{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T12:41:40Z","timestamp":1721824900169},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T00:00:00Z","timestamp":1694217600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T00:00:00Z","timestamp":1694217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Brain Inf."],"published-print":{"date-parts":[[2023,12]]},"abstract":"Abstract<\/jats:title>Early identification of mental disorders, based on subjective interviews, is extremely challenging in the clinical setting. There is a growing interest in developing automated screening tools for potential mental health problems based on biological markers. Here, we demonstrate the feasibility of an AI-powered diagnosis of different mental disorders using EEG data. Specifically, this work aims to classify different mental disorders in the following ecological context accurately: (1) using raw EEG data, (2) collected during rest, (3) during both eye open, and eye closed conditions, (4) at short 2-min duration, (5) on participants with different psychiatric conditions, (6) with some overlapping symptoms, and (7) with strongly imbalanced classes. To tackle this challenge, we designed and optimized a transformer-based architecture, where class imbalance is addressed through focal loss and class weight balancing. Using the recently released TDBRAIN dataset (n= 1274 participants), our method classifies each participant as either a neurotypical or suffering from major depressive disorder (MDD), attention deficit hyperactivity disorder (ADHD), subjective memory complaints (SMC), or obsessive\u2013compulsive disorder (OCD). We evaluate the performance of the proposed architecture on both the window-level and the patient-level. The classification of the 2-min raw EEG data into five classes achieved a window-level accuracy of 63.2% and 65.8% for open and closed eye conditions, respectively. When the classification is limited to three main classes (MDD, ADHD, SMC), window level accuracy improved to 75.1% and 69.9% for eye open and eye closed conditions, respectively. Our work paves the way for developing novel AI-based methods for accurately diagnosing mental disorders using raw resting-state EEG data.<\/jats:p>","DOI":"10.1186\/s40708-023-00201-y","type":"journal-article","created":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T17:01:23Z","timestamp":1694278883000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Transformers for autonomous recognition of psychiatric dysfunction via raw and imbalanced EEG signals"],"prefix":"10.1186","volume":"10","author":[{"given":"Neha","family":"Gour","sequence":"first","affiliation":[]},{"given":"Taimur","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Owais","sequence":"additional","affiliation":[]},{"given":"Iyyakutti Iyappan","family":"Ganapathi","sequence":"additional","affiliation":[]},{"given":"Pritee","family":"Khanna","sequence":"additional","affiliation":[]},{"given":"Mohamed L.","family":"Seghier","sequence":"additional","affiliation":[]},{"given":"Naoufel","family":"Werghi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,9]]},"reference":[{"issue":"2","key":"201_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1088\/1741-2560\/4\/2\/R01","volume":"4","author":"F Lotte","year":"2007","unstructured":"Lotte F, Congedo M, L\u00e9cuyer A, Lamarche F, Arnaldi B (2007) A review of classification algorithms for eeg-based brain-computer interfaces. J Neural Eng 4(2):1","journal-title":"J Neural Eng"},{"issue":"5","key":"201_CR2","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TCBB.2021.3052811","volume":"18","author":"X Gu","year":"2021","unstructured":"Gu X, Cao Z, Jolfaei A, Xu P, Wu D, Jung T-P, Lin C-T (2021) Eeg-based brain-computer interfaces (bcis): a survey of recent studies on signal sensing technologies and computational intelligence approaches and their applications. IEEE\/ACM Trans Comput Biol Bioinform 18(5):1645\u20131666","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"6","key":"201_CR3","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.3390\/s19061423","volume":"19","author":"N Padfield","year":"2019","unstructured":"Padfield N, Zabalza J, Zhao H, Masero V, Ren J (2019) Eeg-based brain-computer interfaces using motor-imagery: techniques and challenges. Sensors 