پیش‌بینی موفقیت در درمان نوروفیدبک برای بیماران اختلال نقص توجه و بیش‌فعالی پیش از شروع درمان
محورهای موضوعی : پردازش سیگنالهای پزشکی
نیکو خان احمدی
1
,
محمدرضا یوسفی
2
*
1 - دانشکده مهندسی برق- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران
2 - دانشکده مهندسي برق- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ايران
کلید واژه: الکتروانسفالوگرام, الگوریتم ژنتیک, بیش‌فعالی, پیش‌بینی, شبکه ارتباطات مغزی, نوروفیدبک,
چکیده مقاله :
در این مقاله روش پیش‌بینی درمان‌پذیری بیماران مبتلا به بیش‌فعالی با آموزش نوروفیدبک به کمک استخراج باند فرکانسی سیگنال الکتروانسفالوگرام (EEG) و با استفاده از معیار ارزیابی ارتباطات مغزی-عملکردی انجام شده تا قبل از شروع درمان نوروفیدبک درمان‌پذیری شخص تشخیص داده شود. این الگوریتم شامل شش مرحله است: در گام اول یک مجموعه داده از ثبت سیگنال EEG حین تحریک نوروفیدبک از 60 دانش‌آموز در رده سنی 7 تا 14 سال (بدون توجه به جنسیت) مبتلا به بیش‌فعالی در دو کلاس درمان‌پذیر و درمان‌ناپذیر از پایگاه داده مندلی دریافت شده است. در گام دوم فیلترینگ اولیه برای کاهش نویز مجموعه داده‌ها با استفاده از یک بلوک پیش‌پردازش انجام شده است. در گام سوم توزیع فرکانسی باند آلفا و بتا از سیگنالهای کاهش نویز شده استخراج شده است. در این نوع داده تفاوت در اجزای EEG هر گروه با استفاده از سنجش ارتباطات مغزی-عملکردی و به کمک شاخص قفل فاز (PLI) قابل بیان بوده که برای تشخیص وجود ارتباط بین لوب‌های مغزی درگیر یک‌بار با استفاده از شاخص مقدار احتمال (PV) در آزمون آماری تی-تست و برای افزایش صحت، از الگوریتم ژنتیک برای تشخیص الکترودهای مؤثر در درمان استفاده شده است.پس گام چهارم استخراج ویژگی یعنی سنجش میزان ارتباطات مغزی در الکترودهای ثبت سیگنال مغزی می‌باشد در گام پنجم یعنی کاهش فضای ویژگی، نتایج نشان میدهند که لوب‌های درگیر هنگام تحریک نوروفیدبک، لوب‌های فرونتال و سنترال هستند و از بین 32 کانال ثبت EEG فقط داده‌های مربوط به 6 کانال C3، FZ، F4، CZ، C4 و F3 تفاوت معناداری در میزان ارتباطات مغزی حین تحریک از خود نشان میدهند و درنهایت گام ششم با استفاده از طبقه‌بندی‌های مختلف، خروجی ترکیب طبقه‌بندها برچسب یکی از دو کلاس درمان‌پذیر یا درمان‌ناپذیر بوده است. در این روش پیشنهادی از معیار صحت برای بیان نتیجه پژوهش استفاده شده و درنهایت درصد صحت به‌دست آمده 6/90 درصد است.
In this paper, the method of predicting the treatability of patients suffering from hyperactivity with neurofeedback training with the help of extracting the frequency band of the electroencephalogram (EEG) signal and using the brain-functional communication evaluation criterion is done to determine the person's treatability before starting the neurofeedback treatment. This algorithm consists of six steps: In the first step, a data set of EEG signal recording during neurofeedback stimulation from 60 students in the age group of 7 to 14 years (regardless of gender) with hyperactivity in two treatable and non-treatable classes was obtained from the Mendelian database. In the second step, primary filtering has been done to reduce the noise of the data set using a pre-processing block. In the third step, the frequency distribution of the alpha and beta bands is extracted from the noise reduction signals. In this type of data, the difference in the EEG components of each group can be expressed by measuring brain-functional communication and using the phase lock index (PLI), which is used to detect the existence of a connection between the brain lobes involved once using the probability value index. In the t-test statistical test and to increase the accuracy, the genetic algorithm was used to identify the effective electrodes in the treatment. So, the fourth step is to extract the feature, which is to measure the amount of brain communication in the brain signal recording electrodes. In the fifth step, it is to reduce the feature space, the results show show that the lobes involved during neurofeedback stimulation are the frontal and central lobes, and among the 32 EEG recording channels, only the data of 6 channels C3, FZ, F4, CZ, C4, and F3 show a significant difference in the amount of brain communication during stimulation. and finally, in the sixth step, by using different classifications, the output of the combination of classifications was the label of one of two classes, treatable or non-treatable. In this proposed method, the correctness criterion is used to express the research result, and finally the percentage of correctness obtained is 90.6%.
[1] K. Molinero, J.D. Hinckley, "Adolescent cannabis use, comorbid attention-deficit/hyperactivity disorder, and other internalizing and externalizing disorders", Child and Adolescent Psychiatric Clinics of North America, vol. 32, no. 1, pp. 57-68, Jan. 2023 (doi: 10.1016/j.chc.2022.07.003).
[2] G. Deshpande, P. Wang, D. Rangaprakash, B. Wilamowski, "Fully connected cascade artificial neural network architecture for attention deficit hyperactivity disorder classification from functional magnetic resonance imaging data", IEEE Trans. on Cybernetics, vol. 45, no. 12, pp. 2668-2679, Dec. 2015 (doi: 10.1109/TCYB.2014.2379621).
[3] M. Dorvashi, N. Behzadfar, G. Shahgholian, "Classification of alcoholic and non-alcoholic individuals based on frequency and non-frequency features of electroencephalogram signal", Journal Iranian Journal of Biomedical Engineering, vol. 14, no. 2, pp. 121-130, July 2020 (doi: 10.22041/ijbme.2020.119841.1551).
[4] H. Gevensleben, B. Hoii, B. Albrecht, D. Schlamp, O. Kratz, P. Studer, S. Wangler, A. Rothenberger, G.H. Moii, H. Heinrich, "Distinct EEG effects related to neurofeedback training in children with ADHD: A randomized controlled trial", International Journal of Psychophysiology, vol. 74, no. 2, pp. 149-157, Sept. 2019 (doi: 10.1016/j.ijpsycho.2009.08.005).
[5] P. Jalali, N. Sho'ouri, "Neurofeedback training protocol based on selecting distinctive features to treat or reduce ADHD symptoms", Clinical EEG and Neuroscience, vol. 52, no. 6, pp. 414-421, Nov. 2021 (doi: 1-0.1177/1550059421¬1033435).
[6] A. Zuberer, D. Brandeis, R. Drechsler, "Are treatment effects of neurofeedback training in children with ADHD related to the successful regulation of brain activity? A review on the learning of regulation of brain activity and a contribution to the discussion on specificity", Frontiers in Human Neuroscience, vol. 9, Article Number: 135, Mar. 2015 (doi: 10.3389/fnhum.2015.00135).
[7] E. Weber, A. Köberl, S. Frank, M. Doppelmayr, "Predicting successful learning of SMR neurofeedback in healthy participants: methodological considerations", Applied Psychophysiology and Biofeedback, vol. 36, no. 1, pp. 37-45, March 2011 (doi: 10.1007/s10484-010-9142-x).
[8] A.K. Dubey, A. Saxena, A. Kumar, A. Rai, "Attention deficit hyperactivity disorder (ADHD) prediction system", Proceeding of the ICSCDS, Erode, India, pp. 1321-1325, 2022 (doi: 10.1109/ICSCDS53736.2022.9760921).
[9] A. Tobeiha, N. Behzadfar, M.R. Yousefi-Najafabadi, H. Mahdavi-Nasab, G. Shahgholian, "Choosing the distinguishing frequency feature of people addicted to heroin from healthy while resting", Signal and Data Processing, vol. 19, no. 3, pp. 49-64, Dec. 2022 (doi: 10.52547/jsdp.19.3.49).
[10] X.Y. Chen, L. Sui, "Alpha band neurofeedback training based on a portable device improves working memory performance of young people", Biomedical Signal Processing and Control, vol. 80, Article Number: 104308, Feb. 2023 (doi: 10.1016/j.bspc.2022.104308).
[11] N. Behzadfar, "A brief overview on analysis and feature extraction of electroencephalogram signals", Signal Processing and Renewable Energy, vol. 6, no. 1, pp. 39-64, March 2022 (dor: 20.100-1.1.25887327.2022.6.1.3.9).
[12] S. Karimi-Shahraki, M. Khezri, "Identification of attention deficit Hyperactivity disorder patients using wavelet-based features of EEG signals", Journal of Intelligent Procedures in Electrical Technology, vol. 12, no. 47, pp. 1-11, Dec. 2021 (dor: 20.1001.1.23223871.1400.12.3.1.1).
[13] M. Dorvashi, N. Behzadfar, G. Shahgholian, "Electroencephalogram signal during neurofeedback training", Signal and Data Processing, vol. 19, no. 3, pp. 163-174, Dec. 2022 (doi: 10.52547/jsdp.19.3.163).
[14] E. Dudek, D. Dodell-Feder, "The efficacy of real-time functional magnetic resonance imaging neurof-eed¬back for psychiatric illness: A meta-analysis of brain and behavioral outcomes", Neuroscience and Biobehavioral Reviews, vol. 121, pp. 291-306, Feb. 2021 (doi: 10.1016/j.neubiorev.2020.12.020).
[15] W. Nan, F. Wang, M. Vaim A.C. Rosa, "Resting and initial beta amplitudes predict learning ability in beta/theta ratio neurofeedback training in healthy young adults", Frontiers in Human Neuroscience, vol. 9 , Article Number: 677, Dec. 2015 (doi: 10.3389/fnhum.2015.00677).
[16] T.W.P. Janssen, M. Bink, W.D. Weeda, K. Geladé, R. Mourik, A. Maras, J. Oosterlaan, "Learning curves of theta/beta neurofeedback in children with ADHD", European Child and Adolescent Psychiatry, vol. 26, no. 5, pp. 573-582, 2017 (doi: 10.1007%2Fs00787-016-0920-8).
[17] H. Marzbani, H.R. Marateb, M. Mansourian, "Neurofeedback: A comprehensive review on system design, methodology and clinical applications", Basic and Clinical Neuroscience, vol. 7, no. 2, pp. 143-58. 2016 (doi: 10.15412/j.bcn.03070208).
[18] K.J. Friston, "Functional and effective connectivity: A review", Brain connectivity, vol. 1, no. 1, pp. 13-36, 2011 (doi: 10.1089/brain.2011.0008).
[19] F. Mottola, A. Blanchfield, J. Hardy, A. Cooke, "EEG neurofeedback improves cycling time to exhaustion", Psychology of Sport and Exercise, vol. 55, Article Number: 101944, July 2021 (doi: 10.1016/j.psychsport.2¬021.101944).
[20] M. Iyzadpanahi, M.R. Yousefi, N. Behzadfar, "Classification of upper limb movement imaginations based on a hybrid method of wavelet transform and principal component analysis for brain-computer interface applications", Journal of Novel Researches on Electrical Power, vol. 9, no. 3, pp. 35-42, Dec. 2020 (dor: 20.1001.1.23222468.1399.9.3.4.6).
[21] M. Dorvashi, N. Behzadfar, G. Shahgholian, "An efficient method for classification of alcoholic and normal electroencephalogram signals based on selection of an appropriate feature", Journal of Medical Signals and Sensors, vol.13, no. 1, pp. 11-20, March 2023 (doi: 10.4103/jmss.jmss_183_21).
[22] Z. Agnieszka, D. Brandeis, and R. Drechsler, "Are treatment effects of neurofeedback training in children with ADHD related to the successful regulation of brain activity? A review on the learning of regulation of brain activity and a contribution to the discussion on specificity", Frontiers in Human Neuroscience, vol. 9, Article Number: 135, Mar. 2015 (doi: 10.3389/fnhum.2015.00135).
[23] M.P. Deiber, R. Hasler, J. Colin, A. Dayer, J.M. Aubry, S. Baggio, N. Perroud, T. Ros, "Linking alpha oscillations, attention and inhibitory control in adult ADHD with EEG neurofeedback", NeuroImage: Clinical, vol. 25, Article Number: 102145, 2020 (doi: 10.1016/j.nicl.2019.102145).
[24] J.H. Gruzelier, P. Holmes, L. Hirst, K. Bulpin, S. Rahman, C. van Run, J. Leach, "Replication of elite music performance enhancement following alpha/theta neurofeedback and application to novice performance and improvisation with SMR benefits", Biological Psychology, vol. 95, pp. 96-107, Jan. 2014 (doi: 10.1016/j.¬bio¬psycho.2013.11.001).
[25] G.W. Hynd, A.R. Lorys, M. Semrud-Clikeman, N. Nieves, M.I. Huettner, B.B. Lahey, "Attention deficit disorder without hyperactivity: a distinct behavioral and neurocognitive syndrome", Journal of Child Neurology, vol. 6, no. 1, pp. 37-43, June 1991 (doi: 0883073891006001s05).
[26] J.C. Edgar, C.L. Fisk, Y.H. Chen, B. Stone-Howell, M.A. Hunter, M. Huang, J.R. Bustillo, J.M. Cañive, "By our bootstraps: Comparing methods for measuring auditory 40 Hz steady‐state neural activity", Psychophysiology, vol. 54, no. 8, pp. 1110-1127, April 2017 (doi: 10.1111/psyp.12876).
[27] H. Fathi-Sanghari, N. Behzadfar, "Application of firefly algorithm in automatic extraction of brain tumor from multi-modality magnetic resonance images", International Journal of Smart Electrical Engineering, vol. 10, no. 4, pp. 187-196, 2021 (doi: 10.30495/ijsee.2021.684023).
[28] F.H. Garabaghi, R. Benzer, S. Benzer, A.Ç. Günal, "Effect of polynomial, radial basis, and Pearson VII function kernels in support vector machine algorithm for classification of crayfish", Ecological Informatics, vol. 72, Article Number: 101911, Dec 2022 (doi: 10.1016/j.ecoinf.2022.101911).
[29] M. Azzeh, Y. Elsheikh, A.B. Nassif, L. Angelis, "Examining the performance of kernel methods for software defect prediction based on support vector machine", Science of Computer Programming, vol. 226, Article Number: 102916, March 2023 (doi: 10.1016/j.scico.2022.102916).
[30] N. Dashti, M, Khezri, "Recognition of motor imagery based on dynamic features of EEG signals", Journal of Intelligent Procedures in Electrical Technology, vol. 11, no. 43, 13-27, December 2020 (in Persian) (dor: 20.1001.1.23223871.1399.11.43.2.5).
[31] Z. Wang, C.M. Wong, W. Nan, Q. Tang, A.C. Rosa, P. Xu, F. Wan, "Learning curve of a short-time neurofeedback training: Reflection of brain network dynamics based on phase-locking value", IEEE Trans. on Cognitive and Developmental Systems, vol. 14, no. 3, pp. 1282-1295, Sept. 2022 (doi: 10.1109/TC¬DS.20¬21.3125948).
[32] A.V. Sazonov, C.K. Ho, J.W. Bergmans, J.B. Arends, P.A. Griep, E.A. Verbitskiy, P.J. Cluitmans, P.A. Boon, "An investigation of the phase locking index for measuring of interdependency of cortical source signals recorded in the EEG”, Biological Cybernetics, vol. 100, no. 2, pp. 129-146, Feb. 2009 (doi: 10.1007/s0042200802834).
[33] J.H. Gruzelier, "A theory of alpha/theta neurofeedback, creative performance enhancement, long distance functional connectivity and psychological integration", Cognitive Processes, vol. 10, op. 101–110, Feb. 2009 (doi: 10.1007/s10339-008-0248-5).
[34] S. Majlesi, M. Khezri, "Stress detection based on fusion of multimodal physiological signals using demp¬ster-shafer evidence theory", Journal of Intelligent Procedures in Electrical Technology, vol. 13, no. 52, pp. 99-110, March 2023 (dor: 20.1001.1.23223871.1401.13.52.7.2).
[35] M. Seif, M.R. Yousefi, N. Behzadfar, "EEG spectral power analysis: A comparison between heroin dependent and control groups", Clinical EEG and Neuroscience, vol. 53, no. 4, Article Number: 15500594221089366, March 2022 (doi: 10.1177/15500594221089366).
[36] H. Li, L. Wu, "EEG classification of normal and alcoholic by deep learning", Brain Sciences, vol. 12, no. 6, Article Number: 778, June 2022 (doi: 10.3390/brainsci12060778).
[37] M. Shafiof, N. Behzadfar, "Diagnosis of brain tumor position in magnetic resonance images by combining bounding box algorithms, artificial bee colonies and grow cut", International Journal of Smart Electrical Engineering, vol. 11, no. 1, pp. 1-12, March 2022 (dor: 20.1001.1.22519246.2022.11.1.1.7).
[38] J.F. Harmsel, M.L. Noordzij, A.E. Goudriaan, J.J.M. Dekker, L.T.A. Swinkels, T.M. Pol, A. Popma, "Biocueing and ambulatory biofeedback to enhance emotion regulation: A review of studies investigating non-psychiatric and psychiatric populations", International Journal of Psychophysiology, vol. 159, pp. 94-106, Jan. 2021 (doi: 10.1¬016/j.ijpsycho.2020.11.009).
[39] E. Hurt, L.E. Arnold, N. Lofthouse, "Quantitative EEG neurofeedback for the treatment of pediatric attention-deficit/hyperactivity disorder, autism spectrum disorders, learning disorders, and epilepsy", Child and Adolescent Psychiatric Clinics of North America, vol. 23, no. 3, pp. 465-486, July 2014 (doi: 10.101¬6/j.chc.2014.02.001).
[40] S. Bartholdy, P. Musiat, I.C. Campbell, U. Schmidt, "The potential of neurofeedback in the treatment of Eating Disorders: A Review of the Literature", European Eating Disorders Review, vol. 21, no. 6, pp. 456-463, Sept. 2013 (doi: 10.1002/erv.2250).
[41] D.R. Simkin, R.W. Thatcher, J. Lubar, "Quantitative EEG and neurofeedback in children and adolescents: anxiety disorders, depressive disorders, comorbid addiction and attention-deficit/hyperactivity disorder, and brain injury", Child and Adolescent Psychiatric Clinics of North America, vol. 23, no. 3, pp. 427-464, July 2014 (doi: 10.1016/j.chc.2014.03.001).
[42] S. Roy, N. Mandal, A. Ray, P.K. Roy, A. Bhattacharyya, P.K. Saha, "Effectiveness of neurofeedback training, behaviour management including attention enhancement training and medication in children with attention-deficit/hyperactivity disorder– A comparative follow up study", Asian Journal of Psychiatry, vol. 76, Article Number: 103133, Oct. 2022 (doi: 10.1016/j.ajp.2022.103133).
[43] Y. Gil, G. Li, J. Lee, “Integrated real-time neurofeedback system to raise the frontal lobe activity: Design and implementation”, Proceecing of the IEEE/IEMBS, pp. 845-848, MN, USA, Sept. 2009 (doi: 10.1109/IEMBS.2009.5333098).
[44] Y. Freund, R.E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting", vol. 55, no. 1, pp. 119-139, Aug. 1997 (doi: 10.1006/jcss.1997.1504).
[45] W. Nan, F. Wan, Q. Tang, C.M. Wong, B. Wang, A. Rosa, "Eyes-closed resting EEG predicts the learning of alpha down-regulation in neurofeedback training", Frontiers in Psychology, vol. 9, Article Number: 30210419, Aug. 2018 (doi: 10.3389/fpsyg.2018.01607).
[46] T.F. Collura, J. Guan, J. Tarrant, J. Bailey, F. Starr, "EEG biofeedback case studies using live Z-score training and a normative database", Journal of Neurotherapy, vol. 14, no. 1, pp. 22-46, Feb. 2010 (doi: 10.1080/10874200903543963).
[47] M. Arns, J. Gunkelman, M. Breteler, D. Spronk, "EEG phenotypes predict treatment outcome to stimulants in children with ADHD", Journal of Integrative Neuroscience, vol. 7, no. 3, pp. 421-438, Sept. 2008 (doi: 10.1142/s0219635208001897).
[48] Y. Okumura, Y. Kita, M. Omori, K. Suzuki, A. Yasumura, A. Fukuda, M. Inagaki, "Predictive factors of success in neurofeedback training for children with ADHD", Developmental Neurorehabilitation, vol. 22, no. 1, pp. 3-12, Jan. 2019 (doi: 10.1080/17518423.2017.1326183).