重度憂鬱症(Major Depressive Disorder, MDD)和阿茲海默症(Alzheimer's Disease, AD)是兩種常見腦神經疾病，其症狀在早期可能非常相似，都可能出現認知功能減退、記憶力下降、興趣與活力缺乏等問題。然而，過去的研究主要集中在疾病患者和健康受試者之間的研究，較缺少對不同疾病患者間的差異研究。因此本論文首先蒐集了MDD、輕度認知障礙(Mild Cognitive Impairment, MCI)與AD的腦電圖(Electroencephalography, EEG)，並進行了MDD與MCI以及MDD與AD的差異比較分析。接著進一步的探索過去研究中較少被探討的電極間相對功率(Relative Power, RP)，以及三種功能性連結特徵—相干性(Magnitude-squared Coherence, Coh)、虛部相干性(Imaginary part of Coherence, ImC)與相位延遲指數(Phase lag index, PLI)。最後，由於不確定每位受測者休息狀態的一致性以及各疾病對於認知能力的影響，本研究設計了前後測休息狀態結合不同難度的記憶任務之腦機介面，並進一步開發了一個跨時域和頻域的鑑別MDD之跨域指標，以作為未來臨床上MDD鑑別的輔助診斷工具。
基於休息狀態腦電圖訊號分析中，透過費雪最佳特徵演算法找出最佳特徵集合，並使用特徵遞增準則(Add-one-feature-in strategy, AOFI)以及基於線性鑑別分析(Linear Discriminant Analysis, LDA)分類器，搭配隨機與非隨機兩種留一個體驗證(Leave-One-Participant-Out Cross Validation, LOPO-CV)分析方法進行MDD鑑別分析。結果顯示，相干性可能是具高穩定性及鑑別力的MDD腦波標記。基於不同難度的記憶任務腦電圖訊號分析中，使用單一特徵與混合特徵兩種分析流程。其中，在混合特徵分析，使用費雪最佳特徵演算法搭配特徵遞增準則以及序列前項選擇(Sequential forward selection, SFS)兩種特徵篩選方法，與有無做基準線校正的記憶任務腦波，進行四種比較的分析探討。結果顯示，有做基準線校正的記憶任務腦波使用混合特徵，並搭配SFS特徵篩選方法，在Task_level3時皆有100%的鑑別準確率，並且根據結果，本研究進一步發展罹患疾病類別可能性指標，為未來臨床上提供更加準確且客觀的MDD鑑別輔助診斷。

Major Depressive Disorder (MDD) and Alzheimer's Disease (AD) are two common neurological disorders, and their symptoms can be very similar in the early stages. Both conditions may exhibit problems such as cognitive decline, memory impairment, and lack of interest and energy, leading to potential misdiagnosis due to the similarity of symptoms. However, previous research has mainly focused on studying the differences between disease patients and healthy controls, lacking studies on the differences among different disease patients. Therefore, this study first collected Electroencephalography (EEG) data for MDD, Mild Cognitive Impairment (MCI), and AD, and conducted comparative analyses between MDD and MCI, as well as between MDD and AD. Furthermore, the study explored the less investigated relative power (RP) between electrodes and three functional connectivity features: magnitude-squared coherence (Coh), imaginary part of coherence (ImC), and phase lag index (PLI). Finally, considering the uncertainty of each participant's resting state consistency and the impact of each disease on cognitive abilities, the study designed a brain-computer interface combining pre- and post-resting states with memory tasks of varying difficulty. Additionally, a cross-domain index for discriminating MDD was developed in both the time and frequency domains as an auxiliary diagnostic tool for future clinical differentiation of MDD.
Based on the analysis of resting state EEG signals, the Fisher optimal feature algorithm was used to identify the best feature set. The feature increment criterion (Add-one-feature-in strategy, AOFI) and Linear Discriminant Analysis (LDA) classifier were employed, along with two types of leave-one-participant-out cross-validation (LOPO-CV) analysis methods: random and non-random. These methods were utilized for MDD discrimination analysis. The results indicated that coherence may be a highly stable and discriminative EEG marker for MDD. For the analysis of memory task EEG signals with different difficulty levels, two analysis processes were employed: single-feature and mixed-feature. In the mixed-feature analysis, the Fisher optimal feature algorithm, along with feature increment criterion and Sequential Forward Selection (SFS) feature selection methods, were used to compare four types of analyses with and without baseline-corrected memory task EEG. The results showed that using mixed features with SFS feature selection and baseline-corrected memory task EEG achieved 100% discrimination accuracy at Task_level3. Based on these findings, the study further developed a probability index for disease occurrence, providing more accurate and objective assistance for the differential diagnosis of MDD in future clinical settings.

