{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:30:49Z","timestamp":1787661049773,"version":"build-2736575974"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T00:00:00Z","timestamp":1681689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec><jats:title>Importance<\/jats:title><jats:p>Sleep disorders are one of the most frequent comorbidities in children with autism spectrum disorder (ASD). However, the link between neurodevelopmental effects in ASD children with their underlying sleep microarchitecture is not well understood. An improved understanding of etiology of sleep difficulties and identification of sleep-associated biomarkers for children with ASD can improve the accuracy of clinical diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>To investigate whether machine learning models can identify biomarkers for children with ASD based on sleep EEG recordings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Design, setting, and participants<\/jats:title><jats:p>Sleep polysomnogram data were obtained from the Nationwide Children\u2019 Health (NCH) Sleep DataBank. Children (ages: 8\u201316\u2009yrs) with 149 autism and 197 age-matched controls without neurodevelopmental diagnosis were selected for analysis. An additional independent age-matched control group (<jats:italic>n<\/jats:italic>\u2009=\u200979) selected from the Childhood Adenotonsillectomy Trial (CHAT) was also used to validate the models. Furthermore, an independent smaller NCH cohort of younger infants and toddlers (age: 0.5\u20133\u2009yr.; 38 autism and 75 controls) was used for additional validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Main outcomes and measures<\/jats:title><jats:p>We computed periodic and non-periodic characteristics from sleep EEG recordings: sleep stages, spectral power, sleep spindle characteristics, and aperiodic signals. Machine learning models including the Logistic Regression (LR) classifier, Support Vector Machine (SVM), and Random Forest (RF) model were trained using these features. We determined the autism class based on the prediction score of the classifier. The area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, and specificity were used to evaluate the model performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the NCH study, RF outperformed two other models with a 10-fold cross-validated median AUC of 0.95 (interquartile range [IQR], [0.93, 0.98]). The LR and SVM models performed comparably across multiple metrics, with median AUC 0.80 [0.78, 0.85] and 0.83 [0.79, 0.87], respectively. In the CHAT study, three tested models have comparable AUC results: LR: 0.83 [0.76, 0.92], SVM: 0.87 [0.75, 1.00], and RF: 0.85 [0.75, 1.00]. Sleep spindle density, amplitude, spindle-slow oscillation (SSO) coupling, aperiodic signal\u2019s spectral slope and intercept, as well as the percentage of REM sleep were found to be key discriminative features in the predictive models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion and relevance<\/jats:title><jats:p>Our results suggest that integration of EEG feature engineering and machine learning can identify sleep-based biomarkers for ASD children and produce good generalization in independent validation datasets. Microstructural EEG alterations may help reveal underlying pathophysiological mechanisms of autism that alter sleep quality and behaviors. Machine learning analysis may reveal new insight into the etiology and treatment of sleep difficulties in autism.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpsyt.2023.1115374","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T14:43:13Z","timestamp":1681742593000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Identification of atypical sleep microarchitecture biomarkers in children with autism spectrum disorder"],"prefix":"10.3389","volume":"14","author":[{"given":"Caroline","family":"Martinez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe Sage","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,4,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"102","DOI":"10.3390\/jcm7050102","article-title":"The relationship between sleep problems, neurobiological alterations, Core symptoms of autism Spectrum disorder, and psychiatric comorbidities","volume":"7","author":"Mazzone","year":"2018","journal-title":"J Clin Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.sleep.2007.01.014","article-title":"Sleep in children with autistic spectrum disorder: a questionnaire and polysomnographic study","volume":"9","author":"Miano","year":"2007","journal-title":"Sleep Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1176\/appi.ajp.2019.19060666","article-title":"Sleep onset problems and subcortical development in infants later diagnosed with autism spectrum disorder","volume":"177","author":"Mac Duffie","year":"2020","journal-title":"Am J Psychiatry"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s40675-015-0012-1","article-title":"Sleep in autism Spectrum disorders","volume":"1","author":"Veatch","year":"2015","journal-title":"Curr Sleep Med Rep"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e12775","DOI":"10.1111\/jsr.12775","article-title":"NREM sleep EEG slow waves in autistic and typically developing children: morphological characteristics and scalp distribution","volume":"28","author":"Lehoux","year":"2019","journal-title":"J Sleep Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"659006","DOI":"10.3389\/fpsyt.2021.659006","article-title":"REM sleep EEG activity and clinical correlates in adults with autism","volume":"12","author":"Gagnon","year":"2021","journal-title":"Front Psych"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s40810-014-0001-58","article-title":"EEG changes associated with autistic spectrum disorders","volume":"1","author":"Boutros","year":"2015","journal-title":"Neuropsychiatr Electrophysiol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"304","DOI":"10.4103\/1817-1745.174438","article-title":"Autism and sleep disorders","volume":"10","author":"Devnani","year":"2015","journal-title":"J Pediatr Neurosci"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e112","DOI":"10.1212\/WNL.0000000000005759","article-title":"Spindle activity in young children with autism, developmental delay, or typical development","volume":"91","author":"Farmer","year":"2018","journal-title":"Neurology"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"101076","DOI":"10.1016\/j.dcn.2022.101076","article-title":"Periodic and aperiodic neural activity displays age-dependent changes across early-to-middle childhood","volume":"54","author":"Hill","year":"2022","journal-title":"Dev Cogn Neurosci"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"ENEURO.0224-21.2021","DOI":"10.1523\/ENEURO.0224-21.2021","article-title":"Aperiodic and periodic components of ongoing oscillatory brain dynamics link distinct functional aspects of cognition across adult lifespan","volume":"8","author":"Thuwal","year":"2021","journal-title":"eNeuro"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.bpsc.2017.11.007","article-title":"Machine