Ear-Seizure Detection (EarSD) Study

Not Applicable

Recruiting

• Conditions: Seizures; Epilepsy
• Interventions: Device: Ear-SD; Diagnostic Test: Electroencephalogram

• Registration Number: NCT06598189
• Lead Sponsor: Felicia Chu

Brief Summary

The proposed study is an investigator-initiated study that aims to measure the accuracy of a wearable seizure detection and prediction device (EarSD) by simultaneous recording with conventional video-EEG (Electroencephalogram) on patients with epileptic seizures in the Epilepsy Monitoring Unit of the hospital.

Detailed Description

A wearable seizure detection and prediction device (EarSD) is worn by patients with epileptic seizures. In this study, the goal is to validate the accuracy of a newly developed portable seizure detection device by examining if the Ear-SD device can (1) provide more comfort, (2) be unobtrusive to the subject during daily activities, and (3) be able to provide additional insight on a patients' seizure control.

Study Timeline

• Study First Submitted: 2024-08-23
• Study First Submitted QC: 2024-09-13
• Study First Posted: 2024-09-19
• Status Verified: 2025-04
• Study Start: 2025-04-03
• Last Update Submitted: 2025-04-23
• Last Update Posted: 2025-04-27
• Primary Completion: 2026-12
• Study Completion: 2032-12

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 40

Inclusion Criteria

1. Age ≥ 18 years.
2. Patients admitted to UMass Memorial Epilepsy Monitoring Unit (EMU) for long term video-EEG monitoring as part of standard care of both focal and generalized epilepsy.
3. Willing to wear the wearable device.
4. Ability to provide informed consent

Exclusion Criteria

1. Subjects wearing other ear devices such as hearing aids.
2. Inability or unwillingness to provide informed consent.
3. Irritation of the skin where the device is to be placed.
4. Patients with intracranial electrodes placement.
5. Prisoners
6. Cognitive impaired individuals
7. Pregnant Women
8. Children (Age 0-17)

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: SINGLE_GROUP

Arm && Interventions

Group	Intervention	Description
Ear-Worn Group	Ear-SD	All consented patients admitted to the Epilepsy Monitoring Unit (EMU) who are on continuous EEG (cEEG) will wear the ear-worn seizure detection device (EarSD) and there will be no randomization. The Ear-SD Device will be simultaneously worn by EMU patients on continuous video 21 electrode EEG (International 10-20 system) and single channel electrocardiogram (ECG). Daily skin assessment will be conducted and electrodes will be replaced as needed. At the end of the study, a self-reported short qualitative survey will be conducted to assess the overall experience of the enrolled subjects. The EarSD device and electrodes will be removed at the end of the study with the last skin examination.
Ear-Worn Group	Electroencephalogram	All consented patients admitted to the Epilepsy Monitoring Unit (EMU) who are on continuous EEG (cEEG) will wear the ear-worn seizure detection device (EarSD) and there will be no randomization. The Ear-SD Device will be simultaneously worn by EMU patients on continuous video 21 electrode EEG (International 10-20 system) and single channel electrocardiogram (ECG). Daily skin assessment will be conducted and electrodes will be replaced as needed. At the end of the study, a self-reported short qualitative survey will be conducted to assess the overall experience of the enrolled subjects. The EarSD device and electrodes will be removed at the end of the study with the last skin examination.

Primary Outcome Measures

Name	Time	Method
Seizure Accuracy/Prediction	up to 5 years	EarSD recordings from each electrode are separated and filtered to eliminate noise and artifact and results in 12 output signals (6 signals/ear) for comparison against cEEG EDF files for accuracy and precision. Mean, standard and average deviation, skewness, kurtosis, lowest and highest value, and the root mean square amplitude are measured from the dataset and are normalized between 0 and 1 then passed into the seizure detection and prediction Machine Learning (ML) model. ML model consisting of algorithms using deep neural networks (DNN), recurrent neural networks (RNNs) and Long Short-Term Memory networks (LSTM), classifies whether the signals are a seizure signal vs non-seizure signal, the focal type (left side/right side) and predicts the accuracy of seizures a minute ahead with the goal of achieving 96 percent or better accuracy and reducing the number of false positives.
Seizure Recording Criteria 1	Through study completion, an average of 7 Days	Recordings of Bioelectrical signal of subjects with the wearable device and simultaneous continuous EEG data is collected for the duration of hospitalization of participants. Outcome measures reported include number of seizure events per participant.
Seizure Recording Criteria 2	Through study completion, an average of 7 Days	Recordings of Bioelectrical signal of subjects with the wearable device and simultaneous continuous EEG data is collected for the duration of hospitalization of participants. Outcome measures reported include average duration of each seizure in minutes and seconds and total recording time in hours aggregated to arrive at one reported value seizure classification.
Seizure Recording Criteria 3	Through study completion, an average of 7 Days	Recordings of Bioelectrical signal of subjects with the wearable device and simultaneous continuous EEG data is collected for the duration of hospitalization of participants. Outcome measures reported include reported value seizure classification. Seizure classification includes Unclassified (UC), Focal Onset Aware (FOA), Focal Onset Impaired (FOIA), Focal to Bilateral Tonic-Clonic (FBTC).
Data Interpretation	up to 2 years	EarSD extracted EEG signals from the log file plotted alongside EDF files from cEEG are measured and compared to detect seizure onset and offset times for data interpretation. Two-minute segments of cEEG European Data Format (EDF) consisting of non-seizure signals from periods before and after the seizures, and non-seizure signals from periods of daily activities like talking, eating, and walking are involved in the comparison to detect seizure onset and offset times. Prediction measurement of Seizure Sensitivity (SS) and False Positivity Rate per hour (FPR/h) are measured from the recorded data signals. Seizure Sensitivity (SS) is the ratio between the (number of predicted seizures)/(total number of seizures) = (number of true alarms)/(total number of seizures). FPR/h is the number of alarms that do not correspond to seizures raised in one hour. FPR/h = ((Number of false alarms/Interictal Duration) - (Number of False Alarms × Refractory period)).

Secondary Outcome Measures

Name	Time	Method
Qualitative Satisfaction Survey	Through study completion, an average of 7 Days	At the end of the study, patients' experience and perception of the EarSD device are collected using a paper-based 7-question survey measured on a 5-point Likert scale ranging from Strongly Disagree to Strongly Agree. A maximum total point score of 35 represents a better reported satisfactory score from participants and having a good experience with the device and its comfortability for daily activities. The survey is a self-administered report, and participants will be asked about the comfortability and perceived utility of the device.

Trial Locations

Locations (2)

Ummmc-Memorial Campus; 🇺🇸 Worcester, Massachusetts, United States

Ummmc-University Campus; 🇺🇸 Worcester, Massachusetts, United States