[1] World Health Organization. “Depressive disorder (depression).”
https://www.who.int/news-room/fact-sheets/detail/depression (accessed July. 3, 2023).
[2] C. T. Wu, D. G. Dillon, H. C. Hsu, S. Huang, E. Barrick, and Y. H. Liu, “Depression detection using relative EEG power induced by emotionally positive images and a conformal kernel support vector machine,” Appl Sci., vol. 8, no. 8, 2018.
[3] World Health Organization. “Global status report on the public health response to dementia.”
https://www.who.int/publications/i/item/9789240033245 (accessed July. 3, 2023).
[4] 台灣失智症協會, ”台灣失智症人口推估,” 台灣失智症協會, Apr.2021.
[5] 莊凱迪、蔡佳芬（2008）。老年人的憂鬱症。台灣老年醫學暨老年學雜誌，第三卷第二期，頁182-190。
[6] S. Gauthier, B. Reisberg, M. Zaudig, R. C. Petersen, K. Ritchie, K. Broich, S. Belleville, H. Brodaty, D. Bennett, H. Chertkow, J. L. Cummings, M. D. Leon, H. Feldman, M. Ganguli, H. Hampel, P. Scheltens, M. C. Tierney, P. Whitehouse, and B. Winblad, “Mild cognitive impairment,” The lancet, vol. 367, 2006.
[7] R. C. Petersen, “Mild cognitive impairment,” The Lancet, vol. 367, no. 9527, p. 1979, 2006. doi:10.1016/s0140-6736(06)68881-8
[8] Dubois, B., Feldman, H. H., Jacova, C., DeKosky, S. T., Barberger-Gateau, P., Cummings, J., and Scheltens, P, “Research criteria for the diagnosis of Alzheimer's disease: revising the NINCDS–ADRDA criteria,” The Lancet Neurology, vol. 6, no. 8, pp. 734–746, 2007.
[9] Alzheimer association, “2020 Alzheimer’s disease facts and figures,” Alzheimer’s and dementia, 2020.
[10] C. J. Stam, G. Nolte, and A. Daffertshofer, “Phase lag index: Assessment of functional connectivity from multi channel EEG and Meg with diminished bias from common sources,” Human Brain Mapping, vol. 28, pp. 1178–1193, 2007.
[11] J. Poza, C. Gómez, M. García, M. A. Tola-Arribas, A. Carreres, M. Cano, and R. Hornero, “Spatio-temporal fluctuations of neural dynamics in mild cognitive impairment and alzheimer's disease,” Curr Alzheimer Research, vol. 14, no. 9, pp. 924-936, 2017.
[12] J. H. Roh, M. H. Park, D. Ko, K. Park, D. Lee, C. Han, S. A. Jo, K. Yang, and K. Jung, “Region and frequency specific changes of spectral power in Alzheimer’s disease and mild cognitive impairment,” Clin Neurophysiology, vol. 122, no. 11, pp. 2169-2176, 2011.
[13] E. Neto, F. Biessmann, H. Aurlien, H. Nordby, and T. Eichele, “Regularized linear discriminant analysis of EEG features in dementia patients,” Front Aging Neuroscience, vol. 8, no. 30, pp. 273, 2016.
[14] N. N. Kulkarni, V. K. Bairagi, “Extracting salient features for EEG-based diagnosis of alzheimer's disease using support vector machine classifier,” IETE J Research, vol. 63, no. 1, pp. 11-22, 2017.
[15] C. T. Wu, D. G. Dillon, H. C. Hsu, S. Huang, E. Barrick, and Y. H. Liu, “Depression detection using relative EEG power induced by emotionally positive images and a conformal kernel support vector machine,” Appl Sciences, vol. 8, 2018.
[16] S. C. Liao, C. T. Wu, H. C. Huang, W. T. Chen, and Y. H. Liu, “Major depression detection from EEG signals using kernel eigen-filter-bank common spatial patterns, ” Sensors (Basel, Switzerland), vol. 17, no. 6, pp. 1385, 2017.
[17] H. Mohammed and M. Diykh, “Improving EEG major depression disorder classification using FBSE coupled with domain adaptation method based machine learning algorithms,” Biomedical Signal Processing and Control, vol. 85, p. 104923, 2023.
[18] B. Jiao et al., “Neural biomarker diagnosis and prediction to mild cognitive impairment and alzheimer’s disease using EEG Technology,” Alzheimer’s Research & Therapy, vol. 15, no. 1, 2023.
[19] C. E. Jackson, P. J. Snyder, “Electroencephalography and event-related potentials as biomarkers of mild cognitive impairment and mild Alzheimer’s disease,” Alzheimer's & Dementia, vol. 4, Issue 1, Supplement 1, pp. 137-143, 2008.
