DETECTION OF SPECIFIC PSYCHIATRIC MENTAL DISORDERS FROM MULTI-CLASS EEG SIGNALS WITH MODIFIED ARTIFICIAL INTELLIGENCE MODELS
Abstract views: 53
/ 
PDF downloads: 31
Keywords:
EEG, CNN, LSTM, Yolov5, Feature Extraction, ClassificationAbstract
Psychiatric disorders have been very common among people and have gained popularity from pyschiatric and artificial intelligence communities. There are many different types of diseases related to the psychiatric based problems. Intelligent recognition methods that based on CAD systems for classifying mental disorders are essential tools in neurogical research area. Various studies have been given to detect mental disorders from neuroimages, EEGs and other radiological based images in literature. In this study, a hybrid method that includes Machine Learning and Deep Learning methods and also their comparison for multi-class mental disorder case detection is given with using a publicly available EEG database. In this study, we used 100 different subjects for each type of disorders which have been diagnosed as Major Depressive Disorder (MDD), Autism Spectrum Disorder (ASD), Schzophrenia (SZ) and healthy. Indeed, additional feature extraction methods with some parameters are used for Machine Learning method of k Nearest Neighbor (kNN) and with no need of feature extraction, modified versions of CNN (Convolutional Neural Network) with LSTM (Long Short Term Memory Network) and YOLOv5 (You Only Look Once) Deep Learning methods are used and all results are compared in detail. The hybrid modified versions of DL models can also acquire detailed knowledge without preprocessing step. For three class classification of psychiatric diseases, the accuracy, specificity, sensitivity and ROC results are obtained as the highest accuracy for modified YOLOv5 model as %99.5 with the average prediction time of 20.38 min, the average prediction speed is 0.083 sec per EEG. Moreover, this study can give a chance for decrease the rate of manual interventions, making the models sufficient for doctors to pre-diagnose during the clinical progress for neurologists, brain surgery area and other related doctors/clinicians.
Downloads
References
Almars, A. M., Badawy, M., & Elhosseini, M. A., 2023. ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework. Heliyon, 9(11).
Nomi, J. S., & Uddin, L. Q., 2015. Face processing in autism spectrum disorders: From brain regions to brain networks. Neuropsychologia, 71, 201-216.
Lauritsen, M. B., 2013. Autism spectrum disorders. European child & adolescent psychiatry, 22, 37-42.
Davignon, M. N., Qian, Y., Massolo, M., & Croen, L. A., 2018. Psychiatric and medical conditions in transition-aged individuals with ASD. Pediatrics, 141(Supplement_4), S335-S345.
Khodatars, M., Shoeibi, A., Sadeghi, D., Ghaasemi, N., Jafari, M., Moridian, P., ... & Berk, M., 2021. Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review. Computers in biology and medicine, 139, 104949.
Bhat, S., Acharya, U. R., Adeli, H., Bairy, G. M., & Adeli, A., 2014. Automated diagnosis of autism: in search of a mathematical marker. Reviews in the Neurosciences, 25(6), 851-861.
Plitt, M., Barnes, K. A., & Martin, A., 2015. Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards. NeuroImage: Clinical, 7, 359-366.
Duda, M., Ma, R., Haber, N., & Wall, D. P., 2016. Use of machine learning for behavioral distinction of autism and ADHD. Translational psychiatry, 6(2), e732-e732.
Chen, Y. H., Chen, Q., Kong, L., & Liu, G., 2022. Early detection of autism spectrum disorder in young children with machine learning using medical claims data. BMJ Health & Care Informatics, 29(1).
Choe, Y. H., Lee, S., Lim, Y., & Kim, S. H., 2024. Machine learning-derived model for predicting poor post-treatment quality of life in Korean cancer survivors. Supportive Care in Cancer, 32(3), 143.
Radhakrishnan, M., Ramamurthy, K., Choudhury, K. K., Won, D., & Manoharan, T. A., 2021. Performance analysis of deep learning models for detection of autism spectrum disorder from EEG signals. Traitement du Signal, 38(3).
