可解释性人工智能用于可穿戴性发作记录:数据质量,患者年龄和抗药物对表现的影响
Mustafa Halimeh1, Michele Jackson2, Solveig Vieluf2
1Computational Neurology Lab, Department of Neurology, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany.
Seizure
|June 19, 2023
概括
可穿戴设备可以通过分析长时间的生理数据来估计患者的发作数量,随着年龄的增长,性能会有所改善. 诸如药物和持续时间等因素影响检测准确度,指导技术对个人有益.
科学领域:
- 生物医学工程 生物医学工程
- 神经学 神经学
- 数字健康数字健康
背景情况:
- 目标性发作计数对于管理至关重要,特别是在门诊环境中.
- 可穿戴式传感器显示出检测强力克隆发作的潜力,但面临着错误报警和错过事件的挑战.
- 现有的检测方法未充分利用长时间的生理特征,如电皮活动和心率变化.
研究的目的:
- 评估使用可穿戴数据进行发作计数的延长后性生理特征的实用性.
- 确定影响基于可穿戴设备的发作记录性能的因素,区分数据质量和算法限制.
- 为了确定哪些患者可能从可穿戴监控技术中受益最多.
主要方法:
- 在视频EEG监测期间使用可穿戴设备 (Empatica E4) 的76名儿科患者的回顾性分析.
- 深度学习模型应用于多式联网数据 (EDA,ACC,HR) 在1小时段进行日志查获.
- 系统地检查影响表现的因素,包括患者年龄,抗发作药物 (ASM) 负载,发作特征和数据工件.
- 利用UMAP和SHAP进行算法可解释性和特征重要性分析.
主要成果:
- 随着患者年龄的增长,发作记录的性能有所改善,较老年人群的曲线下面面积 (AUC) 值更高 (AUC为>15岁的0.85).
- 总体AUC为0.75,灵敏度为0.52,误报率为0.28/24小时.
- 较高的ASM负载和较短的发作持续时间与较差的检测相关 (P=.025,P=.033).
- SHAP分析确定了运动活动和周围/后体HR/EDA增加作为关键信息特征;这些在错过的中缺少表明记录质量问题.
结论:
- 长时间的直后数据段对于使用可穿戴设备的发作记录是有价值的.
- 算法可解释性得到了增强,突出了后生理变化的重要性.
- 高剂量的ASM和短暂的发作时间是限制检测准确性的关键因素.
- 这些发现有助于识别最有可能从可穿戴监测中受益的患者.
更多相关视频
08:43Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System
Published on: July 21, 2015
25.7K
09:16Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
Published on: June 21, 2019
25.7K
相关概念视频
Epilepsy and Seizures: Overview
230
Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
230
Seizures: Classification
443
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
443
