Authors' objectives: Epilepsy affects 1.1% of people in Wales, with 55 new cases per 100,000 each year. It causes recurrent seizures due to abnormal brain activity, with symptoms like jerking movements and unusual sensations. Diagnosis is based on clinical evaluation, combining a detailed history of observed events with laboratory tests such as an electroencephalogram (EEG). Seizures are often underreported by patients and carers. Video EEG (vEEG) and ambulatory EEG (aEEG) help diagnose and monitor seizures but can be resource intensive. Remote video recording of people with suspected or confirmed epilepsy may be an alternative to vEEGs and aEEGs in diagnosing or monitoring the condition. As a test done at home it can potentially overcome barriers to access and as a contactless device it is more tolerable for patients. Nelli (Neuro Event Labs, Finland) is an example of this technology which uses at-home video and audio monitoring (without EEGs) to screen, diagnose, and assess treatment effects in epilepsy. Nelli is typically used as a hybrid system combining artificial intelligence (AI) with human expert review to detect and classify motor-related seizures. This report aims to identify and summarise evidence that addresses the following question: What is the clinical and cost effectiveness of at-home video monitoring for the diagnosis and management of epilepsy

Authors' results and conclusions: Six studies were identified, including one systematic review on video recordings to distinguish between epileptic seizures (ES) and non-epileptic spells (NES). Two diagnostic accuracy studies evaluated the Nelli device in hybrid and automatic modes for detecting motor seizures in epilepsy monitoring units. Three observational studies assessed the Nelli-hybrid device in real-world settings. The evidence indicated that video recordings (without AI assistance, viewed retrospectively) are effective for distinguishing ES from NES, with accuracy varying by the reviewer’s specialty. Neurologists specializing in epilepsy performed better than other specialties. Mobile video footage was comparable to footage from epilepsy monitoring units, though neither has high enough accuracy to replace vEEG as the reference standard test for diagnosis of ES and NES. The Nelli device is effective in detecting major motor seizures but has poor sensitivity for minor seizures. In real-world settings, the Nelli-hybrid device detects more seizures than patients or caregivers report, and it influences treatment decisions. It is also considered acceptable by patients and caregivers. However, the Nelli system, when operating in fully automated mode as a real-time motor seizure monitor, has a high false positive rate, limiting its use as a seizure alarm. There is a lack of evidence on whether video recordings or the Nelli device improve patient-centred outcomes, such as epilepsy control, disease progression, emergency admissions, and health-related quality of life. No evidence was found on time to diagnosis or resource use. No published economic evaluation was identified which met our inclusion/exclusion criteria for at-home video monitoring for the diagnosis and management of epilepsy. However, an unpublished early economic evaluation of Nelli was included for economic review due to its potential insights. Results of their analysis estimated Nelli to be a cost saving intervention, saving £432 per-person over a one-year time horizon. The evaluation was directly applicable to the UK but had potentially serious limitations surrounding the quality of efficacy evidence for Nelli. The cost consequence analysis conducted by HTW compared the Nelli-hybrid system to vEEGs in detecting precise major motor nocturnal epileptic seizures. Whilst the system was estimated to be cost saving, it was also associated with an increase in false negative misdiagnoses. The analysis likely overestimates cost savings, as the costs related to false positive misdiagnoses could not be captured due to limited evidence on the diagnostic specificity of the Nelli system. Similar conclusions were made in scenario analyses exploring the use of the automated system and the detection of various seizure categories, with large variability in false negative misdiagnoses. Sensitivity analyses explored changes in model inputs, which found that increasing the duration of Nelli use to four weeks caused the intervention to become cost incurring. The outcomes of the economic analysis should be interpreted with caution, as the full economic impact could not be assessed due to limitations in the effectiveness evidence.

Authors' recommendations: At-home video monitoring for the diagnosis and management of epilepsy, including systems utilising artificial intelligence, shows promise but the clinical and economic evidence is insufficient to support routine adoption. There was limited clinical effectiveness evidence identified. In one study, the Nelli-hybrid system demonstrated good diagnostic sensitivity in identifying major motor seizures, but this was conducted in a hospital setting rather than at home. Opportunistic video recording of seizures at home is acknowledged as a useful source of supplementary information for clinicians. Whilst the economic impact comparing the Nelli-hybrid system to video electroencephalogram was explored, the full economic impact could not be assessed due to limitations in the clinical effectiveness evidence. Further high quality prospective comparative evidence reporting full diagnostic accuracy, quality of life and acceptability across different patient groups in the home setting is recommended.

Authors' methods: The Evidence Appraisal Report is based on a literature search (strategy available on request) for published clinical and economic evidence on the health technology of interest. It is not a full systematic review but aims to identify the best available evidence on the health technology of interest. Researchers critically evaluate and synthesise this evidence. We include the following clinical evidence in order of priority: systematic reviews; randomised trials; non-randomised trials. We only include evidence for “lower priority” evidence where outcomes are not reported by a “higher priority” source. We also search for economic evaluations or original research that can form the basis of an assessment of costs/cost comparison. We carry out various levels of economic evaluation, according to the evidence that is available to inform this.

Project Status: Completed

Year Published: 2025

URL for published report: https://healthtechnology.wales/reports-guidance/at-home-video-monitoring-for-epilepsy/

English language abstract: An English language summary is available

Publication Type: Rapid Review

Country: Wales, United Kingdom

Organisation Name: Health Technology Wales

Contact Address: c/o Digital Health Care Wales, 21 Cowbridge Road East Cardiff CF11 9AD

Contact Name: Susan Myles, PhD

Contact Email: healthtechnology@wales.nhs.uk