Ali, N. A., Syafeeza, A. R., Jaafar, A. S., Alif, M. K. M. F., & Ali, N. A., 2020. Autism spectrum disorder classification on electroencephalogram signal using deep learning algorithm. IAES International Journal of Artificial Intelligence, 9(1), 91-99.
Arnold, L. M., 2008. Understanding fatigue in major depressive disorder and other medical disorders. Psychosomatics, 49(3), 185-190.
Thom, R., Silbersweig, D. A., & Boland, R. J., 2019. Major depressive disorder in medical illness: a review of assessment, prevalence, and treatment options. Psychosomatic medicine, 81(3), 246-255.
Iosifescu, D. V., Nierenberg, A. A., Alpert, J. E., Smith, M., Bitran, S., Dording, C., & Fava, M., 2003. The impact of medical comorbidity on acute treatment in major depressive disorder. American Journal of Psychiatry, 160(12), 2122-2127.
Fava, M., & Kendler, K. S., 2000. Major depressive disorder. Neuron, 28(2), 335-341.
Coulehan, J. L., Schulberg, H. C., Block, M. R., Janosky, J. E., & Arena, V. C., 1990. Medical comorbidity of major depressive disorder in a primary medical practice. Archives of internal medicine, 150(11), 2363-2367.
Sharma, G., Parashar, A., & Joshi, A. M., 2021. DepHNN: a novel hybrid neural network for electroencephalogram (EEG)-based screening of depression. Biomedical signal processing and control, 66, 102393.
Seal, A., Bajpai, R., Agnihotri, J., Yazidi, A., Herrera-Viedma, E., & Krejcar, O., 2021. DeprNet: A deep convolution neural network framework for detecting depression using EEG. IEEE Transactions on Instrumentation and Measurement, 70, 1-13.
Saeedi, A., Saeedi, M., Maghsoudi, A., & Shalbaf, A., 2021. Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach. Cognitive Neurodynamics, 15(2), 239-252.
Čukić, M., Stokić, M., Radenković, S., Ljubisavljević, M., Simić, S., & Savić, D., 2020. Nonlinear analysis of EEG complexity in episode and remission phase of recurrent depression. International journal of methods in psychiatric research, 29(2), e1816.
Mumtaz, W., Xia, L., Mohd Yasin, M. A., Azhar Ali, S. S., & Malik, A. S., 2017. A wavelet-based technique to predict treatment outcome for major depressive disorder. PloS one, 12(2), e0171409.
Uyulan, C., Ergüzel, T. T., Unubol, H., Cebi, M., Sayar, G. H., Nezhad Asad, M., & Tarhan, N., 2021. Major depressive disorder classification based on different convolutional neural network models: Deep learning approach. Clinical EEG and neuroscience, 52(1), 38-51.
Stevenson N, Tapani K, Lauronen L, Vanhatalo S. A dataset of neonatal EEG recordings with seizure annotations. Sci Data. 2019;6:1–8
Meyer, J. M., & Nasrallah, H. A. (Eds.)., 2009. Medical illness and schizophrenia. American Psychiatric Pub.
Goldman, L. S., 1999. Medical illness in patients with schizophrenia. Journal of Clinical Psychiatry, 60, 10-15
Stevens, J. R., Bigelow, L., Denney, D., Lipkin, J., Livermore, A. H., Rauscher, F., & Wyatt, R. J., 1979. Telemetered EEG-EOG during psychotic behaviors of schizophrenia. Archives of General Psychiatry, 36(3), 251-262.
Li, Y., Tong, S., Liu, D., Gai, Y., Wang, X., Wang, J., ... & Zhu, Y., 2008. Abnormal EEG complexity in patients with schizophrenia and depression. Clinical Neurophysiology, 119(6), 1232-1241.
Jindal, K., Upadhyay, R., Padhy, P. K., & Longo, L., 2022. Bi-LSTM-deep CNN for schizophrenia detection using MSST-spectral images of EEG signals. In Artificial Intelligence-Based Brain-Computer Interface (pp. 145-162). Academic Press.
Shi, E. R., 2021. Schizophrenia through the lens of Chinese classifier: a preliminary study. In Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation(pp. 392-401).
Göker, H., & Tosun, M., 2023. Fast Walsh–Hadamard transform and deep learning approach for diagnosing psychiatric diseases from electroencephalography (EEG) signals. Neural Computing and Applications, 35(32), 23617-23630.
Baygin, M., Yaman, O., Tuncer, T., Dogan, S., Barua, P. D., & Acharya, U. R., 2021. Automated accurate schizophrenia detection system using Collatz pattern technique with EEG signals. Biomedical Signal Processing and Control, 70, 102936.
Barros, C., Roach, B., Ford, J. M., Pinheiro, A. P., & Silva, C. A., 2022. From sound perception to automatic detection of schizophrenia: an EEG-based deep learning approach. Frontiers in Psychiatry, 12, 813460.
https://www.kaggle.com/datasets/samnikolas/eeg-dataset
http://modma.lzu.edu.cn/data/index/
Wong S, Simmons A, Rivera-Villicana J, Barnett S, Sivathamboo S, Perucca P, Ge Z, Kwan P, Kuhlmann L, Vasa R, Mouzakis K, O'Brien TJ. EEG datasets for seizure detection and prediction- A review. Epilepsia Open. 2023 Jun;8(2):252-267. doi: 10.1002/epi4.12704. Epub 2023 Feb 16. PMID: 36740244; PMCID: PMC10235576.
Phillips, J. W., Leahy, R. M., Mosher, J. C., & Timsari, B., 1997. Imaging neural activity using MEG and EEG. IEEE Engineering in Medicine and Biology Magazine, 16(3), 34-42.
Im, C. H., 2018. Computational EEG analysis. Springer Singap Singap, 10, 978-981.
Radüntz, T., Scouten, J., Hochmuth, O., & Meffert, B., 2015. EEG artifact elimination by extraction of ICA-component features using image processing algorithms. Journal of neuroscience methods, 243, 84-93.
Chakravarthi, B., Ng, S. C., Ezilarasan, M. R., & Leung, M. F., 2022. EEG-based emotion recognition using hybrid CNN and LSTM classification. Frontiers in Computational Neuroscience, 16, 1019776.
Subasi, A., 2007. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Systems with Applications, 32(4), 1084-1093.
Bhattacharyya, A., & Pachori, R. B., 2017. A multivariate approach for patient-specific EEG seizure detection using empirical wavelet transform. IEEE Transactions on Biomedical Engineering, 64(9), 2003-2015.
Hong, K. S., Khan, M. J., & Hong, M. J., 2018. Feature extraction and classification methods for hybrid fNIRS-EEG brain-computer interfaces. Frontiers in human neuroscience, 12, 246.
Ramos-Aguilar, R., Olvera-López, J. A., & Olmos-Pineda, I., 2017. Analysis of EEG signal processing techniques based on spectrograms. Res Comput Sci, 145, 151-162.
Ural, A. B., 2023. Non-Invasive Bio-Signal Data Classification Of Psychiatric Mood Disorders Using Modified CNN and VGG16. International Journal of Engineering Research and Development, 15(1), 323-332.
Roy, A. M., & Bhaduri, J., 2023. DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism. Advanced Engineering Informatics, 56, 102007.
Albaqami, H., Hassan, G. M., & Datta, A., 2023. MP-SeizNet: A multi-path CNN Bi-LSTM Network for seizure-type classification using EEG. Biomedical Signal Processing and Control, 84, 104780.
Anas, M., Haq, I. U., Husnain, G., & Jaffery, S. A. F., 2024. Advancing Breast Cancer Detection: Enhancing YOLOv5 Network for Accurate Classification in Mammogram Images. IEEE Access.
