Advances in Automatic Classification and Prediction Study of Neuropsychiatric Diseases
Chen Xiaoyi1,3,4, Zhou Jing1,3,4,5, Ke Pengfei1,3,4, Kong Lingyin1,3,4, Wu Fengchun2,3, Wu Kai1,2,3,4,5,6,7,8#*
1(Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou 510006, China) 2(The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou 510370, China) 3(Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, China) 4(Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou 510500, China) 5(National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou 510006, China) 6(Key Laboratory of Biomedical Engineering of Guangdong Province, South China University of Technology, Guangzhou 510006, China) 7(National Engineering Research Center for Healthcare Devices, Guangzhou 510500, China) 8(Department of Nuclear Medicine and Radiology, Institute of Development, Aging and Cancer, Tohoku University, Sendai980-8575, Japan)
Abstract：There are still many unknown neuropathological mechanisms of neuropsychiatric diseases, and objective clinical diagnostic criteria are lacking, which brings great challenges to the diagnosis and prognosis of neuropsychiatric diseases. With the rapid development of neuroimaging technology, neuroimaging data have been widely used to explore the neuropathological mechanism and potential biomarkers of neuropsychiatric diseases. Compared with traditional univariate analysis methods, that can only perform population-level analyses, neuroimaging-data-driven machine learning models can realize individualized and automated prediction of neuropsychiatric diseases. In this paper, we reviewed recent research progress of automated classification and prediction of neuropsychiatric diseases based on machine learning technology, and summarized and analyzed the basic principles of machine learning technology and the latest research achievements of four typical neuropsychiatric diseases, including schizophrenia, depression, Alzheimer‘s disease and Parkinson's disease. It was shown that current studies still face the challenge of small sample size and low reproducibility. Nonetheless, the sample size can be increased through collaborative analysis of multi-site data in the future. Meanwhile, deep learning and cross-disease diagnosis and prediction are also important directions of future research.
[1] 毕胜. 功能神经影像学技术在神经康复中的应用 [J]. 中国康复医学杂志, 2004, 19(4): 316-318. [2] 文宏伟, 陆菁菁, 何晖光. 机器学习在神经精神疾病诊断及预测中的应用 [J]. 协和医学杂志, 2018, 9(1): 19-24. [3] Saeed U, Compagnone J, Aviv R, et al. Imaging biomarkers in Parkinson's disease and Parkinsonian syndromes: current and emerging concepts [J]. Translational Neurodegeneration, 2017, 6: 8. [4] Cai Xinlu, Xie Dongjie, Madsen KH, et al. Generalizability of machine learning for classification of schizophrenia based on resting-state functional MRI data [J]. Hum Brain Mapp, 2020, 41(1): 172-184. [5] Lu Xiaobing, Yang Yongzhe, Wu Fengchun, et al. Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images [J]. Medicine, 2016, 95(30): e3973. [6] 张越, 杨勇哲, 吴逢春, 等. 基于多模态磁共振影像的精神分裂症患者多特征分类研究 [J]. 中国医学物理学杂志, 2017, 34(1): 99-104. [7] Singh G, Vadera M, Samavedham L, et al. Multiclass diagnosis of neurodegenerative diseases: a neuroimaging machine-learning-based approach [J]. Industrial & Engineering Chemistry Research, 2019, 58(26): 11498-11505. [8] Du Wei, Calhoun VD, Li Hualiang, et al. High classification accuracy for schizophrenia with rest and task fMRI data [J]. Frontiers in Human Neuroscience, 2012, 6: 145. [9] Patel MJ, Khalaf A, Aizenstein HJ. Studying depression using imaging and machine learning methods [J]. Neuroimage Clinical, 2016, 10: 115-123. [10] Lai Chunren, Guo Shengwen, Cheng Lina, et al. Evaluation of feature selection algorithms for classification in temporal lobe epilepsy based on MR images [C]// Eighth International Conference on Graphic and Image Processing (ICGIP). Bellingham: Spie-Int Soc Optical Engineering, 2017: 102252A. [11] 雷炳业, 潘嘉瑜, 吴逢春, 等. 