SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables.
SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables.
复制标题
SeizFt：使用可穿戴设备进行癫痫发作检测的可解释机器学习。
DOI：
10.3390/bioengineering10080918
复制
发表时间：
2023-08-02
影响因子：
4.6
通讯作者：
Mitchell, Cassie S.
中科院分区：
文献类型：
--
作者：
Al-Hussaini, Irfan;Mitchell, Cassie S.
关键词：
这项工作提出了 SeizFt——一种新颖的癫痫发作检测框架，它利用机器学习使用可穿戴 SensorDot 脑电图数据自动检测癫痫发作。受可解释的睡眠分期的启发，我们的新颖方法采用了数据增强、有意义的特征提取和决策树集合的独特组合，以提高对脑电图变化的适应能力，并提高概括看不见的数据的能力。利用傅里叶变换 (FT) 替代来增加样本量并改善标记的非癫痫发作和癫痫发作时期之间的类别平衡。为了提高模型的稳定性和准确性，SeizFt 通过 CatBoost 分类器利用决策树集合将每一秒的 EEG 记录分类为癫痫发作或非癫痫发作。 SeizIt1 数据集用于训练，SeizIt2 数据集用于验证和测试。使用两个主要指标评估癫痫检测的模型性能：使用任意重叠方法 (OVLP) 的灵敏度和使用基于纪元的评分 (EPOCH) 的误报 (FA) 率。值得注意的是，作为 2023 年声学、语音和信号处理国际会议 (ICASSP) 癫痫发作检测大挑战的一部分，SeizFt 在一系列最先进的癫痫发作检测算法中排名第一。 SeizFt 在准确的癫痫检测和最大限度地减少误报方面优于最先进的黑盒模型，获得了 40.15 的总分，在两项任务中结合了 OVLP 和 EPOCH，比下一个最佳方法提高了约 30%。 SeizFt 的可解释性是一个关键优势，因为它促进了医疗保健专业人员之间的信任和问责制。从 SeizFt 中提取的最具预测性的癫痫检测特征是：delta 波、四分位距、标准差、总绝对功率、theta 波、delta 与 theta 的比率、分箱熵、Hjorth 复杂度、delta + theta 和 Higuchi 分形维数。总之，SeizFt 成功应用于可穿戴式 SensorDot 数据表明其在实时、连续监测方面具有改善癫痫个性化医疗的潜力。
This work presents SeizFt—a novel seizure detection framework that utilizes machine learning to automatically detect seizures using wearable SensorDot EEG data. Inspired by interpretable sleep staging, our novel approach employs a unique combination of data augmentation, meaningful feature extraction, and an ensemble of decision trees to improve resilience to variations in EEG and to increase the capacity to generalize to unseen data. Fourier Transform (FT) Surrogates were utilized to increase sample size and improve the class balance between labeled non-seizure and seizure epochs. To enhance model stability and accuracy, SeizFt utilizes an ensemble of decision trees through the CatBoost classifier to classify each second of EEG recording as seizure or non-seizure. The SeizIt1 dataset was used for training, and the SeizIt2 dataset for validation and testing. Model performance for seizure detection was evaluated using two primary metrics: sensitivity using the any-overlap method (OVLP) and False Alarm (FA) rate using epoch-based scoring (EPOCH). Notably, SeizFt placed first among an array of state-of-the-art seizure detection algorithms as part of the Seizure Detection Grand Challenge at the 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). SeizFt outperformed state-of-the-art black-box models in accurate seizure detection and minimized false alarms, obtaining a total score of 40.15, combining OVLP and EPOCH across two tasks and representing an improvement of ~30% from the next best approach. The interpretability of SeizFt is a key advantage, as it fosters trust and accountability among healthcare professionals. The most predictive seizure detection features extracted from SeizFt were: delta wave, interquartile range, standard deviation, total absolute power, theta wave, the ratio of delta to theta, binned entropy, Hjorth complexity, delta + theta, and Higuchi fractal dimension. In conclusion, the successful application of SeizFt to wearable SensorDot data suggests its potential for real-time, continuous monitoring to improve personalized medicine for epilepsy.
登录
查看更多内容
影响因子：
4.3
作者：
Gramfort A;Luessi M;Larson E;Engemann DA;Strohmeier D;Brodbeck C;Goj R;Jas M;Brooks T;Parkkonen L;Hämäläinen M
通讯作者：
Hämäläinen M
影响因子：
4.7
作者：
Athena, Fabia F.;West, Matthew P.;Hah, Jinho;Graham, Samuel;Vogel, Eric M.
通讯作者：
Vogel, Eric M.
DOI：
10.1109/icassp49357.2023.10097091
发表时间：
2023-06-01
期刊：
Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)
影响因子：
--
作者：
Al-Hussaini, Irfan;Mitchell, Cassie S
通讯作者：
Mitchell, Cassie S
影响因子：
4.7
作者：
Basnet, Pradip;Anderson, Erik C.;Vogel, Eric M.
通讯作者：
Vogel, Eric M.
影响因子：
2.6
作者：
Chiang, Sharon;Moss, Robert;Rao, Vikram R.
通讯作者：
Rao, Vikram R.