Case study 6 - Technologically-enabled epilepsy care
Integrating and adapting technology to support epilepsy care and self-management.
The case study examines the process of integrating and adapting technological tools for specialist epilepsy care and self-management. We are interested in generating a detailed understanding of the complex ways in which patients manage technological devices in the context of living with and receiving care for epilepsy. Emphasis is placed on the adaptations and workarounds users carry out in practice to be able to actively achieve ‘good’ and ‘safe’ epilepsy care, as part of their individual needs and pre-existing routines. This includes an understanding of what counts as effective communication between patients and clinical teams and how this can be engineered effectively through technology, given the clinical complexity of this condition.
Technological tools include wearables and apps, as well as remote consulting, shared care records, visualisation tools, real-time data sharing, cloud storage, team-based messaging and machine learning. For example, patients are provided with fitness and activity trackers that measure movement and other biomedical markers. These are then combined with data on seizures, self-reported by the patient through an app. This results in a large dataset with the potential to provide new insights into seizure patterns and improve management of the condition. These technologies are currently being introduced and piloted by a private/public collaboration between the NHS, industry and academic partners.
The research is based around a specialist NHS epilepsy clinic in South West England. This clinic employs multiple interacting technologies to support patients remotely, in an attempt to overcome resource limitations and to respond to the challenges of delivering care in rural populations across the county.
Study design and methods
The case study is driven by action research principles, which means we are working together with service providers, people living with epilepsy and their carers to establish what currently works well in technologically-enabled epilepsy care and to identify areas for improvement.
Ethnographic methods are used to generate data: interviews with patients, carers and health professionals; observations in the epilepsy clinic and peoples’ homes/everyday lives; multimodal data (e.g. from photos, screenshots) and documents. Although the initial phase of research will primarily focus on a detailed understanding of patient and carer experiences (e.g. in the form of stories and user experience data), we will also reach a wider range of stakeholders (such as technology developers and policy-makers) to increase the impact of our findings.
Learning will be fed back into the health service to inform technology development as part of service re-design. This work may also support the design of a longitudinal trial aiming to compare current care with the new, technologically-enabled model.
Specific aspects on the role of machine learning in this study are funded by a separate Springboard – Health of the Public 2040 Award from the Academy of Medical Sciences.