Non-invasive Seizure Detection Using Wearable Wrist-worn Accelerometry and Deep Learning

Nilushika Udayangani Hewa Dehigahawattage; Kishor Nandakishor; Marimuthu Palaniswami

cs.LGOct 5, 2026

Non-invasive Seizure Detection Using Wearable Wrist-worn Accelerometry and Deep Learning

Authors: Nilushika Udayangani Hewa Dehigahawattage, Kishor Nandakishor, Marimuthu Palaniswami

Organizations: dept. of Electrical and Electronic Engineering University of Melbourne Victoria, Australia

Abstract

Seizure monitoring and detection are crucial for reducing the morbidity and mortality associated with seizures. Current epilepsy care, often involving expensive video-electroencephalography (VEEG) monitoring, requires specialized expertise and is limited to in-hospital settings, and intrusive in nature. Seizure diaries, on the other hand, suffer from unreliability due to under-reporting, leading to incorrect therapeutic decisions. Wearable non-invasive seizure detection may offer a more tolerable and feasible solution for long-term ambulatory monitoring. This study explores a wearable remote monitoring system utilizing a single wrist-worn accelerometer device and capable of detecting multiple types of seizures, including shorter duration events. We enrolled 79 patients under video-electroencephalography monitoring to wear accelerometer devices and collect data. Concurrent VEEG recordings were reviewed by board-certified epileptologists to produce annotations, including seizure onset, offset, and seizure type. Using this data, we constructed a deep neural network based on the time-series ResNet architecture, which could discriminate among seizure and non-seizure events. Our proposed approach achieved a seizure detection sensitivity of 95.65% and an overall false alarm rate of 0.15/24 hours during the evaluation, which spanned 5576 hours of total recording. Additionally, it resulted in an area under the receiver operating characteristic curve (AUC-ROC) of 0.98 and an area under the precision-re call curve (AUC-PRC) of 0.67 when averaged over 20 patients who experienced 46 convulsive seizures. These promising results suggest that the proposed seizure detection system can be effectively used for long-term ambulatory seizure monitoring. Future steps include validating our findings in larger datasets and assessing the utility of detection for additional seizure types.

Figures & tables

Patient ID	#GTCS	#PNES
$P_{1}$	2	0
$P_{2}$	2	1
$P_{3}$	1	0
$P_{4}$	1	0
$P_{5}$	2	0
$P_{6}$	1	0

TABLE I: Seizure distribution among patients.

seizure duration	$\geq 10s$	$\geq 20s$	$\geq 30s$	$\geq 40s$	$\geq 50s$	$\geq 60s$
#patients	20/79	20/79	18/79	18/79	17/79	14/79
#seizures	46/46	45/46	39/46	34/46	29/46	25/46

TABLE II: Seizure Durations Distribution

Fig. 1: Overview of the Proposed Method.

Fig. 2: Time Series ResNet Architecture.

Patient ID	AUC -ROC	AUC -PRC	Sensitivity (%)	Specificity (%)	F1score (%)	PPV (%)	FAR/24h
$P_{1}$	1	1	100	100	100	100	0
$P_{2}$	1	1	100	100	100	100	0
$P_{3}$	1	1	100	100	100	100	0
$P_{4}$	0.97	0.07	100	96.92	25	14.29	2.23
$P_{5}$	1	1	100	100	100	100	0
$P_{6}$	0.99	0.13	100	99.2	40	25	0.82

TABLE III: THE LEAVE-ONE-PATIENT-OUT(LOPO) VALIDATION RESULTS FOR PATIENT GROUP PG1

Patient ID	AUC -ROC	AUC -PRC	Sensitivity (%)	Specificity (%)	F1score (%)	PPV (%)	FAR/24h
$P_{1}$	1	1	100	100	100	100	0
$P_{2}$	0.99	0.71	100	97.65	66.67	50	0.59
$P_{3}$	1	1	100	100	100	100	0
$P_{4}$	0.98	0.1	100	97.95	33.33	20	1.49
$P_{5}$	1	1	100	100	100	100	0
$P_{6}$	1	1	100	100	100	100	0

