The CAVA Multicentre Dizziness Trial

This is a multicentre diagnostic accuracy study with a recruitment target of 255 adult participants. Recruitment will take place across ten sites in the UK, over two years. To be eligible, participants must have an existing diagnosis of Ménière's disease, vestibular migraine or BPPV. The study will recruit eighty-five participants with each condition. Each patient's diagnosis will form the "reference standard" which will later be compared with a automated computer diagnosis.

Each participant will wear the CAVA device near continuously for thirty days. The device will record all eye and head movements during this time, including during any episodes of vertigo. When a patient experiences an episode of vertigo, they will be asked to activate an event marker on the CAVA device and keep a written record of attack onset and duration in a diary. Although this manual logging will not be relied upon for algorithm development, the whole 30 days of data will be used to detect periods of eye movement associated with dizziness.

The investigators will develop computer algorithms that use the data captured by the CAVA devices to differentiate between three target conditions. These algorithms will build on the algorithms that have been developed during the current MRC grant which have produced excellent results.10,11,17. The algorithms use deep learning neural networks (DNNs) in a so-called 'end-to-end' approach. In this approach, a multi-layered network takes as input 'raw' time domain data and outputs a classification decision without using any explicit intermediate representations of the signal (such as signal entropy, power, skewness, kurtosis etc.). End-to-end approaches, which typically utilise alternating sequences of convolution and pooling layers, fully connected layers, auto-encoders and long short-term memory (LSTM) layers, have been shown to outperform traditional approaches in cases where large amounts of training data are available. However, they provide little insight into how they work (i.e., which features of the signal are important for classification). It will therefore also be considered to develop methods in which intermediate representations are generated and then use these input features to test a range of classifiers (e.g., boosted trees, random forests, logistic regression, support vector machines etc.).

The performance of the algorithms will be assessed using the 'leave-one-out cross-validation' technique, which is the usual way of evaluating classifiers.22 In this technique, the data from a single patient is set aside and the remaining data from the other patients is used to 'train' the classifier. A algorithm will be referred to that is trained to distinguish the three conditions as a 'classifier'. The classifier is then tested on the set aside data: the testing process consists of comparing the classifier's predicted diagnosis ('Ménière's disease', 'vestibular migraine' or 'BPPV') with the true diagnosis (the reference standard label). This process is repeated, removing a different patient's data each time, producing an automated diagnosis for all 255 patients. Although computationally expensive, this ensures that the classifier has not 'seen' during training the data from the patient it tests, which would bias its decision. It also closely matches the real-world scenario of a new patient presenting to their clinician and a diagnosis being provided on the basis of their experience of other patients.

The study will present the sensitivity and specificity for diagnosing each of the three target conditions and Receiver Operator Curves (ROCs), showing how the diagnostic accuracy changes for various classification thresholds.

The target conditions have different incidences. Reflecting this imbalance in this study's statistical calculations would require many thousands of patients with the most common of these conditions. It is believed that this would not be economically viable and would not add value to the study. The results obtained will be sufficiently robust to demonstrate the system's efficacy and the expected detection rate for each disease.

A Health Economist (HE) will assess the potential resource, financial savings and patient benefits of a diagnostic pathway incorporating CAVA compared to existing pathways. The study design ensures that appropriate data collection is embedded into the study for the economic evaluation. An early cost-effectiveness model will be developed using retrospective patient data (e.g., history, number of tests and hospital visits). The model will reveal the potential savings and benefits of CAVA's predictive algorithms at various hypothetical thresholds of diagnostic accuracy versus a standard diagnostic pathway. A counterfactual pathway of diagnosis with the CAVA device will be developed against standard of usual care at the moment, to inform the most likely potential economic benefits.

A commercialisation consultant will oversee a portfolio of work to support the commercialisation of the CAVA system. They will produce a market access plan detailing CAVA's route to commercialisation and confirm CAVA's placement within existing NHS pathways and how it would be implemented. The Investigators will build upon the previous focus-group work with a stakeholders' event involving professionals, patients, and IT stakeholders from NHS organisations. The investigators will identify the issues important to stakeholders regarding the feasibility of adoption within the NHS and will establish support for adoption. A PPI event will be hosted to review the interim findings from the trial and a public dissemination event to share the findings with the public. Throughout the project prospective licenses will be engaged.