Can a Wearable Detect Seizures?
Two validation studies found seizures caught 87% to 93% of the time, but only in the roughly half of patients whose heart rate reacts enough.
Evidence rating for the proposition “An HRV algorithm on a wearable ECG detects seizures in patients with marked ictal autonomic change”: Established
In some people, yes. Two independent Phase 2 validation studies tested HRV-based algorithms, recorded with a wearable ECG device and checked against video-EEG monitoring. They found high sensitivity for detecting seizures, but only in patients whose seizures produce a large enough heart-rate change to begin with. In the two studies, 57.9% and 53.5% of patients qualified as reliable responders, and the algorithms caught 87% and 93.1% of their seizures. For the rest, HRV alone was not a reliable signal.
Can a wearable actually detect a seizure as it happens?
Every other HRV article on this site treats heart rate variability as a slow-moving readout of stress, recovery, or autonomic health measured over hours or nights. Two Phase 2 validation studies used the same underlying signal for something much more acute and time-sensitive: detecting an epileptic seizure as it happens, using a wearable ECG device instead of the electrode-heavy video-EEG setup that's the actual diagnostic gold standard.
The premise works because many seizures, especially convulsive ones, produce a sharp, measurable spike in heart rate as the autonomic nervous system reacts. The question both studies tested is whether that spike is consistent and specific enough to build a real detection algorithm around.
2 studies
- In prospectively recruited patients wearing an ECG patch (ePatch), 11 of 19 patients with seizures (57.9%) had a greater than 50 beats/min ictal heart-rate change and were classified as responders. In that group, the algorithm detected 20 of 23 seizures (sensitivity 87.0%), catching all but one of 10 convulsive seizures and all 8 focal impaired-awareness seizures, while missing 2 of 4 focal aware seizures. The false alarm rate was 0.9 per 24 hours (0.22 per night).
- In 100 consecutively recruited patients undergoing long-term video-EEG monitoring, 126 seizures (108 nonconvulsive, 18 convulsive) from 43 patients were analyzed against 26 automated HRV algorithms, blinded to the EEG data. The best-performing algorithm classified 53.5% of patients as responders (over two-thirds of their seizures detected). Among responders, 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 specifically.
The catch: about half of patients don't qualify
Both studies converge on the same limitation from two different patient cohorts and slightly different algorithms: HRV-based seizure detection depends entirely on whether a given patient's seizures actually produce a strong enough autonomic signature. In the first study, responders were defined by a greater-than-50-beats-per-minute heart-rate change during a seizure; in the second, by whether more than two-thirds of a patient's seizures were caught. In both, only about half of patients met that bar (57.9% and 53.5%, respectively).
For the patients who don't qualify, this isn't a story about the algorithm needing refinement so much as a documented physiological ceiling: their seizures may simply not move heart rate enough to be caught by any HRV-based approach as currently designed. Neither study reports what algorithm, if any, was more accurate for these non-responders.
Both studies were run in clinical settings with a wearable ECG PATCH device, alongside simultaneous video-EEG monitoring as the reference standard, not a consumer smartwatch or fitness ring used unsupervised at home. Neither study tested how this performs outside a monitored clinical environment.
What this doesn't establish
Neither study reports what happens after a detection: whether an alert reaches a caregiver in time to matter, or whether earlier detection changes clinical outcomes. Both are validation studies measuring whether the algorithm correctly flags a seizure that already happened, against a video-EEG record, not real-time-response or outcome studies.
The false alarm rate from the first study (0.9 per 24 hours) is a real, useful number, but the second study doesn't report a comparable figure in what's summarized here, so the two aren't directly comparable on that specific metric. Read the sensitivity figures as evidence that the underlying approach is real and reproducible across two independent cohorts, not as a claim that any consumer product implements it this way today.
Neither study tested a downstream outcome (faster medical response, reduced injury, etc.) from an HRV-based alert. Both measure detection accuracy against a video-EEG reference, not real-world clinical benefit.
Common questions
Can a wearable actually detect a seizure using heart rate variability?
In two Phase 2 validation studies, yes, for a subset of patients. Detection sensitivity was 87% and 93.1% respectively among patients whose seizures produced a large enough heart-rate change to qualify as algorithm "responders."
Does HRV-based seizure detection work for every patient?
No. In both studies, only about half of patients (57.9% and 53.5%) qualified as responders. For the rest, their seizures didn't produce a strong enough autonomic/heart-rate signature for the algorithms tested to reliably detect.
What's the false alarm rate for HRV-based seizure detection?
One of the two studies reported 0.9 false alarms per 24 hours (0.22 per night). The other study didn't report a directly comparable figure in the portion of its findings summarized here.
Was this tested with a consumer smartwatch?
No. Both studies used a dedicated wearable ECG patch device in a clinical setting, validated against simultaneous video-EEG monitoring, not a consumer smartwatch or fitness ring used at home.