Cogninet Australia, Sydney, NSW, 2010, Australia.
School of Engineering, Nanyang Polytechnic, Singapore.
Comput Biol Med. 2023 Sep;164:107312. doi: 10.1016/j.compbiomed.2023.107312. Epub 2023 Aug 5.
Epilepsy is one of the most common neurological conditions globally, and the fourth most common in the United States. Recurrent non-provoked seizures characterize it and have huge impacts on the quality of life and financial impacts for affected individuals. A rapid and accurate diagnosis is essential in order to instigate and monitor optimal treatments. There is also a compelling need for the accurate interpretation of epilepsy due to the current scarcity in neurologist diagnosticians and a global inequity in access and outcomes. Furthermore, the existing clinical and traditional machine learning diagnostic methods exhibit limitations, warranting the need to create an automated system using deep learning model for epilepsy detection and monitoring using a huge database.
The EEG signals from 35 channels were used to train the deep learning-based transformer model named (EpilepsyNet). For each training iteration, 1-min-long data were randomly sampled from each participant. Thereafter, each 5-s epoch was mapped to a matrix using the Pearson Correlation Coefficient (PCC), such that the bottom part of the triangle was discarded and only the upper triangle of the matrix was vectorized as input data. PCC is a reliable method used to measure the statistical relationship between two variables. Based on the 5 s of data, single embedding was performed thereafter to generate a 1-dimensional array of signals. In the final stage, a positional encoding with learnable parameters was added to each correlation coefficient's embedding before being fed to the developed EpilepsyNet as input data to epilepsy EEG signals. The ten-fold cross-validation technique was used to generate the model.
Our transformer-based model (EpilepsyNet) yielded high classification accuracy, sensitivity, specificity and positive predictive values of 85%, 82%, 87%, and 82%, respectively.
The proposed method is both accurate and robust since ten-fold cross-validation was employed to evaluate the performance of the model. Compared to the deep models used in existing studies for epilepsy diagnosis, our proposed method is simple and less computationally intensive. This is the earliest study to have uniquely employed the positional encoding with learnable parameters to each correlation coefficient's embedding together with the deep transformer model, using a huge database of 121 participants for epilepsy detection. With the training and validation of the model using a larger dataset, the same study approach can be extended for the detection of other neurological conditions, with a transformative impact on neurological diagnostics worldwide.
癫痫是全球最常见的神经系统疾病之一，也是美国第四大常见疾病。其特征是反复发作的非诱发性癫痫发作，对患者的生活质量和经济状况都有巨大影响。为了进行最佳治疗，快速准确的诊断至关重要。由于神经科诊断医生的短缺以及全球在获取和结果方面的不平等，因此对癫痫的准确解读也有强烈的需求。此外，现有的临床和传统机器学习诊断方法存在局限性，因此需要创建一个使用深度学习模型的自动化系统，该系统使用大型数据库来进行癫痫检测和监测。
使用来自 35 个通道的 EEG 信号来训练基于深度学习的变压器模型，名为（EpilepsyNet）。对于每个训练迭代，从每个参与者中随机抽取 1 分钟的数据。此后，将每个 5 秒的时段映射到矩阵上，使用 Pearson 相关系数（PCC），这样就丢弃了三角形的底部，只将矩阵的上三角矢量化为输入数据。PCC 是一种可靠的方法，用于衡量两个变量之间的统计关系。基于 5 秒的数据，然后进行单个嵌入，以生成一维信号数组。在最后阶段，将可学习参数的位置编码添加到每个相关系数的嵌入中，然后将其作为输入数据提供给开发的 EpilepsyNet，以用于癫痫 EEG 信号。该模型使用十折交叉验证技术生成。
我们基于变压器的模型（EpilepsyNet）产生了 85%、82%、87%和 82%的高分类准确性、灵敏度、特异性和阳性预测值。
由于使用十折交叉验证评估模型的性能，因此所提出的方法既准确又稳健。与现有的用于癫痫诊断的深度学习模型相比，我们提出的方法简单且计算量小。这是最早的一项研究，它独特地将可学习参数的位置编码应用于每个相关系数的嵌入，并与一个包含 121 名参与者的大型数据库一起，使用深度变压器模型来检测癫痫。通过使用更大的数据集对模型进行训练和验证，相同的研究方法可以扩展到其他神经疾病的检测，从而对全球神经诊断产生变革性的影响。
