EpiMonitor
Empatica Srl • Neurology • 02/15/2024
Device Purpose
The EpiMonitor system is a prescription wearable device designed for adjunct monitoring of generalized tonic-clonic seizures in individuals aged 6 and older, utilizing electrodermal activity and motion sensors. Its methodology involves an on-board algorithm for real-time seizure pattern detection and caregiver alerts, with adjustable sensitivity modes to balance detection accuracy and false alarm rates, while also collecting physiological data for retrospective clinical review.
Summary
The EpiMonitor system, comprising the EmbracePlus wearable device and the EpiMonitor mobile application, is designed as an adjunct for monitoring generalized tonic-clonic seizures (GTCS) in adults and children aged six and above, in both home and healthcare settings. It functions by having the user wear the EmbracePlus on their wrist, where it continuously collects electrodermal activity (EDA) and motion data. An onboard algorithm, EpiAlgo 2.1, analyzes this data; upon detecting patterns indicative of a GTCS, the wearable signals the paired EpiMonitor app, which then alerts designated caregivers via voice call and SMS through the Empatica Cloud. The system also records and transmits accelerometer, EDA, peripheral skin temperature, and activity data to the cloud for retrospective review by healthcare professionals via the Care Monitoring Portal. The EpiMonitor introduces 'high' and 'low' sensitivity modes for its seizure detection algorithm to optimize performance during periods of rest/sleep versus low-intensity activity, aiming to reduce false alarms. While the 'high' sensitivity mode's performance is benchmarked against a predicate device, the 'low' sensitivity mode's efficacy was evaluated through retrospective analyses of clinical data. In Epilepsy Monitoring Unit settings during non-rest activities, the low-sensitivity mode showed a Positive Percent Agreement (PPA) of 1.000 (corrected 0.905) for adults and 0.895 (corrected 0.791) for pediatrics, with False Alarm Rates (FAR) of 0.28 and 0.70 per 24 hours, respectively. Analysis of real-world data (from a similar device) for this mode indicated PPAs of 0.80 (corrected 0.77) for adults and 0.87 (corrected 0.86) for pediatrics, with FARs of 0.25 and 0.34 per 24 hours, respectively, suggesting acceptable seizure detection with fewer false alerts.
AI Regulatory Concerns
Powered by
Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.
Keywords
Device Metadata
Relevant Clinical Questions
- Q1. How does the 'Low-Sensitivity' mode algorithmically differ from the 'High-Sensitivity' mode to achieve a lower false alarm rate during low-intensity activities, and what is the specific trade-off in detection sensitivity for Generalized Tonic-Clonic Seizures?; Given that the real-world data for the Low-Sensitivity mode performance was captured using the Embrace2 wearable, what are the potential implications or limitations when extrapolating these performance metrics to the EmbracePlus device used in the EpiMonitor system?; What specific 'low-intensity activities' were included in the validation of the 'Low-Sensitivity' mode, and how robust is its performance across the diverse range of such activities that patients might typically engage in?; How is 'activity during sleep' quantified by the EpiMonitor system, and what is the clinical utility or correlation of this parameter, along with peripheral skin temperature, in the retrospective review by healthcare professionals for epilepsy management?; What are the specific mechanisms within the Empatica Cloud and Care Monitoring Portal that ensure data security, patient privacy, and timely, reliable access for healthcare providers reviewing the retrospectively collected physiological data?
Risk Classification
ESL AnalysisFDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Post-§524B but no clear network capability detected
Learn how Parasoft automates IEC 62304 compliance testing →Cybersecurity Evidence
Powered by SBOMator™Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.
Supply Chain BOM Evidence
Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.
Analysis:
• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.
• Evidence of ML-BOM, SaaSBOM, HBOM detected in AI-generated device summary.
• SBOM not mentioned in AI-generated device summary. Under §524B (effective Oct 2023), cyber devices must provide a SBOM.
• Not detected in AI-generated device summary: SBOM, CBOM, VDR/VEX, OBOM. These may be present in the full FDA submission.
Preparing a similar submission?
ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.
Assess Your Readiness →Or contact ESL directly