基于机器学习的神经精神疾病辅助诊断研究进展 [J]. 中国医学物理学杂志, 2020, 37(02): 257-264. [12] 郑泓, 王毅, 陈楚侨. 基于脑结构特征的精神分裂症机器学习分类研究 [C]//第二十一届全国心理学学术会议摘要集. 北京: 中国心理学会, 2018: 1203-1204. [13] 皇甫浩然, 杨剑, 杨阳. 基于fMRI动态功能连接的抑郁症患者分类研究 [J]. 计算机应用研究, 2017, 34(3): 678-682. [14] Sarica A, Cerasa A, Quattrone A. Random forest algorithm for the classification of neuroimaging data in Alzheimer's disease: A systematic review [J]. Front Aging Neurosci, 2017, 9: 329. [15] Lahmiri S, Shmuel A. Performance of machine learning methods applied to structural MRI and ADAS cognitive scores in diagnosing Alzheimer's disease [J]. Biomedical Signal Processing and Control, 2019, 52: 414-419. [16] 刘盛锋. 多模态磁共振影像融合技术及其在精神分裂症中的应用 [D]. 哈尔滨: 哈尔滨理工大学, 2017. [17] Zeng Lingli, Wang Huaning, Hu Panpan, et al. Multi-site diagnostic classification of schizophrenia using discriminant deep learning with functional connectivity MRI [J]. EBioMedicine, 2018, 30: 74-85. [18] Li Ang, Zalesky A, Yue Weihua, et al. A neuroimaging biomarker for striatal dysfunction in schizophrenia [J]. Nature Medicine, 2020, 26(4): 558-565. [19] 杨勇哲, 张越, 吴逢春, 等. 基于多模态磁共振影像的首发未用药精神分裂症自动分类研究 [J]. 生物医学工程学杂志, 2017, 34(5): 674-680. [20] Wu Fengchun, Zhang Yue, Yang Yongzhe, et al. Structural and functional brain abnormalities in drug-naive, first-episode, and chronic patients with schizophrenia: a multimodal MRI study [J]. Neuropsychiatric Disease and Treatment, 2018, 14: 2889-2904. [21] Oh J, Oh BL, Lee KU, et al. Identifying schizophrenia using structural MRI with a deep learning algorithm [J]. Front Psychiatry, 2020, 11: 16. [22] Qiu Yue, Lin Qiuhua, Kuang Lidan, et al. Classification of schizophrenia patients and healthy controls using ICA of complex-valued fMRI data and convolutional neural networks [C]// Lecture Notes in Computer Science. Cham: Springer, 2019: 540-547. [23] Niu Yanwei, Lin Qiuhua, Qiu Yue, et al. Sample augmentation for classification of schizophrenia patients and healthy controls using ICA of fMRI data and convolutional neural networks [C]//Proceedings of the 10th International Conference on Intelligent Control and Information Processing. Piscataway: IEEE, 2019: 297-320. [24] Qureshi MNI, Oh J, Lee B. 3D-CNN based discrimination of schizophrenia using resting-state fMRI [J]. Artificial Intelligence in Medicine, 2019, 98: 10-17. [25] Srinivasagopalan S, Barry J, Gurupur V, et al. A deep learning approach for diagnosing schizophrenic patients [J]. Journal of Experimental & Theoretical Artificial Intelligence, 2019, 31(6): 803-816. [26] Kelly S, Jahanshad N, Zalesky A, et al. Widespread white matter microstructural differences in schizophrenia across 4322 individuals: results from the ENIGMA schizophrenia DTI working group [J]. Molecular Psychiatry, 2018, 23(5): 1261-1269. [27] 禚传君, Triplett P, Ciprini A, 等. 基于脑影像和机器学习的抑郁型精神分裂症早期定性诊断预测模型展望 [J]. 中华诊断学电子杂志, 2018, 6(1): 1-8. [28] 张越. 基于多模态磁共振脑影像特征的精神分裂症自动分类及个体化预测研究 [D]. 广州: 华南理工大学, 2019. [29] Gould IC, Shepherd AM, Laurens KR, et al. Multivariate neuroanatomical classification of cognitive subtypes in schizophrenia: A support vector machine learning approach [J]. Neuroimage Clinical, 2014, 6: 229-236. [30] Xie Teng, Zhang Xiangrong, Tang Xiaowei, et al. Mapping convergent and divergent cortical thinning patterns in patients with deficit and nondeficit schizophrenia [J]. Schizophrenia Bulletin, 2019, 45(1): 211-221. [31] Koutsouleris N, Wobrock T, Guse B, et al. Predicting response to repetitive transcranial magnetic stimulation in patients with schizophrenia using structural magnetic resonance imaging:a multisite machine learning analysis [J]. Schizophrenia Bulletin, 2018, 44(5): 1021-1034. [32] 吴秀勇, 吴效明, 彭红军, 等. 