19(6):1423","journal-title":"Sensors"},{"issue":"1","key":"201_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40708-020-00108-y","volume":"7","author":"M Rahman","year":"2020","unstructured":"Rahman M, Khanam F, Ahmad M, Uddin MS et al (2020) Multiclass eeg signal classification utilizing r\u00e9nyi min-entropy-based feature selection from wavelet packet transformation. Brain Inform 7(1):1\u201311","journal-title":"Brain Inform"},{"issue":"4","key":"201_CR5","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/TAI.2021.3097307","volume":"2","author":"MT Sadiq","year":"2021","unstructured":"Sadiq MT, Yu X, Yuan Z, Aziz MZ, Siuly S, Ding W (2021) Toward the development of versatile brain-computer interfaces. IEEE Trans Artif Intell 2(4):314\u2013328","journal-title":"IEEE Trans Artif Intell"},{"key":"201_CR6","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neucom.2013.06.046","volume":"129","author":"X-W Wang","year":"2014","unstructured":"Wang X-W, Nie D, Lu B-L (2014) Emotional state classification from eeg data using machine learning approach. Neurocomputing 129:94\u2013106","journal-title":"Neurocomputing"},{"key":"201_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104696","volume":"136","author":"MM Rahman","year":"2021","unstructured":"Rahman MM, Sarkar AK, Hossain MA, Hossain MS, Islam MR, Hossain MB, Quinn JM, Moni MA (2021) Recognition of human emotions using eeg signals: a review. Comput Biol Med 136:104696","journal-title":"Comput Biol Med"},{"key":"201_CR8","doi-asserted-by":"crossref","unstructured":"Mahato S, Paul S Electroencephalogram (eeg) signal analysis for diagnosis of major depressive disorder (mdd): a review. Nanoelectronics, Circuits and Communication Systems, 323\u2013335 (2019)","DOI":"10.1007\/978-981-13-0776-8_30"},{"key":"201_CR9","doi-asserted-by":"publisher","first-page":"78060","DOI":"10.1109\/ACCESS.2021.3083519","volume":"9","author":"L-M S\u00e1nchez-Reyes","year":"2021","unstructured":"S\u00e1nchez-Reyes L-M, Rodr\u00edguez-Res\u00e9ndiz J, Avecilla-Ram\u00edrez GN, Garc\u00eda-Gomar M-L, Robles-Ocampo J-B (2021) Impact of eeg parameters detecting dementia diseases: a systematic review. IEEE Access 9:78060\u201378074","journal-title":"IEEE Access"},{"issue":"2","key":"201_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40708-018-0079-9","volume":"5","author":"H Perera","year":"2018","unstructured":"Perera H, Shiratuddin MF, Wong KW (2018) Review of eeg-based pattern classification frameworks for dyslexia. Brain Inform 5(2):1\u201314","journal-title":"Brain Inform"},{"issue":"14","key":"201_CR11","doi-asserted-by":"publisher","first-page":"6967","DOI":"10.3390\/app12146967","volume":"12","author":"AM Maitin","year":"2022","unstructured":"Maitin AM, Romero Mu\u00f1oz JP, Garc\u00eda-Tejedor \u00c1J (2022) Survey of machine learning techniques in the analysis of eeg signals for parkinson\u2019s disease: A systematic review. Appl Sci 12(14):6967","journal-title":"Appl Sci"},{"issue":"3","key":"201_CR12","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ab0ab5","volume":"16","author":"A Craik","year":"2019","unstructured":"Craik A, He Y, Contreras-Vidal JL (2019) Deep learning for electroencephalogram (eeg) classification tasks: a review. J Neural Eng 16(3):031001","journal-title":"J Neural Eng"},{"issue":"1387","key":"201_CR13","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1098\/rstb.1999.0468","volume":"354","author":"A Gevins","year":"1999","unstructured":"Gevins A, Smith ME, McEvoy LK, Leong H, Le J (1999) Electroencephalographic imaging of higher brain function philosophical transactions of the royal society of London. Series B Biol Sci 354(1387):1125\u20131134","journal-title":"Series B Biol Sci"},{"issue":"5","key":"201_CR14","doi-asserted-by":"publisher","first-page":"987","DOI":"10.3390\/s19050987","volume":"19","author":"X Jiang","year":"2019","unstructured":"Jiang X, Bian G-B, Tian Z (2019) Removal of artifacts from eeg signals: a review. Sensors 19(5):987","journal-title":"Sensors"},{"key":"201_CR15","doi-asserted-by":"publisher","first-page":"30630","DOI":"10.1109\/ACCESS.2018.2842082","volume":"6","author":"MMN Mannan","year":"2018","unstructured":"Mannan MMN, Kamran MA, Jeong MY (2018) Identification and removal of physiological artifacts from electroencephalogram signals: a review. Ieee Access 6:30630\u201330652","journal-title":"Ieee Access"},{"issue":"7806","key":"201_CR16","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/d41586-020-00922-8","volume":"581","author":"M Marshall","year":"2020","unstructured":"Marshall M (2020) The hidden links between mental disorders. Nature 581(7806):19\u201322","journal-title":"Nature"},{"key":"201_CR17","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser, \u0141, (2017) Polosukhin I Attention is all you need. Advances in neural information processing systems 30"},{"key":"201_CR18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.07125","author":"Q Wen","year":"2022","unstructured":"Wen Q, Zhou T, Zhang C, Chen W, Ma Z, Yan J, Sun L (2022) Transformers in time series: a survey. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2202.07125","journal-title":"arXiv"},{"issue":"1","key":"201_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01409-z","volume":"9","author":"H van Dijk","year":"2022","unstructured":"van Dijk H, van Wingen G, Denys D, Olbrich S, van Ruth R, Arns M (2022) The two decades brainclinics research archive for insights in neurophysiology (tdbrain) database. Scientif Data 9(1):1\u201310","journal-title":"Scientif Data"},{"key":"201_CR20","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1109\/RBME.2020.2969915","volume":"14","author":"M-P Hosseini","year":"2020","unstructured":"Hosseini M-P, Hosseini A, Ahi K (2020) A review on machine learning for eeg signal processing in bioengineering. IEEE Rev Biomed Eng 14:204\u2013218","journal-title":"IEEE Rev Biomed Eng"},{"key":"201_CR21","doi-asserted-by":"publisher","first-page":"523","DOI":"10.7717\/peerj-cs.523","volume":"7","author":"A Alhudhaif","year":"2021","unstructured":"Alhudhaif A (2021) A novel multi-class imbalanced eeg signals classification based on the adaptive synthetic sampling (adasyn) approach. PeerJ Comp Sci 7:523","journal-title":"PeerJ Comp Sci"},{"issue":"3","key":"201_CR22","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.cmpb.2012.10.008","volume":"109","author":"B Hosseinifard","year":"2013","unstructured":"Hosseinifard B, Moradi MH, Rostami R (2013) Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from eeg signal. Comp Meth prog Biomed 109(3):339\u2013345","journal-title":"Comp Meth prog Biomed"},{"key":"201_CR23","doi-asserted-by":"crossref","unstructured":"Das D, Chowdhury T, Pal U (2020) Analysis of multi-class classification of eeg signals using deep learning. In: International Conference on Pattern Recognition and Artificial Intelligence, pp. 203\u2013217 . Springer","DOI":"10.1007\/978-3-030-59830-3_18"},{"issue":"1","key":"201_CR24","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/aa5199","volume":"3","author":"V Bajaj","year":"2017","unstructured":"Bajaj V, Rai K, Kumar A, Sharma D (2017) Time-frequency image based features for classification of epileptic seizures from eeg signals. Biomed Phys Eng Exp 3(1):015012","journal-title":"Biomed Phys Eng Exp"},{"key":"201_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104926","author":"\u02d9IE EMRE","year":"2022","unstructured":"Tarhan N (2022) Multi-class classification model for psychiatric disorder discrimination. Int J Med Inform. https:\/\/doi.org\/10.1016\/j.ijmedinf.2022.104926","journal-title":"Int J Med Inform"},{"issue":"2","key":"201_CR26","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1007\/s10462-021-09986-y","volume":"55","author":"MJ Rivera","year":"2022","unstructured":"Rivera MJ, Teruel MA, Mate A, Trujillo J (2022) Diagnosis and prognosis of mental disorders by means of eeg and deep learning: a systematic mapping study. Artifi Intell Rev 55(2):1209\u20131251","journal-title":"Artifi Intell Rev"},{"key":"201_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105738","volume":"197","author":"M Moghaddari","year":"2020","unstructured":"Moghaddari M, Lighvan MZ, Danishvar S (2020) Diagnose adhd disorder in children using convolutional neural network based on continuous mental task eeg. Comp Meth Prog Biomed 197:105738","journal-title":"Comp Meth Prog Biomed"},{"issue":"1","key":"201_CR28","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1177\/1550059420916634","volume":"52","author":"C Uyulan","year":"2021","unstructured":"Uyulan C, Erg\u00fczel TT, Unubol H, Cebi M, Sayar GH, Nezhad Asad M, Tarhan N (2021) Major depressive disorder classification based on different convolutional neural network models: deep learning approach. Clin EEG Neurosci 52(1):38\u201351","journal-title":"Clin EEG