Embrace, a wearable convulsive seizure detection and alert system First performance report of a case study in real-life settings R. Picard 1,2 , G. Regalia 1 , C. Caborni 1 , M. Migliorini 1 , F. Onorati 1 1 Empatica, Inc, Cambridge, MA and Milan, Italy; 2 MIT Media Lab, Massachusetts Institute of Technology, Cambridge (MA), US INTRODUCTION • Empatica’s Embrace is a comfortable wristband wearable convulsive seizure (CS) detection system (Figure 1). • It is based on accelerometer (ACC) and electrodermal activity (EDA) data and works with a smartphone app, Alert. • Embrace with Alert app is a medical device (CE) in the European Union. Alert is available only through a clinical trial in the USA. RATIONALE • In EMU settings, the system has achieved Sens = 92-100% and false alarm rate (FAR) = 0.15-2.02 false alarms per day 1,2 . • EMU settings may differ from the real-life environment. • We have recently shown that adding outpatient data to the EMU-based training set allows to attain better performance 2 . METHOD 1. A patient with Dravet Syndrome (14y) wore the Embrace 113 days for 1,973 hours (average daily wear = 17.2±5 hrs/day). 2. This patient’s data were not used to train the classifier. 3. As a ground truth the patient’s caregiver was asked to meticulously annotate the occurrence of each CS. Alert without a CS were labeled as a false alarm (FA). RESULTS • The system detected 22 out of 24 recorded CSs (Sens = 92%), with a delay from 15-64 seconds (38 sec avg) between the onset and the alert, and 6-57 seconds (11 sec avg) between the alert and call. • The 2 missed seizures were characterized by a low EDA and a mild brief clonic component (Figure 3A). • FAR = 0.35 false alarms per day worn, with a total of 39 FAs. In 88 days out of 113 there were no FAs. In only 2 days out of 113 were there more than 2 FAs (Figure 2B). Figure 1. Schematics of Embrace convulsive seizure (CS) detection and alert system: a wristband detects an event, transmits an alert to the smartphone, which generates a call via a cloud-based service to designated caregivers. Bottom: Empatica’s Embrace. 1 Regalia et al. "An improved wrist-worn convulsive seizure detector based on accelerometry and electrodermal activity sensors”, 69 th AES, December 4-8, 2015, Philadelphia, PA. 2 Onorati et al. "Improving convulsive seizure detection by exploiting data from outpatient settings using the Embrace wristband”,12 th European Congress on Epileptology, September 11-15, 2016, Prague. CONCLUSION • We reported the performance of Embrace+Alert system used 3 months in real-life settings. • The performance, both Sens and FAR, mirrored the results obtained in EMU settings. • All seizures during sleep were detected (Figure 2A). • Caregiver reported that FAs were generated by activities like hands shaking, car transport and dancing. AIM To present the first case study about long-term Embrace recordings and alerts in real-life settings. CONTACT www.empatica.com/product- embrace Francesco Onorati: [email protected] Rosalind Picard [email protected], [email protected] Figure 2. Left (A): Distribution of patient’s seizures based on hour of the day. Right (B): Histogram of FAR over the 113 days of recording. A B Figure 3. EDA (top) and ACM (bottom) for two CSs recorded with Embrace. The violet patches mark the seizures. Left(A): missed event. Right(B): detected event. A B

Embrace, a wearable convulsive seizure detection and … · Embrace, a wearable convulsive seizure detection and alert system First performance report of a case study in real -life

Download PDF Report

Upload
nguyenkien
View
215
Download
0

Embed Size (px)

Citation preview

Page 1: Embrace, a wearable convulsive seizure detection and … · Embrace, a wearable convulsive seizure detection and alert system First performance report of a case study in real -life

Embrace, a wearable convulsive seizure detection and alert systemFirst performance report of a case study in real-life settings

R. Picard1,2, G. Regalia1, C. Caborni1, M. Migliorini1, F. Onorati11 Empatica, Inc, Cambridge, MA and Milan, Italy; 2 MIT Media Lab, Massachusetts Institute of Technology, Cambridge (MA), US

INTRODUCTION• Empatica’s Embrace is a comfortable wristband wearable

convulsive seizure (CS) detection system (Figure 1).• It is based on accelerometer (ACC) and electrodermal activity

(EDA) data and works with a smartphone app, Alert.• Embrace with Alert app is a medical device (CE) in the European

Union. Alert is available only through a clinical trial in the USA.

RATIONALE• In EMU settings, the system has achieved Sens = 92-100% and

false alarm rate (FAR) = 0.15-2.02 false alarms per day1,2.• EMU settings may differ from the real-life environment.• We have recently shown that adding outpatient data to the

EMU-based training set allows to attain better performance2.

METHOD1. A patient with Dravet Syndrome (14y) wore the Embrace 113

days for 1,973 hours (average daily wear = 17.2±5 hrs/day).

2. This patient’s data were not used to train the classifier.

3. As a ground truth the patient’s caregiver was asked tometiculously annotate the occurrence of each CS. Alertwithout a CS were labeled as a false alarm (FA).

RESULTS

• The system detected 22 out of 24 recorded CSs (Sens = 92%), with a delay from 15-64 seconds (38 sec avg)between the onset and the alert, and 6-57 seconds (11 sec avg) between the alert and call.

• The 2 missed seizures were characterized by a low EDA and a mild brief clonic component (Figure 3A).

• FAR = 0.35 false alarms per day worn, with a total of 39 FAs. In 88 days out of 113 there were no FAs. In only 2days out of 113 were there more than 2 FAs (Figure 2B).

Figure 1. Schematics of Embrace convulsive seizure (CS) detection and alert system: a wristband detects an event, transmits an alert tothe smartphone, which generates a call via a cloud-based service to designated caregivers. Bottom: Empatica’s Embrace.

1 Regalia et al. "An improved wrist-worn convulsive seizure detector based on accelerometry and electrodermal activity sensors”, 69th AES, December 4-8, 2015, Philadelphia, PA.2 Onorati et al. "Improving convulsive seizure detection by exploiting data from outpatient settings using the Embrace wristband”,12th European Congress on Epileptology, September 11-15, 2016, Prague.

CONCLUSION• We reported the performance of Embrace+Alert system used 3 months in real-life settings.

• The performance, both Sens and FAR, mirrored the results obtained in EMU settings.

• All seizures during sleep were detected (Figure 2A).

• Caregiver reported that FAs were generated by activities like hands shaking, car transport anddancing.

AIMTo present the first case study about long-term

Embrace recordings and alerts in real-life settings.

CONTACTwww.empatica.com/product-embrace

Francesco Onorati: [email protected]

Rosalind Picard [email protected], [email protected]

Figure 2. Left (A): Distribution of patient’s seizures based on hour of the day. Right (B): Histogram of FAR over the 113 days of recording.

A B

Figure 3. EDA (top) and ACM (bottom) for two CSs recorded with Embrace. The violet patches mark the seizures. Left(A): missed event. Right(B): detected event.

A B