For people with insufficient hearing to effectively use hearing aids, cochlear implants can provide great benefit, although they do not restore normal hearing. Cochlear implants stimulate the hearing nerve directly with electrical currents from a set of electrodes surgically implanted into the inner ear (cochlea). Although cochlear implants are a great success, a wide range in speech perception outcomes are observed. The aim of this programme of research is to reduce the variability in performance as well as increasing the levels of speech recognition achieved by all. We propose to achieve this by using a special machine to measure brain activity in response to sound for cochlear implant users. This technique is used routinely in clinical practice and involves wearing a special hat to make the recordings. We will use this method to record responses at different parts of the hearing system between cochlea and brain. By understanding the relationship between these responses and speech understanding it will help us to appreciate the importance of different stages in the hearing pathway. These measures will allow us to observe the brain changes that take place once cochlear implants are switched on. We will define 'biomarkers' that can be used by clinicians to guide implant fitting and rehabilitation. A biomarker is an objective measurement of typical changes in the body. We will develop guidance for adjusting the ways that sounds are sent through the cochlear implant or for switching off electrodes. For those with bilateral cochlear implants we will also develop guidelines for adjusting the implants to make the sounds more similar in each ear to improve the way that the ears work together. This research will be conducted with both adults and children to fully understand how people hear with a cochlear implant.

One in 17 people have a rare disease. Rare diseases can be extremely difficult to diagnose, but they often have an unidentified genetic cause. Recent advances in clinical imaging, pathology, and genomic technologies have led to remarkable progress in understanding disease - particularly rare diseases. However, the power of these technologies cannot be fully realised until the immense volume of data generated can be integrated with NHS data, then analysed by researchers in a secure environment that protects the privacy of individuals. Working across the NHS, academia and industry we will use existing tools to transfer data from NHS Trusts to a secure environment that interfaces with the NHS network and shares data with Public Health England. NHS information will then be combined with research data in a cloud-based platform. Initially, we will involve patients with rare diseases recruited to the NIHR BioResource; a national resource of volunteers who have already provided consent that information retrieved from their health records can be used for medical research. This will create a rich research resource with the potential to transform our understanding of rare genetic disorders, drive improvements in diagnosis and management, and provide proof of principle for use in other diseases.

"Crohn's Disease and Ulcerative Colitis are the main forms of IBD. They cause debilitating symptoms affecting 0.78% of the UK population (500,0001 people), and costing UK health budgets approximately £1.5 Billion2 each year. Treatment is with steroids, immunosuppressants and antibody therapies, but results are variable. Over 70% of patients with Crohn’s and 15% with colitis require major surgery3. There is an urgent need to better understand why patients respond differently to treatments in order to improve outcomes and reduce costs. Recent advances in clinical imaging, pathology, and genomic technologies have produced remarkable progress in understanding IBD. However, the power of these technologies cannot be clinically realised until these data can be combined and used in a meaningful way. Our DIH will integrate data from multiple sources and create a secure research resource that allows approved researchers to access data, whilst protecting the privacy of individuals. Patient and public involvement is key to our success. 25,000 IBD patients have already provided consent for their health records to be retrieved and used for medical research. Working together, we will transform our understanding of IBD, drive improvements in diagnosis and treatment, and deliver a data framework to reproduce in other disease areas."

