AI system
- System
-
Empatica Embrace wrist-worn seizure detection (electrodermal activity and accelerometer, on-board algorithm) with the Alert smartphone app
- Model
-
Not assessed
- Release
-
Exact release not established.
- Application developer
-
Empatica
- Role
-
The device classified sensor signals for possible seizures and sent alerts through its phone app.
- Configuration
-
The initial report concerned the Embrace device. Later reports concerned Embrace2.
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
A convulsive (generalized tonic-clonic) seizure, the only type the device is cleared to detect. The wristband worn and paired with a phone running the Alert app, with a caregiver designated. A caregiver able to reach the patient or call emergency services on receiving the alert.
- Human oversight
-
Not assessed
- Relation to AI
-
Per IEEE Spectrum, the Embrace detected the seizure and its app alerted McGrath's mother, who made the emergency call. The device did not call for help itself. The article calls the algorithm proprietary. The FDA summary describes it as an on-board algorithm validated against video-EEG. Empatica's own 2021 study calls it a predefined machine-learning algorithm. The McGrath event is known only from this single news item. The AES case-study abstract is not among the sources.
- AI contribution
-
Per IEEE Spectrum, the Embrace detected the seizure and its app alerted McGrath's mother, who made the emergency call. The device did not call for help itself. The article calls the algorithm proprietary. The FDA summary describes it as an on-board algorithm validated against video-EEG. Empatica's own 2021 study calls it a predefined machine-learning algorithm. The McGrath event is known only from this single news item. The AES case-study abstract is not among the sources.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
IEEE Spectrum (6 February 2018): an Embrace wristband alerted the mother of Morgan McGrath, 26, of Fulton, Mo., during a seizure about 15 months earlier; she called paramedics and McGrath survived.
- Category
-
Improved Physical Health
- Status
-
Not assessed
- Beneficiary groups
-
People.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Not assessed
- Comparison
-
seizures recorded during more than 6,500 hours of monitoring of 135 patients (device test reported by IEEE Spectrum)
- Results
-
Result: the device correctly identified nearly every single seizure, with a false alarm rate below that of the seizure frequency for most individuals.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Empatica.
- Jurisdictions
-
Benefit: Fulton, Missouri,
United States. Developer: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Connectivity between watch, phone and caregiver (one of 16 alerts in Montreal failed on a Wi-Fi disconnection). Caregivers tolerate false alarms (29 in 373 monitoring days in Montreal, mostly from routine movements). Focal seizures without convulsions are not detected (none of 510 in Montreal).
- Replication attempts
-
2 follow-up entries. Benefit recurred: 2.
- Later findings
-
7 January 2026. An independent Montreal epilepsy-monitoring-unit study later found the Embrace2 detected all 16 convulsive seizures that occurred while worn and working, with alerts reaching caregivers in 15 of 16 cases and 29 false alarms over the study.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0296-source-0001–0005
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Independent, Developer
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People.
- Depth
-
People: 3.
- Reasons
-
People: A young woman not breathing during a seizure had paramedics summoned by her mother on the device's alert and is reported alive and well. A potentially life-saving response documented only in one news report.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently studied
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Healthcare (epilepsy; seizure monitoring). Prescription wearable seizure monitor used at home.
- Purpose
-
Built to detect convulsive seizures from electrodermal activity and motion and to summon designated caregivers. The alert to McGrath's mother was that purpose.
- Dates
-
Date basis unassessed: 2018 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: f99e1615d50b…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
6 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Developer
Onorati F, Regalia G, Caborni C, LaFrance WC Jr, Blum AS, Bidwell J, De Liso P, El Atrache R, Loddenkemper T, Mohammadpour-Touserkani F, Sarkis RA, Friedman D, Jeschke J, Picard R (2021). Prospective Study of a Multimodal Convulsive Seizure Detection Wearable System on Pediatric and Adult Patients in the Epilepsy Monitoring Unit. Frontiers in Neurology 12:724904 (PMC8418082). Lead authors at Empatica, Inc.
A prospective study was conducted for the FDA clearance of an ACM and EDA-based CS-detection device based on a predefined machine learning algorithm.
-
Peer-reviewed study Independent author
Jahani A, Galindo Lazo DA, Sarzo Wabi I, Gharbi O, Robert M, Millan JP, D'Onofrio G, Robin A, Nguyen DK, Bou Assi E (2026). Prospective evaluation of a seizure detection wearable device for timely interventions in an epilepsy monitoring unit. Epilepsia 67(4):1802-1816 (PMC13075604).
Alerts successfully reached caregivers in 15 of 16 cases, with one failure due to a Wi‐Fi disconnection.
-
Regulatory document Developer
When a likely GTC is detected, the Embrace sends a message to the Alert smartphone application, which initiates calls and texts to summon the attention of designated caregivers.
-
News report Independent author
Dolgin E (2018). This Seizure-Detecting Smartwatch Could Save Your Life. IEEE Spectrum, 6 February 2018.
McGrath's wristworn Embrace device sent her mother an alert. Her mother called the paramedics.
Fifteen months ago, the 26-year-old teacher from Fulton, Mo., suffered an epileptic seizure that left her unresponsive, frothing at the mouth, with blue lips, and not breathing.