[20] N. Sharma, M.H. Kolekar, K. Jha, Y. Kumar, “EEG and Cognitive Biomarkers Based Mild Cognitive Impairment Diagnosis,” IRBM, vol. 40, Issue 2, pp. 113-121, 2019.
[21] World Health Organization. “Dementia.”
https://www.who.int/news-room/fact-sheets/detail/dementia (accessed July. 3, 2023).
[22] C. Imperatori, B. Farina, E. M. Valenti, A. D. Poce, S. D'Ari, E. D. Rossi, C. Murgia, G. A. Carbone, C. Massullo, G. D. Marca, “Is resting state frontal alpha connectivity asymmetry a useful index to assess depressive symptoms? A preliminary investigation in a sample of university students,” Journal of Affective Disorders, vol. 257, pp. 152–159, 2019.
[23] N. Jaworska, P. Blier, W. Fusee, V. Knott, “Alpha power, alpha asymmetry and anterior cingulate cortex activity in depressed males and females,” Journal of Psychiatric Research, vol. 46, no. 11, pp.1483-1491, 2012.
[24] J. K. Gollan, D. Hoxha, D. Chihade, M. E. Pflieger, L. Rosebrock, J. Cacioppo, “Frontal alpha EEG asymmetry before and after behavioral activation treatment for depression,” Biological Psychology, vol. 99, pp. 798-208, 2014.
[25] W. Mumtaz, L. Xia, S. S. A. Ali, M. A. M.Yasin, M. Hussain, A. S. Malik, “Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD),” Biomedical Signal Processing and Control, vol. 31, pp. 108-115, 2017.
[26] S. Y. Baik, C. Kim, S. Kim, D. Yook, H. S. Kim, H.n Chang, S. Lee, “The moderating effect of heart rate variability on the relationship between alpha asymmetry and depressive symptoms,” Heliyon, vol. 5, no. 3, 2019.
[27] Omel'chenko, V.P., Zaika, V.G. “Changes in the EEG-Rhythms in Endogenous Depressive Disorders and the Effect of Pharmacotherapy,” Human Physiology 28, pp. 275–281, 2002.
[28] Henriques, J. B., & Davidson, R. J. “Left frontal hypoactivation in depression,” Journal of Abnormal Psychology, vol. 100, no. 4, pp. 535-545, 1991.
[29] V. Knott, C. Mahoney, S. Kennedy, K. Evans, “EEG power, frequency, asymmetry and coherence in male depression,” Psychiatry Research: Neuroimaging, vol.106, no. 2, pp.123-140. 2001.
[30] Reid, S., Duke, L., & Allen, J. “Resting frontal electroencephalographic asymmetry in depression: Inconsistencies suggest the need to identify mediating factors,” Psychophysiology, vol. 42, no.1, pp.389-404, 1998.
[31] Segrave, R. A., Cooper, N. R., Thomson, R. H., Croft, R. J., Sheppard, D. M., & Fitzgerald, P. B., “ Individualized alpha activity and frontal asymmetry in major depression,” Clinical EEG and Neuroscience, 2011
[32] A. Carvalho, H. Moraes, H. Silveira, P. Ribeiro, R. A. M. Piedade, A. C. Deslandes, J. Laks, M. Versiani, “EEG frontal asymmetry in the depressed and remitted elderly: Is it related to the trait or to the state of depression?,” Journal of Affective Disorders, vol. 129, no. 1–3, 2011.
[33] B. Hosseinifard, M. H. Moradi, R. Rostami, “Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal,” Computer Methods and Programs in Biomedicine, vol. 109, no. 3, pp.339-345, 2013.
[34] I. Kalatzis, N. Piliouras, E. Ventouras, C.C. Papageorgiou, A.D. Rabavilas, D. Cavouras, “Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals,” Computer Methods and Programs in Biomedicine, vol. 75, no. 1, pp.11-22, 2004.
[35] W. Mumtaz, A. S. Malik, M. A. M. Yasin, L. Xia, “Review on EEG and ERP predictive biomarkers for major depressive disorder,” Biomedical Signal Processing and Control, vol. 22, pp.85-95, 2015.
[36] P. N. Prinz, P. P. Vitaliano, M. V. Vitiello, J. Bokan, M. Raskind, E. Peskind, and C. Gerber, “Sleep, EEG and mental function changes in senile dementia of the Alzheimer's type,” Neurobiol Aging, vol. 3, no. 4, pp. 361-370, 1982.
[37] C. F. Reynolds 3rd, D. J. Kupfer, L. S. Taska, C. C. Hoch, D. G. Spiker, D. E. Sewitch, B. Zimmer, R. S. Marin, J. P. Nelson, D. Martin, and R. Morycz, “EEG sleep in elderly depressed, demented, and healthy subjects,” Biological Psychiatry, vol. 20, no. 4, pp. 431-442, 1985.