Delivery of pathology tissue diagnoses, most of which are cancer, in the current format is unsustainable. Advances in genomic medicine and immune-oncology have shown that the classification of tumours into subtypes allows selection of patients for specific treatments but also spares patients unnecessary toxic and expensive therapies. Still, making such diagnoses has become more time-consuming, involving the selection and interpretation of ancillary tests which requires an ever-growing specialist knowledge for each cancer type. Whilst the need for diagnostic expertise is increasing, there is already a shortfall of 25% of pathologists who are able to report results: this is set to decline. We propose that the use of AI can ensure that the delivery of tissue diagnoses by pathologists is sustainable and supports delivery of personalised treatments. The benefits of AI in pathology are beginning to be seen, e.g. identification of high-grade areas of prostate cancer shows a reduction in errors and pathologists' time. The development of AI for diagnoses is timely as full adoption of digitised histological images, allowing them to be interrogated by both humans and artificial intelligence (AI), is expected in the UK by 2025. AI is a data-hungry process; it is unrealistic to provide 100,000s images that are required to train a model. Even the most common cancers (e.g. breast) have multiple subtypes; identification of these is required for selection of patients for personalised treatments. To address this challenge, we propose to develop a novel AI strategy using a relatively small sample size (~1000 images per class). Such a model could be adapted to any cancer type. A multiple-instance learning framework will be developed, using transformers for feature extraction and classification. A tool that flags samples that cannot be confidently classified will be applied thereby alerting the pathologist of potentially unseen diseases. The deep learning model will be strengthened by the injection of pathologists' domain knowledge. Soft tissue and bone tumours We will develop the AI model on tumours of soft tissue (muscle, fat, blood vessels, etc.) and bone, an area considered to be one of the most challenging diagnostically. These tumours comprise approximately 100 different subtypes, and represent some of the most common cancers in children and young adults. We will build on our existing deep learning model of 15 different subtypes trained on 2122 images, which predicts the correct diagnosis in 87% of cases. Selection of confirmatory ancillary tests is then prompted by the algorithm and streamlines the diagnostic pathway. 17,000 images that have already been scanned will be added to the library and allow the rapid development and extension of the classification model. The image library will be linked to clinical outcomes and expanded to 35,000 images during the project. Added to this is the commitment of the established Sarcoma Network of at least 20 pathologists from across all countries in the UK, to provide the additional 20,000 images mentioned above. Additional benefits The study and infrastructure will serve as the framework for the continued development of the model which can rapidly be expanded prospectively with the introduction of digital pathology in the NHS and globally. The model can be developed over time in response to new advances. The image library will be available for training future pathologists, research, validation of other AI algorithms, and contribute to the Sarcoma Genomics England Clinical Interpretation Partnership (GeCIP) offering a valuable resource for future multi-modal multi-omic research. Working closely with Sarcoma charities, and partners, we will involve and engage patients, their families, and the public, to build trust in the use of AI in health care. Development of AI models for digitised pathology images can avert the crisis facing this medical specialty.

Current hearing aids suffer from two major limitations: 1) hearing aid audio processing strategies are inflexible and do not adapt sufficiently to the listening environment, 2) hearing tests and hearing aid fitting procedures do not allow reliable diagnosis of the underlying nature of the hearing loss and frequently lead to poor fitting of devices. This research programme will use new machine learning methods to revolutionise both of these aspects of hearing aid technology, leading to intelligent hearing devices and testing procedures which actively learn about a patient's hearing loss enabling more personalised fitting. Intelligent audio processing The optimal audio processing strategy for a hearing aid depends on the acoustic environment. A conversation held in a quiet office, for example, should be processed in a different way from one held in a busy reverberant restaurant. Current high-end hearing aids do switch between a small number of different processing strategies based upon a simple acoustic environment classification system that monitors simple aspects of the incoming audio. However, the classification accuracy is limited, which is one of the reasons why hearing devices perform very poorly in noisy multi-source environments. Future intelligent devices should be able to recognise a far larger and more diverse set of audio environments, possibly using wireless communication with a smart phone. Moreover, the hearing aid should use this information to inform the way the sound is processed in the hearing aid. The purpose of the first arm of the project is to develop algorithms that will facilitate the development of such devices. One of the focuses will be on a class of sounds called audio textures, which are richly structured, but temporally homogeneous signals. Examples include: diners babbling at a restaurant; a train rattling along a track; wind howling through the trees; water running from a tap. Audio textures are often indicative of the environment and they therefore carry valuable information about the scene that could be harnessed by a hearing aid. Moreover, textures often corrupt target signals and their suppression can help the hearing impaired. We will develop efficient texture recognition systems that can identify the noises present in an environment. Then we will design and test bespoke real-time noise reduction strategies that utilise information about the audio textures present in the environment. Intelligent hearing devices Sensorineural hearing loss can be associated with many underlying causes. Within the cochlea there may be dysfunction of the inner hair cells (IHCs) or outer hair cells (OHCs), metabolic disturbance, and structural abnormalities. Ideally, audiologists should fit a patient's hearing aid based on detailed knowledge of the underlying cause of the hearing loss, since this determines the optimal device settings or whether to proceed with the intervention at. Unfortunately, the hearing test employed in current fitting procedures, called the audiogram, is not able to reliably distinguish between many different forms of hearing loss. More sophisticated hearing tests are needed, but it has proven hard to design them. In the second arm of the project we propose a different approach that refines a model of the patient's hearing loss after each stage of the test and uses this to automatically design and select stimuli for the next stage that are particularly informative. These tests will be be fast, accurate and capable of determining the form of the patient's specific underlying dysfunction. The model of a patient's hearing loss will then be used to setup hearing devices in an optimal way, using a mixture of computer simulation and listening test.