Preictal period optimization for deep learning-based epileptic seizure prediction

计算机科学 句号(音乐) 人工智能 癫痫 癫痫发作 机器学习 神经科学 心理学 声学 物理
作者
Petros Koutsouvelis,Bartlomiej Chybowski,Alfredo Gonzalez‐Sulser,Shima Abdullateef,Javier Escudero
出处
期刊:Journal of Neural Engineering [IOP Publishing]
卷期号:21 (6): 066040-066040 被引量:17
标识
DOI:10.1088/1741-2552/ad9ad0
摘要

Abstract Objective. Accurate seizure prediction could prove critical for improving patient safety and quality of life in drug-resistant epilepsy. While deep learning-based approaches have shown promising performance using scalp electroencephalogram (EEG) signals, the incomplete understanding and variability of the preictal state imposes challenges in identifying the optimal preictal period (OPP) for labeling the EEG segments. This study introduces novel measures to capture model behavior under different preictal definitions and proposes a data-centric deep learning methodology to identify the OPP. Approach. We trained a competent subject-specific CNN-Transformer model to detect preictal EEG segments using the open-access CHB-MIT dataset. To capture the temporal dynamics of the model’s predictions, we fitted a sigmoidal curve to the model outputs obtained from uninterrupted multi-hour EEG recordings prior to seizure onset. From this fitted curve, we derived key performance measures reflecting the timing of predictions, including classifier convergence, average error, output stability, and the transition between interictal and preictal states. These measures were then combined to compute the Continuous Input–Output Performance Ratio, a novel metric designed to comprehensively compare model behavior across different preictal definitions (60, 45, 30, and 15 min) and suggest the OPP for each patient. Main results. The CNN-Transformer model achieved state-of-the-art performance (area under the curve of 99.35% and F1-score of 97.46%) using minimally pre-processed EEG signals. The 60-minute preictal definition was associated with earlier seizure prediction, lower error in the preictal state, and reduced output fluctuations, leading to significantly higher CIOPR scores (p < 0.001). Conventional accuracy-related metrics (sensitivity, specificity, F1-score) were less sensitive to varying preictal definitions and often discordant with CIOPR findings. Cross- and intra-patient heterogeneities in the prediction times were also observed, complicating the establishment of a global preictal interval. Significance. The newly developed metrics demonstrate that varying the preictal period significantly impacts the timing of predictions in ways not captured by conventional accuracy-related metrics. Understanding this impact and the inter-seizure heterogeneities is essential for developing intelligent systems tailored to individual patient needs and for underlining practical limitations in detecting the preictal period in real-world clinical applications.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
SY完成签到,获得积分10
刚刚
领导范儿的应助被lnww采纳,获得10
刚刚
从容太兰发布了新的文献求助10
刚刚
zcyuqing发布了新的文献求助10
刚刚
刚刚
AAA院士杰青批发完成签到,获得积分10
刚刚
刚刚
Porkpike发布了新的文献求助10
刚刚
某个角度发布了新的文献求助10
刚刚
华仔的应助被dhx采纳,获得10
刚刚
赴山珩发布了新的文献求助10
1秒前
徐雨发布了新的文献求助30
1秒前
Jasper的应助被闪闪的灵采纳,获得10
2秒前
null的应助被zhuwei采纳,获得10
2秒前
周周发布了新的文献求助10
2秒前
2秒前
斯文败类的应助被莫笑采纳,获得10
2秒前
王彬发布了新的文献求助10
2秒前
2秒前
stephenzhou发布了新的文献求助10
2秒前
郭芙蓉完成签到,获得积分10
3秒前
wp发布了新的文献求助10
4秒前
4秒前
cc发布了新的文献求助10
4秒前
科研通AI6.4的应助被七月清风采纳,获得10
4秒前
乐乐的应助被爱笑夜蕾采纳,获得10
4秒前
背后的胡萝卜完成签到,获得积分10
4秒前
4秒前
JH.Zhao发布了新的文献求助10
4秒前
木木发布了新的文献求助10
5秒前
5秒前
彭于彦祖的应助被飘逸的太阳采纳,获得30
5秒前
samo发布了新的文献求助10
5秒前
FanFan发布了新的文献求助10
5秒前
5秒前
Bsisoy发布了新的文献求助100
5秒前
婷玉完成签到,获得积分10
5秒前
科研通AI6.2的应助被aspirant采纳,获得10
6秒前
hope完成签到 ,获得积分10
6秒前
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8162755
求助须知:如何正确求助?哪些是违规求助? 9557016
关于积分的说明 21737907
捐赠科研通 7753093
什么是DOI,文献DOI怎么找? 3427901
关于科研通互助平台的介绍 2552719
邀请新用户注册赠送积分活动 2472528