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

DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
Jul 13, 2026Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri +2Seizure Detection Deep Learning
Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon · Institute of Applied Artificial Intelligence, T´ELUQ University, Montreal, Canada
A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection
Apr 29, 2026Tong Lu, Ke Xu, Zimo Zhang +12Seizure Detection
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
From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks
Jun 20, 2026Sepideh Kheirollahi, Mohammad Rasoul RoshanshahSeizure Detection Electroencephalography
School of Electrical and Computer Engineering College of Engineering, University of Tehran Tehran, Iran

Jul 13, 2026, cs.LGJ/K move · Enter open · S save

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

Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri, Belkacem Chikhaoui+1

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

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

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

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