Aarhus University Seal / Aarhus Universitets segl

Seizure detection based on heart rate variability using a wearable electrocardiography device

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

DOI

OBJECTIVE: To assess the feasibility and accuracy of seizure detection based on heart rate variability (HRV) using a wearable electrocardiography (ECG) device. Noninvasive devices for detection of convulsive seizures (generalized tonic-clonic and focal to bilateral tonic-clonic seizures) have been validated in phase 2 and 3 studies. However, detection of nonconvulsive seizures still needs further research, since currently available methods have either low sensitivity or an extremely high false alarm rate (FAR). METHODS: In this phase 2 study, we prospectively recruited patients admitted to long-term video-EEG monitoring (LTM). ECG was recorded using a dedicated wearable device. Seizures were automatically detected using HRV parameters computed off-line, blinded to all other data. We compared the performance of 26 automated algorithms with the seizure time-points marked by experts who reviewed the LTM recording. Patients were classified as responders if >66% of their seizures were detected. RESULTS: We recruited 100 consecutive patients and analyzed 126 seizures (108 nonconvulsive and 18 convulsive) from 43 patients who had seizures during monitoring. The best-performing HRV algorithm combined a measure of sympathetic activity with a measure of how quickly HR changes occurred. The algorithm identified 53.5% of the patients with seizures as responders. Among responders, detection sensitivity was 93.1% (95% CI: 86.6%-99.6%) for all seizures and 90.5% (95% CI: 77.4%-97.3%) for nonconvulsive seizures. FAR was 1.0/24 h (0.11/night). Median seizure detection latency was 30 s. Typically, patients with prominent autonomic nervous system changes were responders: An ictal change of >50 heartbeats per minute predicted who would be responder with a positive predictive value of 87% and a negative predictive value of 90%. SIGNIFICANCE: The automated HRV algorithm, using ECG recorded with a wearable device, has high sensitivity for detecting seizures, including the nonconvulsive ones. FAR was low during the night. This approach is feasible in patients with prominent ictal autonomic changes.

Original languageEnglish
JournalEpilepsia
Volume60
Issue10
Pages (from-to)2105-2113
Number of pages9
ISSN0013-9580
DOIs
Publication statusPublished - Oct 2019

    Research areas

  • automated, epilepsy, focal seizures, phase 2 study, seizure alarm, TONIC-CLONIC SEIZURES, MULTICENTER, SERIAL-ADDITION TASK, STANDARDS, SUDDEN UNEXPECTED DEATH, ACCELEROMETER, ICTAL TACHYCARDIA, EPILEPTIC-SEIZURES

See relations at Aarhus University Citationformats

ID: 163724008