抑郁症及焦虑障碍的磁共振影像学研究进展 [J]. 航天医学与医学工程, 2015, 28(3): 229-234. [33] Mwangi B, Ebmeier KP, Matthews K, et al. Multi-centre diagnostic classification of individual structural neuroimaging scans from patients with major depressive disorder [J]. Brain, 2012, 135(5): 1508-1521. [34] Chi Mingyue, Guo Shengwen, Ning Yuping, et al. Discriminative analysis of major depressive disorder and anxious depression using support vector machine [J]. Journal of Computational and Theoretical Nanoscience, 2015, 12(7): 1395-1401. [35] Wang Jing, Peng Hongjun, Zhang Yue, et al. Discriminative analysis of depression patients studied with structural MR images using support vector machine and recursive feature elimination [J]. Sensing and Imaging, 2019, 20(1): 11-21. [36] Drysdale AT, Grosenick L, Downar J, et al. Resting-state connectivity biomarkers define neurophysiological subtypes of depression [J]. Nature Medicine, 2017, 23(1): 28-38. [37] Pei Cong, Sun Yurong, Zhu Jinlong, et al. Ensemble learning for early-response prediction of antidepressant treatment in major depressive disorder [J]. Journal of Magnetic Resonance Imaging, 2020, 52(1): 161-171. [38] 王静, 彭红军, 杨勇哲, 等. 基于多模态磁共振影像的抑郁障碍自动分类研究 [J]. 中国神经精神疾病杂志, 2018, 44(10): 583-588. [39] Ay B, Yildirim O, Talo M, et al. Automated depression detection using deep representation and sequence learning with EEG signals [J]. Journal of Medical Systems 2019, 43(7): 205. [40] Li Xiaowei, La Rong, Wang Ying, et al. EEG-based mild depression recognition using convolutional neural network [J]. Medical & Biological Engineering & Computing, 2019, 57(6): 1341-1352. [41] Sadan MAHM, Pampouchidou A, Meriaudeau F. Deep learning techniques for depression assessment [C]//2018 International conference on intelligent and advanced system (ICIAS). New York: IEEE, 2018: 18282919. [42] 孙也婷, 陈桃林, 何度, 等. 基于精神影像和人工智能的抑郁症客观生物学标志物研究进展 [J]. 生物化学与生物物理进展, 2019, 46(9): 879-899. [43] Fonseka TM, MacQueen GM, Kennedy SH. Neuroimaging biomarkers as predictors of treatment outcome in major depressive disorder [J]. Journal of Affective Disorders, 2018, 233: 21-35. [44] 范炤, 李彩. 基于机器学习的阿尔茨海默病病程分类 [J]. 中国医学影像学杂志, 2019, 27(10): 792-795,800. [45] Beheshti I, Demirel H, Farokhian F, et al. Structural MRI-based detection of Alzheimer's disease using feature ranking and classification error [J]. Computer Methods and Programs in Biomedicine, 2016, 137: 177-193. [46] Liu Mingxia, Zhang Jun, Adeli E, et al. Joint classification and regression via deep multi-task multi-channel learning for Alzheimer's disease diagnosis [J]. IEEE Transactions on Biomediical Engineering, 2019, 66(5): 1195-1206. [47] Bi Xiaan, Shu Qing, Sun Qi, et al. Random support vector machine cluster analysis of resting-state fMRI in Alzheimer's disease [J]. PLoS ONE, 2018, 13(3): e0194479. [48] Basaia S, Agosta F, Wagner L, et al. Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks [J]. Neuroimage Clinical, 2019, 21: 101645. [49] Böhle M, Eitel F, Weygandt M, et al. Layer-wise relevance propagation for explaining deep neural network decisions in MRI-based Alzheimer's disease classification [J]. Frontiers in Aging Neuroscience, 2019, 11: 194. [50] Spasov S, Passamonti L, Duggento A, et al. A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease [J]. Neuroimage, 2019, 189: 276-287. [51] Song Xuegang, Zhou Feng, Frangi AF, et al. Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction [J]. Medical Image Analysis, 2021, 69: 101947. [52] Koikkalainena J, Rhodius-Meesterb H, Tolonena A, et al. Differential diagnosis of neurodegenerative diseases using structural MRI data [J]. NeuroImage Clinical, 2016, 11: 435-449. [53] Rao SS, Hofmann LA, Shakil A. Parkinson's disease: diagnosis and treatment [J]. American Family Physician, 2006, 74(12): 2046-2054. [54] 杜婷婷, 陈颍川, 朱冠宇, 等. 基于机器学习的帕金森病诊断研究 [J]. 立体定向和功能性神经外科杂志, 2019, 32(3): 129-132,136. [55] Karapinar Senturk Z. Early diagnosis of Parkinson's disease using machine learning algorithms [J]. Medical Hypotheses, 2020, 138: 109603. [56] Rubbert C, Mathys C, Jockwitz C, et al. Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity [J]. British Journal of Radiology, 2019, 92(1101): 20180886. [57] Mabrouk R, Chikhaoui B, Bentabet L. Machine learning based classification using clinical and DaTSCAN SPECT imaging features: a study on Parkinson's disease and SWEDD [J]. IEEE Transactions on Radiation and Plasma Medical Sciences, 2019, 3(2): 170-177. [58] Salvatore C, Cerasa A, Castiglioni I, et al. Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and progressive supranuclear palsy [J]. Journal of Neuroscience Methods, 2014, 222: 230-237. [59] Huppertz HJ, Müller L, Südmeyer M, et al. Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification [J]. Movement Disorders, 2016, 31(10): 1506-1517. [60] Adeli E, Wu Guorong, Saghafi B, et al. Kernel-based joint feature selection and max-margin classification for early diagnosis of Parkinson's disease [J]. Scientific Reports, 2017, 7: 41069. [61] Kollia I, Stafylopatis AG, Kollias S, et al. Predicting Parkinson's disease using latent information extracted from deep neural networks [C]//International Joint Conference on Neural Networks (IJCNN). New York: IEEE, 2019: 19028247. [62] Esmaeilzadeh S, Yao Y, Adeli E. End-to-end Parkinson disease diagnosis using brain MR-images by 3D-CNN[DB/OL]. https://arxiv.org/abs/1806.05233,2018-06-13/2020-11-20. [63] Prashanth R, Roy SD, Mandal PK, et al. Automatic classification and prediction models for early Parkinson's disease diagnosis from SPECT imaging [J]. Expert Systems with Applications, 2014, 41(7): 3333-3342. [64] Li Lanjuan, Ning Zubiao, Jin Xinyu. Classification of neurodegenerative diseases based on CNN and LSTM [C]//Nineth International Conference on Information Technology in Medicine and Education (ITME). New York: IEEE, 2018: 82-85. [65] Zhan Chenyang, Liu Yuhong, Wu Kai, et al. Structural and functional abnormalities in children with attention-deficit/hyperactivity disorder: a focus on subgenual anterior cingulate cortex [J]. Brain Connectivity, 2017, 7(2): 106-114. [66] Lei Bingye, Wu Fengchun, Zhou Jing, et al. NEURO-LEARN: A solution for collaborative pattern analysis of neuroimaging data [J]. Neuroinformatics, 2020, 19(1): 79-91. [67] Jack CR, Bernstein MA, Fox NC, et al. The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods [J]. J Magn Reson Imaging, 2008, 27(4): 685-691. [68] Shen Dinggang, Wu Guorong, Suk H-II. Deep learning in medical image analysis [J]. Annu Rev Biomed Eng, 2017, 19(1): 221-248. [69] Vieira S, Pinaya WH, Mechelli A. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: methods and applications [J]. Neuroscience Biobehavioral Reviews, 2017, 74: 58-75. [70] Xia Mingrui, Womer FY, Chang Miao, et al. Shared and distinct functional architectures of brain networks across psychiatric disorders [J]. Schizophrenia Bulletin, 2019, 45(2): 450-463. [71] Mothi SS, Sudarshan M, Tandon N, et al. Machine learning improved classification of psychoses using clinical and biological stratification: update from the bipolar-schizophrenia network for intermediate phenotypes (B-SNIP) [J]. Schizophrenia Research, 2019, 214: 60-69.
