Perellón-Alfonso Ruben, Oblak Aleš, Kuclar Matija, Škrlj Blaž, Pileckyte Indre, Škodlar Borut, Pregelj Peter, Abellaneda-Pérez Kilian, Bartrés-Faz David, Repovš Grega, Bon Jurij
Faculty of Medicine and Health Sciences, and Institute of Neurosciences, University of Barcelona, Barcelona, Spain.
Institute of Biomedical Research August Pi i Sunyer (IDIBAPS), Barcelona, Spain.
Front Psychiatry. 2023 Sep 25;14:1205119. doi: 10.3389/fpsyt.2023.1205119. eCollection 2023.
Patients with schizophrenia typically exhibit deficits in working memory (WM) associated with abnormalities in brain activity. Alterations in the encoding, maintenance and retrieval phases of sequential WM tasks are well established. However, due to the heterogeneity of symptoms and complexity of its neurophysiological underpinnings, differential diagnosis remains a challenge. We conducted an electroencephalographic (EEG) study during a visual WM task in fifteen schizophrenia patients and fifteen healthy controls. We hypothesized that EEG abnormalities during the task could be identified, and patients successfully classified by an interpretable machine learning algorithm.
We tested a custom dense attention network (DAN) machine learning model to discriminate patients from control subjects and compared its performance with simpler and more commonly used machine learning models. Additionally, we analyzed behavioral performance, event-related EEG potentials, and time-frequency representations of the evoked responses to further characterize abnormalities in patients during WM.
The DAN model was significantly accurate in discriminating patients from healthy controls, = 0.69, SD = 0.05. There were no significant differences between groups, conditions, or their interaction in behavioral performance or event-related potentials. However, patients showed significantly lower alpha suppression in the task preparation, memory encoding, maintenance, and retrieval phases (1,28) = 5.93, = 0.022, η = 0.149. Further analysis revealed that the two highest peaks in the attention value vector of the DAN model overlapped in time with the preparation and memory retrieval phases, as well as with two of the four significant time-frequency ROIs.
These results highlight the potential utility of interpretable machine learning algorithms as an aid in diagnosis of schizophrenia and other psychiatric disorders presenting oscillatory abnormalities.
精神分裂症患者通常表现出与大脑活动异常相关的工作记忆（WM）缺陷。连续WM任务的编码、维持和检索阶段的改变已得到充分证实。然而，由于症状的异质性及其神经生理基础的复杂性，鉴别诊断仍然是一项挑战。我们对15名精神分裂症患者和15名健康对照者在视觉WM任务期间进行了脑电图（EEG）研究。我们假设在任务期间可以识别出EEG异常，并通过可解释的机器学习算法成功对患者进行分类。
我们测试了一种定制的密集注意力网络（DAN）机器学习模型，以区分患者和对照受试者，并将其性能与更简单、更常用的机器学习模型进行比较。此外，我们分析了行为表现、事件相关EEG电位以及诱发反应的时频表示，以进一步表征患者在WM期间的异常情况。
DAN模型在区分患者和健康对照者方面具有显著的准确性，=0.69，标准差=0.05。在行为表现或事件相关电位方面，组间、条件或它们的相互作用没有显著差异。然而，患者在任务准备、记忆编码、维持和检索阶段的α波抑制明显较低（1,28）=5.93，=0.022，η=0.149。进一步分析表明，DAN模型注意力值向量中的两个最高峰在时间上与准备和记忆检索阶段重叠，也与四个显著时频ROI中的两个重叠。
这些结果突出了可解释机器学习算法在辅助诊断精神分裂症和其他表现出振荡异常的精神疾病方面的潜在效用。