TABLE IV: THE LEAVE-ONE-PATIENT-OUT(LOPO) VALIDATION RESULTS FOR PATIENT GROUP PG2

Patient ID	AUC -ROC	AUC -PRC	Sensitivity (%)	Specificity (%)	F1score (%)	PPV (%)	FAR/24h
$P_{1}$	1	1	100	100	100	100	0
$P_{2}$	1	1	100	100	100	100	0
$P_{3}$	1	1	100	100	100	100	0
$P_{4}$	0.87	0.02	0	100	0	0	0
$P_{5}$	1	1	100	100	100	100	0
$P_{6}$	1	1	100	100	100	100	0

TABLE V: THE LEAVE-ONE-PATIENT-OUT(LOPO) VALIDATION RESULTS FOR PATIENT GROUP PG3

Patient ID	AUC -ROC	AUC -PRC	Sensitivity (%)	Specificity (%)	F1score (%)	PPV (%)	FAR/24h
$P_{1}$	1	1	100	100	100	100	0
$P_{2}$	0.99	0.76	100	98.81	85.71	75	0.29
$P_{3}$	1	1	100	100	100	100	0
$P_{4}$	0.88	0.02	0	100	0	0	0
$P_{5}$	1	1	100	100	100	100	0
$P_{6}$	1	1	100	100	100	100	0

TABLE VI: THE LEAVE-ONE-PATIENT-OUT(LOPO) VALIDATION RESULTS FOR PATIENT GROUP PG4

patient group	method	sensitivity	specificity	F1score	PPV	FAR/24h
GTCS	baseline	95.23	98.04	56.33	40	0.72
	proposed	100	99.15	76.36	61.76	0.34
GTCS+CPS	baseline	88.26	96.75	45.54	30.66	1.24
	proposed	96.15	99.44	83.33	73.53	0.2
GTCS+PNES	baseline	87.8	97.12	44.44	29.75	1.56
	proposed	90.24	99.16	71.84	59.68	0.54

TABLE VII: Result Comparison Of The Proposed Method With The Baseline Method

Fixed parameters
Study	baseline [ 45 ]	Beniczky [ 9 ]	Lockman [ 50 ]	Kramer [ 44 ]	Conradsen [ 19 ]	Szabó [ 69 ]	Agrahri [ 1 ]	Motahar [ 53 ]	Beniczky [ 7 ]	Jeppesen [ 40 ]	CNN	LSTMFCN tsai	ResNet tsai	CNN Keras (all)	ResNet tsai (all)
Sensor	1 ACM	1 ACM	1 ACM	1 ACM	1 sEMG	1 sEMG	1 ACM	1 ACM	1 sEMG	1 ECG (HRV)	1 ACM	1 ACM	1 ACM	1 ACM	1 ACM
Variable parameters
Seizure duration	$\geq 10$	–	–	$\geq 20$	$\geq 50$	–	–	1 s	–	$\geq 20$	$\geq 10$	$\geq 10$	$\geq 10$	$\geq 10$	$\geq 10$
Total patients	79	73	40	31	60	33	79	1	71	19	79	79	79	79	79
Seizure patients	12	20	6	15	11	11	35	1	20	11	12	12	12	20	20

TABLE VIII: Comparison of the proposed study with seizure detection systems based on a single sensor.