learning for precision psychiatry: opportunities and challenges","volume":"3","author":"Bzdok","year":"2018","journal-title":"Biol Psychiatry"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"100602","DOI":"10.1016\/j.patter.2022.100602","article-title":"Modern views of machine learning for precision psychiatry","volume":"3","author":"Chen","year":"2022","journal-title":"Patterns"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1093\/jamia\/ocy064","article-title":"The national sleep research resource: towards a sleep data commons","volume":"25","author":"Zhang","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1056\/NEJMoa1215881","article-title":"Childhood Adenotonsillectomy trial (CHAT). A randomized trial of adenotonsillectomy for childhood sleep apnea","volume":"368","author":"Marcus","year":"2013","journal-title":"New Engl J Med"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e70092","DOI":"10.7554\/eLife.70092","article-title":"An open-source, high-performance tool for automated sleep staging","volume":"10","author":"Vallat","year":"2021","journal-title":"elife"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.21105\/joss.01026","article-title":"Pingouin: statistics in python","volume":"3","author":"Vallat","year":"2018","journal-title":"J Open Source Softw"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1111\/j.1365-2869.2009.00785.x","article-title":"Sleep classification according to AASM and Rechtschaffen and kales: effects on sleep scoring parameters of children and adolescents","volume":"19","author":"Novelli","year":"2010","journal-title":"J Sleep Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.jneumeth.2018.08.014","article-title":"A sleep spindle detection algorithm that emulates human expert spindle scoring","volume":"316","author":"Lacourse","year":"2019","journal-title":"J Neurosci Methods"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2427","DOI":"10.1152\/jn.00388.2019","article-title":"EEG power spectral slope differs by ADHD status and stimulant medication exposure in early childhood","volume":"122","author":"Robertson","year":"2019","journal-title":"J Neurophysiol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"100931","DOI":"10.1016\/j.dcn.2021.100931","article-title":"Behavioral and cognitive correlates of the aperiodic (1\/f-like) exponent of the EEG power spectrum in adolescents with and without ADHD","volume":"48","author":"Ostlund","year":"2021","journal-title":"Dev Cogn Neurosci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1038\/s41593-020-00744-x","article-title":"Parameterizing neural power spectra into periodic and aperiodic components","volume":"23","author":"Donoghue","year":"2020","journal-title":"Nat Neurosci"},{"key":"ref23","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1016\/j.jaac.2017.03.013","article-title":"What is the male-to-female ratio in autism spectrum disorder? A systematic review and meta-analysis","volume":"56","author":"Loomes","year":"2017","journal-title":"Child Adolesc Psychiatry"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"792","DOI":"10.21037\/atm.2019.11.53","article-title":"Emerging biomarkers in autism spectrum disorder: a systematic review","volume":"7","author":"Frye","year":"2019","journal-title":"Ann Transl Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cca.2019.12.009","article-title":"Biomarkers in autism spectrum disorders: current progress","volume":"502","author":"Shen","year":"2020","journal-title":"Clin Chim Acta"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/s41386-019-0409-5","article-title":"Sleep as a translationally-relevant endpoint in studies of autism spectrum disorder (ASD)","volume":"45","author":"Missig","year":"2020","journal-title":"Neuropsychopharmacology"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.ijpsycho.2015.05.00","article-title":"Intelligence measures and stage 2 sleep in typically developing and autistic children","volume":"97","author":"Tessier","year":"2015","journal-title":"Int J Psychophysiol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"201","DOI":"10.5935\/1984-0063.20200059","article-title":"Analysis of sleep spindles in children with Asperger\u2019s syndrome","volume":"14","author":"Cebreros-Paniagua","year":"2021","journal-title":"Sleep Sci"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3670951","DOI":"10.1155\/2016\/3670951","article-title":"Developmental changes in sleep spindle characteristics and sigma power across early childhood","volume":"2016","author":"McClain","year":"2016","journal-title":"Neural Plast"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"13613","DOI":"10.1523\/JNEUROSCI.2041-09.2009","article-title":"Broadband shifts in local field potential power spectra are correlated with single-neuron spiking in humans","volume":"29","author":"Manning","year":"2009","journal-title":"J Neurosci"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2944","DOI":"10.1523\/JNEUROSCI.2250-20.2021","article-title":"Network asynchrony underlying increased broadband gamma power","volume":"41","author":"Guyon","year":"2021","journal-title":"J Neurosci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e33477","DOI":"10.1371\/journal.pone.0033477","article-title":"Human gamma oscillations during slow wave sleep","volume":"7","author":"Valderrama","year":"2012","journal-title":"PLoS One"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s11689-017-9191-z","article-title":"A resting EEG study of neocortical hyperexcitability and altered functional connectivity in fragile X syndrome","volume":"9","author":"Wang","year":"2017","journal-title":"J Neurodev Disord"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"23242","DOI":"10.1073\/pnas.1820836117","article-title":"Critical period regulation across multiple timescales","volume":"117","author":"Reh","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.neuron.2019.10.008","article-title":"GABAergic restriction of network dynamics regulates interneuron survival in the developing cortex","volume":"105","author":"Duan","year":"2020","journal-title":"Neuron"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"3893","DOI":"10.3390\/jcm10173893","article-title":"Subjective and electroencephalographic sleep parameters in children and adolescents with autism spectrum disorder: a systematic review","volume":"10","author":"Petruzzelli","year":"2021","journal-title":"J Clin Med"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2023.1115374\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T14:43:17Z","timestamp":1681742597000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2023.1115374\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,17]]},"references-count":37,"alternative-id":["10.3389\/fpsyt.2023.1115374"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2023.1115374","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,17]]},"article-number":"1115374"}}