A pilot study of machine learning of resting-state EEG and depression in Parkinson's disease.
A pilot study of machine learning of resting-state EEG and depression in Parkinson's disease.
复制标题
DOI：
10.1016/j.prdoa.2022.100166
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Narayanan, Nandakumar S.
中科院分区：
文献类型：
--
作者：
Espinoza, Arturo I.;May, Patrick;Anjum, Md Fahim;Singh, Arun;Cole, Rachel C.;Trapp, Nicholas;Dasgupta, Soura;Narayanan, Nandakumar S.
关键词：
我们用脑电图分析帕金森病的抑郁症状。抑郁性PD患者与非抑郁性PD和无PD的抑郁患者相比具有不同的频谱EEG。频谱脑电图有助于了解PD抑郁的神经生理基础。机器学习算法可以帮助区分帕金森病中的抑郁症。抑郁症是帕金森病（PD）的一种非运动症状。PD相关的抑郁症很难诊断，神经生理学基础也知之甚少。抑郁对大脑皮层功能有明显影响，提示头皮脑电图（EEG）可能有助于区分PD患者的抑郁状态。我们进行了一项初步研究抑郁症和静息态脑电图在PD。我们招募了18名无抑郁症的PD患者，18名有抑郁症的PD患者和12名人口统计学相似的有临床抑郁症的非PD患者。所有患者均接受常规药物治疗。我们收集了所有患者的静息态脑电图，并比较了抑郁症患者和非抑郁症患者的大脑皮质信号特征。我们使用了一种利用整个功率谱的机器学习算法（PD EEG算法的线性预测编码：LEAPD）来区分各组。我们发现有抑郁症和无抑郁症的PD患者在α频段（8-13 Hz）以及中央电极的β频段（13-30 Hz）和γ频段（30-50 Hz）存在差异。从两分钟的静息状态EEG中，我们发现基于LEAPD的机器学习可以以97%的准确率稳健地区分有抑郁症和无抑郁症的PD患者，并以100%的准确率区分有抑郁症的PD患者和有抑郁症的非PD患者。我们通过确认分类准确性随着数据被随机截断而优雅地下降来验证我们发现的鲁棒性。我们的研究结果表明，静息态脑电功率谱分析有可能区分抑郁症的PD准确。我们证明了LEAPD算法在识别PD患者抑郁症的PD患者无抑郁症和对照抑郁症的有效性。我们的数据提供了深入了解抑郁症的皮质机制，并可能导致新的神经生理学标记物的非运动症状的PD。
We used EEG to analyze depression in Parkinson’s disease. Depressed PD patients have different spectral EEG compared to non-depressed PD and depressed patients without PD. Spectral EEG can contribute to the understanding of the neurophysiological basis depression in PD. Machine learning algorithms can help distinguish depression in Parkinson's disease. Depression is a non-motor symptom of Parkinson’s disease (PD). PD-related depression is difficult to diagnose, and the neurophysiological basis is poorly understood. Depression can markedly affect cortical function, which suggests that scalp electroencephalography (EEG) may be able to distinguish depression in PD. We conducted a pilot study of depression and resting-state EEG in PD. We recruited 18 PD patients without depression, 18 PD patients with depression, and 12 demographically similar non-PD patients with clinical depression. All patients were on their usual medications. We collected resting-state EEG in all patients and compared cortical brain signal features between patients with and without depression. We used a machine learning algorithm that harnesses the entire power spectrum (linear predictive coding of EEG Algorithm for PD: LEAPD) to distinguish between groups. We found differences between PD patients with and without depression in the alpha band (8–13 Hz) globally and in the beta (13–30 Hz) and gamma (30–50 Hz) bands in the central electrodes. From two minutes of resting-state EEG, we found that LEAPD-based machine learning could robustly distinguish between PD patients with and without depression with 97 % accuracy and between PD patients with depression and non-PD patients with depression with 100 % accuracy. We verified the robustness of our finding by confirming that the classification accuracy gracefully declines as data are randomly truncated. Our results suggest that resting-state EEG power spectral analysis has the potential to distinguish depression in PD accurately. We demonstrated the efficacy of the LEAPD algorithm in identifying PD patients with depression from PD patients without depression and controls with depression. Our data provide insight into cortical mechanisms of depression and could lead to novel neurophysiological markers for non-motor symptoms of PD.
登录
查看更多内容
DOI：
10.1176/appi.neuropsych.20100268
发表时间：
2021
期刊：
The Journal of neuropsychiatry and clinical neurosciences
影响因子：
--
作者：
Bormann NL;Trapp NT;Narayanan NS;Boes AD
通讯作者：
Boes AD
影响因子：
2.6
作者：
Gotlib, IH;Ranganath, C;Rosenfeld, JP
通讯作者：
Rosenfeld, JP
影响因子：
6.6
作者：
Dissanayaka, Nadeeka N. W.;Au, Tiffany R.;Copland, David A.
通讯作者：
Copland, David A.
影响因子：
3.2
作者：
PRIMAVERA, A;NOVELLO, P
通讯作者：
NOVELLO, P
DOI：
10.1038/s41531-021-00158-x
发表时间：
2021-02-15
期刊：
NPJ Parkinson's disease
影响因子：
--
作者：
Singh A;Cole RC;Espinoza AI;Evans A;Cao S;Cavanagh JF;Narayanan NS
通讯作者：
Narayanan NS