Reliable detection of generalized convulsive seizures using an off-the-shelf digital watch: A multisite phase 2 study

Yash Shashank Vakilna; Xiaojin Li; Jaison S Hampson; Yan Huang; John C Mosher; Yuri Dabaghian; Xi Luo; Blanca Talavera; Sandipan Pati; Masel Todd; Ryan Hays; Charles Akos Szabo; Guo-Qiang Zhang; Samden D Lhatoo

doi:10.1111/epi.17974

Reliable detection of generalized convulsive seizures using an off-the-shelf digital watch: A multisite phase 2 study

Epilepsia. 2024 May 13. doi: 10.1111/epi.17974. Online ahead of print.

Authors

Yash Shashank Vakilna^{1

2}, Xiaojin Li^{1

2}, Jaison S Hampson^{1

2}, Yan Huang^{1

2}, John C Mosher^{1

2}, Yuri Dabaghian^{1

2}, Xi Luo³, Blanca Talavera^{1

2}, Sandipan Pati^{1

2}, Masel Todd⁴, Ryan Hays⁵, Charles Akos Szabo⁶, Guo-Qiang Zhang^{1

2}, Samden D Lhatoo^{1

2}

Affiliations

¹ Department of Neurology, University of Texas Health Science Center at Houston, Houston, Texas, USA.
² Texas Institute of Restorative Neurotechnologies, University of Texas Health Science Center at Houston, Houston, Texas, USA.
³ Department of Biostatistics and Data Science, University of Texas Health Science Center at Houston, Houston, Texas, USA.
⁴ Department of Neurology, University of Texas Medical Branch, Galveston, Texas, USA.
⁵ Department of Neurology, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
⁶ Department of Neurology, University of Texas Health Science Center at San Antonio, San Antonio, Texas, USA.

PMID: 38738972
DOI: 10.1111/epi.17974

Abstract

Objective: The aim of this study was to develop a machine learning algorithm using an off-the-shelf digital watch, the Samsung watch (SM-R800), and evaluate its effectiveness for the detection of generalized convulsive seizures (GCS) in persons with epilepsy.

Methods: This multisite epilepsy monitoring unit (EMU) phase 2 study included 36 adult patients. Each patient wore a Samsung watch that contained accelerometer, gyroscope, and photoplethysmographic sensors. Sixty-eight time and frequency domain features were extracted from the sensor data and were used to train a random forest algorithm. A testing framework was developed that would better reflect the EMU setting, consisting of (1) leave-one-patient-out cross-validation (LOPO CV) on GCS patients, (2) false alarm rate (FAR) testing on nonseizure patients, and (3) "fixed-and-frozen" prospective testing on a prospective patient cohort. Balanced accuracy, precision, sensitivity, and FAR were used to quantify the performance of the algorithm. Seizure onsets and offsets were determined by using video-electroencephalographic (EEG) monitoring. Feature importance was calculated as the mean decrease in Gini impurity during the LOPO CV testing.

Results: LOPO CV results showed balanced accuracy of .93 (95% confidence interval [CI] = .8-.98), precision of .68 (95% CI = .46-.85), sensitivity of .87 (95% CI = .62-.96), and FAR of .21/24 h (interquartile range [IQR] = 0-.90). Testing the algorithm on patients without seizure resulted in an FAR of .28/24 h (IQR = 0-.61). During the "fixed-and-frozen" prospective testing, two patients had three GCS, which were detected by the algorithm, while generating an FAR of .25/24 h (IQR = 0-.89). Feature importance showed that heart rate-based features outperformed accelerometer/gyroscope-based features.

Significance: Commercially available wearable digital watches that reliably detect GCS, with minimum false alarm rates, may overcome usage adoption and other limitations of custom-built devices. Contingent on the outcomes of a prospective phase 3 study, such devices have the potential to provide non-EEG-based seizure surveillance and forecasting in the clinical setting.

Keywords: machine learning; seizure detection; seizure forecasting; wearable devices.

Grants and funding

R01NS126690/Foundation for the National Institutes of Health