Neurosci"},{"key":"201_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106225","volume":"151","author":"R Supakar","year":"2022","unstructured":"Supakar R, Satvaya P, Chakrabarti P (2022) A deep learning based model using rnn-lstm for the detection of schizophrenia from eeg data. Comput Biol Med 151:106225","journal-title":"Comput Biol Med"},{"key":"201_CR30","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.neucom.2015.02.039","volume":"161","author":"TT Erguzel","year":"2015","unstructured":"Erguzel TT, Ozekes S, Sayar GH, Tan O, Tarhan N (2015) A hybrid artificial intelligence method to classify trichotillomania and obsessive compulsive disorder. Neurocomputing 161:220\u2013228","journal-title":"Neurocomputing"},{"issue":"5","key":"201_CR31","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c","volume":"15","author":"VJ Lawhern","year":"2018","unstructured":"Lawhern VJ, Solon AJ, Waytowich NR, Gordon SM, Hung CP, Lance BJ (2018) Eegnet: a compact convolutional neural network for eeg-based brain-computer interfaces. J Neural Eng 15(5):056013","journal-title":"J Neural Eng"},{"issue":"11","key":"201_CR32","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","volume":"38","author":"RT Schirrmeister","year":"2017","unstructured":"Schirrmeister RT, Springenberg JT, Fiederer LDJ, Glasstetter M, Eggensperger K, Tangermann M, Hutter F, Burgard W, Ball T (2017) Deep learning with convolutional neural networks for eeg decoding and visualization. Human Brain Map 38(11):5391\u20135420","journal-title":"Human Brain Map"},{"key":"201_CR33","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1109\/TNSRE.2022.3194600","volume":"30","author":"J Xie","year":"2022","unstructured":"Xie J, Zhang J, Sun J, Ma Z, Qin L, Li G, Zhou H, Zhan Y (2022) A transformer-based approach combining deep learning network and spatial-temporal information for raw eeg classification. IEEE Trans Neural Syst Rehab Eng 30:2126\u20132136","journal-title":"IEEE Trans Neural Syst Rehab Eng"},{"key":"201_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3230250","author":"Y Song","year":"2022","unstructured":"Song Y, Zheng Q, Liu B, Gao X (2022) Eeg conformer: convolutional transformer for eeg decoding and visualization. IEEE Trans Neural Syst Rehabil Eng. https:\/\/doi.org\/10.1109\/TNSRE.2022.3230250","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"12","key":"201_CR35","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1016\/j.clinph.2007.07.028","volume":"118","author":"RJ Barry","year":"2007","unstructured":"Barry RJ, Clarke AR, Johnstone SJ, Magee CA, Rushby JA (2007) Eeg differences between eyes-closed and eyes-open resting conditions. Clin Neurophysiol 118(12):2765\u20132773","journal-title":"Clin Neurophysiol"},{"key":"201_CR36","doi-asserted-by":"crossref","unstructured":"Zerveas G, Jayaraman S, Patel D, Bhamidipaty A, Eickhoff C. (2021). A transformer-based framework for multivariate time series representation learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2114\u20132124","DOI":"10.1145\/3447548.3467401"},{"key":"201_CR37","unstructured":"Zhang Z, Sabuncu M (2018) Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems 31"},{"issue":"2","key":"201_CR38","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1093\/oxfordjournals.pan.a004868","volume":"9","author":"G King","year":"2001","unstructured":"King G, Zeng L (2001) Logistic regression in rare events data. Polit Anal 9(2):137\u2013163","journal-title":"Polit Anal"},{"key":"201_CR39","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["Brain Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-023-00201-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40708-023-00201-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-023-00201-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T15:05:36Z","timestamp":1700319936000},"score":1,"resource":{"primary":{"URL":"https:\/\/braininformatics.springeropen.com\/articles\/10.1186\/s40708-023-00201-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,9]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["201"],"URL":"http:\/\/dx.doi.org\/10.1186\/s40708-023-00201-y","relation":{},"ISSN":["2198-4018","2198-4026"],"issn-type":[{"value":"2198-4018","type":"print"},{"value":"2198-4026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,9]]},"assertion":[{"value":"22 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}