[38] C. F. Reynolds 3rd, D. J. Kupfer, L. S. Taska, C. H. Hoch, D. E. Sewitch, and V. J. Grochocinski, “Slow wave sleep in elderly depressed, demented, and healthy subjects,” Sleep, vol. 8, no. 2, pp. 155-159, 1985.
[39] C. C. Hoch, C. F. Reynolds 3rd, and P. R. Houck, “Sleep patterns in Alzheimer, depressed, and healthy elderly,” Western Journal of Nursing Research, vol. 10, no. 3, pp. 239-256, 1988.
[40] A. Pfefferbaum, B. G. Wenegrat, J. M. Ford, W. T. Roth, and B. S. Kopell, “Clinical Application of the P3 Component of Event-Related Potentials. II. Dementia, Depression and Schizophrenia,” Electroencephalography and Clinical Neurophysiology, vol. 59, no. 2, pp. 104-124, 1984.
[41] J. V. Patterson, H. J. Michalewski, and A. Starr, “Latency Variability of the Components of Auditory Event-Related Potentials to Infrequent Stimuli in Aging, Alzheimer-type Dementia, and Depression,” Electroencephalography and Clinical Neurophysiology, vol. 71, no. 6, pp. 450-460, 1988.
[42] C. Kraiuhin, E. Gordon, S. Coyle, G. Sara, C. Rennie, A. Howson, P. Landau, and R. Meares, “Normal Latency of the P300 Event-Related Potential in Mild-To-Moderate Alzheimer's Disease and Depression,” Biological Psychiatry, vol. 28, no. 5, pp. 372-386, 1990.
[43] Deslandes, A., Veiga, H., Cagy, M., Fiszman, A., Piedade, R., & Ribeiro, P. , “Quantitative electroencephalography (qeeg) to discriminate primary degenerative dementia from major depressive disorder (depression),” Arquivos de Neuro-Psiquiatria, vol. 62, no.1, pp.44-50, 2004.
[44] K. Lee, J. W. Han, K. W. Kim, “Regional Beta Index of Electroencephalography May Differentiate Alzheimer's Disease from Depression,” Psychiatry Investigation, vol.14, no.5, p.708, 2017.
[45] Fingelkurts, A. A., Fingelkurts, A. A., Rytsälä, H., Suominen, K., Isometsä, E., & Kähkönen, “Impaired functional connectivity at EEG Alpha and Theta frequency bands in Major Depression,” Human Brain Mapping, vol. 28, no.3, pp.247-261, 2006.
[46] Mumtaz W, Ali SSA, Yasin MAM, Malik AS, “A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD),” Medical & Biological Engineering & Computing, vol. 56, no.2, pp.233-246, 2017.
[47] V. J. Lawhern et al., “EEGNet: A compact convolutional neural network for EEG-based brain–computer interfaces,” Journal of Neural Engineering, vol. 15, no. 5, p. 056013, 2018.
[48] Z. Pan, C. Park, E. Brietzke, H. Zuckerman, C. Rong, R. B. Mansur, D. Fus, M. Subramaniapillai, Y. Lee, and R. S. McIntyre, “Cognitive impairment in major depressive disorder,” CNS Spectrums, vol. 24, no. 1, pp. 22-29, 2019.
[49] R. Botto, N. Callai, A. Cermelli, L. Causarano, and I. Rainero, “Anxiety and depression in alzheimer’s disease: A systematic review of pathogenetic mechanisms and relation to cognitive decline,” Neurological Sciences, vol. 43, no. 7, pp. 4107-4124, 2022.
[50] P. N. Prinz and M. V. Vitiell, “Dominant occipital (alpha) rhythm frequency in early stage alzheimer’s disease and Depression,” Electroencephalography and Clinical Neurophysiology, vol. 73, no. 5, pp. 427–432, 1989
[51] S. Brassen et al., “Late-onset depression with mild cognitive deficits: Electrophysiological evidences for a preclinical dementia syndrome,” Dementia and Geriatric Cognitive Disorders, vol. 18, no. 3–4, pp. 271–277, 2004.
[52] 林逢輝，《基於休息腦波之老年重度憂鬱症及輕度認知障礙鑑別診斷研究》，碩士論文，國立臺北科技大學機械工程系機電整合碩士班，2020。
[53] T. T. Trinh , C. F. Tsai, Y. T. Hsiao, C. Y. Lee , C. T. Wu , Y. H. Liu, “Identifying individuals with mild cognitive impairment using working memory-induced intra-subject variability of resting-state EEGs,” Frontiers in Computational Neuroscience, vol. 15, 2021.