Explore similar work

Jul 13, 2026cs.LG

DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations

Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses both limitations through denoising diffusion pre-training and reinforcement learning (RL)-based fine-tuning. Pre-trained on 1.3M unlabeled segments from the Temple University Hospital Seizure Corpus (TUHSZ), DiffEEG learns generic neural representations via a 1D U-Net with multi-head self-attention. For downstream adaptation, a reinforced decision layer employs policy gradient optimization to directly maximize F1-score, prioritizing sensitivity to rare seizure events over overall accuracy. Under strict patient-wise evaluation (279 patients, Leave-One-Fold-Out), DiffEEG achieves 61% accuracy and 59% F1 for 4-class seizure subtyping, and 81% accuracy with 85% weighted F1 for binary detection, maintaining clinically viable seizure recall (59%) despite extreme imbalance (6.7% prevalence). Segment-level evaluation establishes an upper bound of 97.6% accuracy, confirming strong architectural capacity. DiffEEG demonstrates that diffusion-based pre-training combined with metric-aware reinforcement learning enables clinically deployable seizure monitoring with minimal labeled data requirements.

Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri +2

Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon · Institute of Applied Artificial Intelligence, T´ELUQ University, Montreal, Canada

Seizure Detection Deep Learning Denoising Diffusion Probabilistic Model

Ask PDF

Apr 29, 2026cs.CV

A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection

Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-based methods are easily confounded by benign behaviors, whereas EEG-based methods are vulnerable to ictal motion artifacts. We present EEGVFusion, a multimodal framework that combines self-supervised EEG representation learning, spatio-temporal video encoding, optimal-transport alignment, and bidirectional cross-attention to integrate neural and behavioral evidence. We also curate an expert-annotated dataset of synchronized EEG and video recordings comprising 93 sessions from 15 mice for training and evaluation. In the random-session split, EEGVFusion achieved a Balanced Accuracy of 0.9957 with perfect event sensitivity and an Event FAR of 0.6250 FP/h, indicating strong seizure detection performance with a low false-alarm burden. In a single held-out-subject evaluation with Subject 110 reserved for testing, EEGVFusion achieved a Balanced Accuracy of 0.9718 and reduced Event FAR from 2.7250 FP/h for the EEG-only counterpart to 0.4833 FP/h while preserving perfect event sensitivity. Targeted ablations further showed that EEG pre-training and OT alignment help reduce false alarms while preserving event sensitivity.

Tong Lu, Ke Xu, Zimo Zhang +12

Beijing Institute for Brain Research, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 102206, China · Chinese Institute for Brain Research, Beijing, Beijing, 102206, China · Department of Neurosurgery, SanBo Brain Hospital, Capital Medical University, Beijing, 100018, China +4

Seizure Detection

Ask PDF

Jun 20, 2026cs.LG

From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks

Electroencephalogram (EEG) analysis remains the clinical gold standard for epilepsy diagnosis and seizure detection. While Deep Learning (DL) has significantly advanced automated EEG interpretation, its transition from controlled experimental settings to routine clinical deployment is severely bottlenecked by fundamental architectural flaws. Standard DL models operate as opaque black-boxes lacking clinical interpretability, demand massive amounts of balanced annotated data, and incur steep computational costs incompatible with resource-constrained wearable or implantable neuromodulation devices. This paper presents a comprehensive review of these prevailing limitations and explores Kolmogorov-Arnold Networks (KANs) as a emerging paradigm for EEG-based seizure detection. By replacing the fixed activation functions of traditional neurons with flexible, learnable functions along the network's connections, KANs bridge the critical gap between predictive accuracy and mathematical transparency. We systematically analyze how KAN architectures resolve the shortcomings of traditional DL-based models by offering exceptional parameter efficiency, inherent interpretability for physician trust, and robust performance under data scarcity. Ultimately, this review establishes KANs not merely as an incremental algorithmic update, but as a fundamental paradigm shift necessary to actualize next-generation, patient-specific, and thoroughly transparent clinical EEG monitoring systems.

Sepideh Kheirollahi, Mohammad Rasoul Roshanshah

School of Electrical and Computer Engineering College of Engineering, University of Tehran Tehran, Iran

Seizure Detection Electroencephalography Electrocardiogram Classification Adaptive Deep Brain Stimulation Deep Learning Kolmogorov-Arnold Networks+3

Ask PDF