Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis.
Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis.
复制标题
DOI：
10.3390/brainsci12111497
复制
发表时间：
2022-11-04
期刊：
影响因子：
3.3
通讯作者：
Ferrarelli, Fabio
中科院分区：
文献类型：
--
作者：
Keihani, Ahmadreza;Sajadi, Seyed Saman;Hasani, Mahsa;Ferrarelli, Fabio
关键词：
静息态脑电图（EEG）的微观状态反映了亚秒级的、准稳定的大脑活动状态。几项研究报道了精神分裂症（SZ）患者微观状态特征的改变。基于这些发现，有人建议，microstates可能代表神经生理学生物标志物的分类SZ。为了探索这种可能性，可以采用机器学习方法。贝叶斯优化是一种机器学习方法，它从现有模型中选择具有调整超参数的最佳拟合机器学习模型来改进分类。在这项基于二次分析的概念验证初步研究中，从14名SZ患者和14名健康对照者的EEG信号中提取了20个微观状态特征。然后，根据这些参数的重要性将其列为预测因子，并应用优化的机器学习方法来评估分类的性能。与健康对照组相比，SZ患者的微观特征发生了改变。此外，贝叶斯优化优于传统的多变量分析，并显示出最高的准确性（90.93%），AUC（0.90），灵敏度（91.37%）和特异性（90.48%），仅使用6个微观预测因子就获得了可靠的结果。总之，在这项概念验证研究中，我们表明，贝叶斯优化的机器学习可用于表征EEG微状态改变，并有助于SZ患者的分类。
Resting-state electroencephalography (EEG) microstates reflect sub-second, quasi-stable states of brain activity. Several studies have reported alterations of microstate features in patients with schizophrenia (SZ). Based on these findings, it has been suggested that microstates may represent neurophysiological biomarkers for the classification of SZ. To explore this possibility, machine learning approaches can be employed. Bayesian optimization is a machine learning approach that selects the best-fitted machine learning model with tuned hyperparameters from existing models to improve the classification. In this proof-of-concept preliminary study based on secondary analysis, 20 microstate features were extracted from 14 SZ patients and 14 healthy controls’ EEG signals. These parameters were then ranked as predictors based on their importance, and an optimized machine learning approach was applied to evaluate the performance of the classification. SZ patients had altered microstate features compared to healthy controls. Furthermore, Bayesian optimization outperformed conventional multivariate analyses and showed the highest accuracy (90.93%), AUC (0.90), sensitivity (91.37%), and specificity (90.48%), with reliable results using just six microstate predictors. Altogether, in this proof-of-concept study, we showed that machine learning with Bayesian optimization can be utilized to characterize EEG microstate alterations and contribute to the classification of SZ patients.
登录
查看更多内容
影响因子：
4.8
作者：
Kam, Julia W. Y.;Bolbecker, Amanda R.;O'Donnell, Brian F.;Hetrick, William P.;Brenner, Colleen A.
通讯作者：
Brenner, Colleen A.
影响因子：
5.7
作者：
Britz, Juliane;Van De Ville, Dimitri;Michel, Christoph M.
通讯作者：
Michel, Christoph M.
DOI：
10.1176/appi.ajp.2020.20070968
发表时间：
2021-10-01
期刊：
The American journal of psychiatry
影响因子：
--
作者：
Ferrarelli F
通讯作者：
Ferrarelli F
影响因子：
6.6
作者：
Kambeitz, Joseph;Kambeitz-Ilankovic, Lana;Malchow, Berend
通讯作者：
Malchow, Berend
影响因子：
7.7
作者：
Bagherzadeh, Sara;Shahabi, Mohsen Sadat;Shalbaf, Ahmad
通讯作者：
Shalbaf, Ahmad