and repeatedly contact large groups of patients. This replaces manual calls being made by skilled administrative and clinical staff with a new channel of two way communication. Despite the resource constraints faced by NHS organisations, care teams will have a tool to keep in touch with individuals who otherwise might feel abandoned. The content of the call is captured and analysed to allow care teams to more easily identify patients who may be at risk or who are particularly concerned for further review. The technology will initially be trialled at Oxford University Hospitals Foundation Trust. Patients, clinicians and administrative professionals will be involved in the process of refining the conversations and developing the platform. Following a successful pilot it will be available across the NHS in time to help hospitals manage the ongoing challenges to services created by COVID-19. The extension of this award will take insights form the first phase and enable the system to supports calls across multiple clinical teams. It will additionally support follow-on calls from human members of staff so that the experience for patients and professionals is integrated. This is especially import at this challenging time when changes in the delivery of clinical care in response to the pandemic are occurring on a weekly basis.

no public description

This project will introduce automation of clinical follow-up to enable proactive and timely access to healthcare services for patients, whilst optimising professionals' workload so they can deliver the best, most efficient care. The lead applicant, Ufonia, is a highly innovative digital health platform based on artificial intelligence technologies that can provide autonomous, voice-based conversation with patients in order to assess their health status. This application builds on a successful Innovate UK Feasibility award made to Ufonia and which met its milestones of technical feasibility and user acceptance of the voice-based platform. The solution being developed will be applicable and scalable to most healthcare conditions and pathways. The focus of the first deployment will be to optimise the management of patients requiring cataract surgery, because of the scale of escalating demand for cataract surgery, meaning there is an urgent need to make care pathways as effective and efficient as possible. Buckinghamshire Healthcare NHS Trust (BHT), will pilot the first clinical use of the technology. The project is further supported by Oxford AHSN who will provide health economic evaluation and business development (including the Bucks Health and Social Care Ventures Accelerator), the Science and Technology Facilities Council's Hartree Centre who have worked with IBM Watson to support Ufonia's AI development to date, and Oxford University Innovation's Clinical Outcomes Group, who bring academic and business development expertise to the application, licensing and development of patient reported outcome measures.

"Ufonia is an artificially intelligent system, that monitors health and wellness through a conversation with a medical voice 'chat-bot'. This project builds a version of Ufonia to assess the outcome following knee surgery. Traditionally this measurement has been performed using a paper, or sometimes electronic, questionnaire called the Oxford Knee Score (OKS). Whilst this score is a well-established way of assessing the result of surgery, the questionnaires are often not completed, are costly to deliver and limit the feedback of participants to fixed responses. We will be working with the team from Oxford University who authored the OKS to compare whether using Ufonia allows us to capture the same information using a more natural interface -- a voice conversation. This method is simple for everyone to complete without requiring posting and analysing paper questionnaires. It also does not require the use of an electronic device, download of software or any training. Additionally, Ufonia can analyse the overall sentiment of participants response language and capture extra information, beyond the limited structure of the basic questionnaire. This information likely to be important when trying to determine why particular patients improved more or less than others; and when trying to make more subtle distinctions in the outcomes from different treatments. The project will establish the technical feasibility, user acceptance and clinical validity of the system. This will then provide a foundation for the development of similar means of monitoring other patient reported outcomes. Ultimately, we anticipate that Ufonia can be used as a tool to help monitor the health and wellness of patients, without the resource constraints facing healthcare systems throughout the world."