Investigating the Relationship Between Pre-Ictal Heart Rate Variability and Seizure Duration in Focal Epilepsy
CSEF · 2026 Medicine & Physiology (Senior Division)
Overview
Seizures impact 10% of the global population, with epilepsy developing in 1-2%. Seizure duration is an important marker of severity, with longer duration leading to increased morbidity and mortality. As the heart and brain are interlinked with the autonomic nervous system, electrocardiogram (ECG) data can be used to study seizures. While heart rate variability (HRV), a measure derived from ECG, has been studied for seizure detection, its relationship to severity, with seizure duration as an index, remains largely unexplored. This study investigates whether pre-ictal HRV, quantified using the root mean square successive differences (RMSSD), is associated with subsequent seizure duration in patients with focal epilepsy. Data was obtained from the SeizeIT2 dataset containing synchronized ECG and EEG recordings with multiple vigilance states and seizure types of 125 patients in epilepsy monitoring units (EMUs). Pre-ictal HRV was calculated over a 300-second window preceding seizure onset, and seizure duration was log-transformed to account for skew. Linear regression was applied to model seizure duration as an outcome of RMSSD values, followed by a multivariable regression model with interaction terms and patient-level clustering. A total of 843 seizures were analyzed, and lower RMSSD was significantly associated with a longer seizure duration, specifically for focal aware seizures (β = −0.0147, p = 0.011). These findings suggest that pre-ictal autonomic measures may help identify patients at risk for prolonged seizures in specific focal seizure types, potentially contributing to the development of personalized epilepsy monitoring and devices that improve patient quality of life or enable earlier treatment.
Competition history
- CSEF 2026
Related projects
CSEF · 2026
Filtering Electroencephalogram Data Using R: A Study on Patients with Seizures
ISEF · 2026
A Multimodal Approach to Real-Time Seizure Prediction Using Discreet Wearables
ISEF · 2020
A Biologically-inspired, Biomarker-driven, Rapid Early Warning System for Epileptic Onset Prediction and Seizure Detection Using Machine Learning
ISEF · 2016
Application of a Machine Learning Logistic Regression Algorithm in a Classification Model to Predict Epileptic Seizures
CSEF · 2026
ICAM: A Non-Invasive Low-Cost Wearable Device for Resource-Efficient Monitoring of Non-Convulsive Epileptic Seizures
JSHS · 2025
Design and Testing of an Adjustable Functional Near-Infrared Spectroscopy (fNIRS)
ISEF · 2024
Voxel-Based Morphometry and Time Frequency Analysis of Epilepsy for Detection of Ictal Impaired Consciousness
ISEF · 2018
A Rapid Prediction Method for Epileptic Seizures Using Machine Learning Algorithms
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects