Wearable EEG Neurofeedback Based-on Machine Learning Algorithms for Children with Autism: A Randomized, Placebo-controlled Study

Abstract

Objective

Behavioral interventions have been shown to ameliorate the electroencephalogram (EEG) dynamics underlying the behavioral symptoms of autism spectrum disorder (ASD), while studies have also demonstrated that mirror neuron mu rhythm-based EEG neurofeedback training improves the behavioral functioning of individuals with ASD. This study aimed to test the effects of a wearable mu rhythm neurofeedback training system based on machine learning algorithms for children with autism.

Methods

A randomized, placebo-controlled study was carried out on 60 participants aged 3 to 6 years who were diagnosed with autism, at two center-based intervention sites. The neurofeedback group received active mu rhythm neurofeedback training, while the control group received a sham neurofeedback training. Other behavioral intervention programs were similar between the two groups.

Results

After 60 sessions of treatment, both groups showed significant improvements in several domains including language, social and problem behavior. The neurofeedback group showed significantly greater improvements in expressive language (P=0.013) and cognitive awareness (including joint attention, P=0.003) than did the placebo-controlled group.

Conclusion

Artificial intelligence-powered wearable EEG neurofeedback, as a type of brain-computer interface application, is a promising assistive technology that can provide targeted intervention for the core brain mechanisms underlying ASD symptoms.

Keywords

neurofeedback training / autism spectrum disorder / artificial intelligence / mu rhythm / brain-computer interface / wearable technology

References

[1] Maenner MJ, Warren Z, Williams AR, et al. Prevalence and Characteristics of Autism Spectrum Disorder Among Children Aged 8 Years—Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2020. MMWR Surveill Summ, 2023, 72(2): 1-14

[2] Leigh JP, Du J. Brief report: Forecasting the economic burden of autism in 2015 and 2025 in the United States. J Autism Dev Disord, 2015, 45: 4135-4139

[3] Zhou H, Xu X, Yan W, et al. Prevalence of Autism Spectrum Disorder in China: A Nationwide Multicenter Population-based Study Among Children Aged 6 to 12 Years. Neurosci Bull, 2020, 36: 961-971

[4] Zhao YN, Li ZW, Li L, et al. Current status of autism spectrum disorder screening in children aged 0 to 6 years in China. Zhongguo Shengyu Jiankang Zazhi (Chinese), 2023, 34(5): 423-428

[5] Reichow B, Barton EE, Boyd BA, et al. Early intensive behavioral intervention (EIBI) for young children with autism spectrum disorders (ASD). Cochrane Database Syst Rev, 2012, 10: CD009260

[6] Pineda JA, Brang D, Hechtet E, et al. Positive behavioral and electrophysiological changes following neurofeedback training in children with autism. Res Autism Spectr Disord, 2008, 2: 557-581

[7] Pineda JA, Carrasco K, Datko M, et al. Neurofeedback training produces normalization in behavioral and electrophysiological measures of high-functioning autism. Philos Trans R Soc Lond B Biol Sci, 2014, 369: 20130183

[8] Friedrich EVC, Sivanathan A, Lim T, et al. An effective neurofeedback intervention to improve social interactions in children with autism spectrum disorder. J Autism Dev Disord, 2015, 45(12): 4084-4100

[9] Sitaram R, Ros T, Stoeckel L, et al. Closed-loop brain training: the science of neurofeedback. Nat Rev Neurosci, 2017, 18: 86-100

[10] Bagherzadeh Y, Baldauf D, Pantazis D, et al. Alpha Synchrony and the Neurofeedback Control of Spatial Attention. Neuron, 2020, 105: 1-11

[11] Mahrooz MH, Fattahzadeh F, Gharibzadeh S. Decoding the debate: a comparative study of brain-computer interface and neurofeedback. Appl Psychophysiol Biofeedback, 2024, 49(1): 47-53

[12] Steiner NJ, Frenette EC, Rene KM, et al. In-school neurofeedback training for ADHD: sustained improvements from a randomized control trial. Pediatrics, 2014, 133: 483-492

[13] Luo X, Guo X, Zhao Q, et al. A randomized controlled study of remote computerized cognitive, neurofeedback, and combined training in the treatment of children with attentiondeficit/hyperactivity disorder. Eur Child Adolesc Psychiatry, 2023, 32: 1475-1486

[14] Arnold LE, Arns M, Barterian J, et al. Double-blind placebo-controlled randomized clinical trial of neurofeedback for attention-deficit/hyperactivity disorder with 13-month follow-up. J Am Acad Child Adolesc Psychiatry, 2021, 60(7): 841-855

[15] Oberman LM, Hubbard EM, McCleery JP, et al. EEG evidence for mirror neuron dysfunction in autism spectrum disorders. Cogn Brain Res, 2005, 24: 190-198

[16] Pineda JA. The functional significance of mu rhythms: translating “seeing” and “hearing” into “doing”. Brain Res Rev, 2005, 50(1): 57-68

[17] Molcho L, Maimon NB, Regev-Plotnik N, et al. Single-channel EEG features reveal an association with cognitive decline in seniors performing auditory cognitive assessment. Front Aging Neurosci, 2022, 14: 773692

[18] Kovacevic N, Ritter P, Tays W, et al. ‘My virtual dream’: Collective neurofeedback in an immersive art environment. PloS One, 2015, 10(7): e0130129

[19] Kosmyna N, Maes P. AttentivU: An EEG-Based Closed-Loop Biofeedback System for Real-Time Monitoring and Improvement of Engagement for Personalized Learning. Sensors, 2019, 19: 5200

[20] Schopler E, Reichler RJ, Renner BR. The childhood autism rating scale (CARS), 2010, Los Angeles, CA: Western Psychological Services

[21] Krug DA, Arick JR, Almond P. Autism screening instrument for educational planning, 2008, Austin: Pro-ed

[22] Constantino JN, Gruber CP. Social responsiveness scale: SRS, 2005, Torrance, CA: Western psychological services

[23] Schopler E, LansinG MD, Reichler RJ, et al. PEP-3, Psychoeducational profile, 2005

[24] Rimland B, Edelson M. Autism Treatment Evaluation Checklist, 1999, San Diego, CA: Autism Research Institute

[25] Dawson G, Jones EJH, Merkle K, et al. Early behavioral intervention is associated with normalized brain activity in young children with autism. J Am Acad Child Adolesc Psychiatry, 2012, 51(11): 1150-1159

[26] Aaronson B, Estes A, Rogers SJ, et al. The Early Start Denver Model intervention and mu rhythm attenuation in autism spectrum disorders. J Autism Dev Disord, 2022, 52(7): 3304-3313

[27] Corbett BA, Abdullah M. Video modeling: Why does it work for children with autism?. J Early Intensive Behav Interv, 2005, 2(1): 2

[28] Neurofeedback Collaborative Group Neurofeedback for attention-deficit/hyperactivity disorder: 25-month follow-up of double-blind randomized controlled trial. J Am Acad Child Adolesc Psychiatry, 2023, 62(4): 435-446

[29] Sperdin HF, Coito A, Kojovic N, et al. Early alterations of social brain networks in young children with autism. Elife, 2018, 7: e31670

[30] Müller RA, Fishman I. Brain connectivity and neuroimaging of social networks in autism. Trends Cogn Sci, 2018, 22(12): 1103-1116