[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121416-en":3,"doc-seo-121416-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121416,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders - Classification with Machine Learning","Electroretinograms (ERGs) reveal systematic differences between typically developing groups and individuals diagnosed with autism spectrum disorder (ASD) or attention deficit/hyperactivity disorder (ADHD). Using a dataset of ERGs collected in ASD (n=77), ADHD (n=43), ASD+ADHD (n=21), and control (n=137) groups, the study applies machine learning with feature selection to improve classification across clinically defined populations. Time-domain and signal-analysis features are evaluated across multiple models. For ASD, balanced accuracy reaches 0.87 for male participants, and for ADHD 0.84 for female participants. Multi-class performance decreases, reaching 0.53 when all groups are included, indicating sex-dependent utility and limitations for broader classification.","Article  \nSpectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning  \nPaul A. Constable 1, *,†, Javier O. Pinzon-Arenas 2, Luis Roberto Mercado Diaz 2, Irene O. Lee 3, Fernando Marmolejo-Ramos 4, Lynne Loh 1, Aleksei Zhdanov 5, Mikhail Kulyabin 6, Marek Brabec 7,8, David H. Skuse 3, Dorothy A. Thompson 9,10 and Hugo Posada-Quintero 2,†  \nAcademic Editors: Verónica Barroso-García and Fernando Vaquerizo-Villar  \nReceived: 26 November 2024  \nRevised: 26 December 2024  \nAccepted: 27 December 2024  \nPublished: 28 December 2024  \nCitation: Constable, P.A.; Pinzon-Arenas, J.O.; Mercado Diaz, L.R.; Lee, I.O.; Marmolejo-Ramos, F.;  \nLoh, L.; Zhdanov, A.; Kulyabin, M.; Brabec, M.; Skuse, D.H.; et al. Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders:  \nClassification with Machine Learning. Bioengineering 2025, 12, 15 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)bioengineering12010015  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Caring Futures Institute, College of Nursing and Health Sciences, Flinders University, Adelaide 5000, SA, Australia; [lynne.loh@flinders.edu.au](lynne.loh@flinders.edu.au)  \n2 Biomedical Engineering Department, University of Connecticut, Storrs, CT 06269, USA; [javier.pinzon_arenas@uconn.edu](javier.pinzon_arenas@uconn.edu) (J.O.P.-A.); [luis.mercado_diaz@uconn.edu](luis.mercado_diaz@uconn.edu) (L.R.M.D.); [hugo.posada-quintero@uconn.edu](hugo.posada-quintero@uconn.edu) (H.P.-Q.)  \n3 Behavioural and Brain Sciences Unit, Population Policy and Practice Programme, UCL Great Ormond Street Institute of Child Health, University College London, London WC1N 1EH, UK; [irene.lee@ucl.ac.uk](irene.lee@ucl.ac.uk) (I.O.L.); [d.skuse@ucl.ac.uk](d.skuse@ucl.ac.uk) (D.H.S.)  \n4 College of Psychology and Education, Flinders University, Adelaide 5000, SA, Australia; [fernando.marmolejoramos@flinders.edu.au](fernando.marmolejoramos@flinders.edu.au)  \n5 “VisioMed.AI”, Golovinskoe Highway, 8/2A, 125212 Moscow, Russia; [zhdanov@visiomed.ai](zhdanov@visiomed.ai)  \n[6](6 Pattern Recognition Lab)[ Pattern Recognition Lab](6 Pattern Recognition Lab), [Friedrich-Alexander-Universit](Friedrich-Alexander-Universit)ä[t Erlangen-N](t Erlangen-N)ü[rnberg](rnberg), [91058 Erlangen](91058 Erlangen), [Germany](Germany); [mikhail.kulyabin@fau.de](mikhail.kulyabin@fau.de)  \n7 Institute of Computer Science of the Czech Academy of Sciences, Pod Vodarenskou Vezi 2,  \n182 00 Prague, Czech Republic; [mbrabec@cs.cas.cz](mbrabec@cs.cas.cz)  \n8 National Institute of Public Health, Srobarova 48, 100 00 Prague, Czech Republic  \n9 The Tony Kriss Visual Electrophysiology Unit, Clinical and Academic Department of Ophthalmology, Great Ormond Street Hospital for Children NHS Trust, London WC1N 3BH, UK; [dorothy.thompson@ucl.ac.uk](dorothy.thompson@ucl.ac.uk)  \n10 UCL Great Ormond Street Institute of Child Health, University College London, London WC1N 1EH, UK  \n* [Correspondence: paul.constable@flinders.edu.au](Correspondence: paul.constable@flinders.edu.au)[ ](Correspondence: paul.constable@flinders.edu.au)† These authors contributed equally to this work.  \nAbstract: Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity disorder (ADHD) . In a series of ERGs collected in ASD (n = 77), ADHD (n = 43), ASD + ADHD (n = 21), and control (n = 137) groups, this analysis explores the use of machine learning and feature selection techniques to improve the classification between these clinically defined groups. Standard t","cbCainLe7Wi8TyY2","https://ap.wps.com/l/cbCainLe7Wi8TyY2","pdf",5176633,1,30,"English","en",105,"# Abstract\n# Introduction\n# Methods\n## Data and Groups\n## Machine Learning and Feature Selection\n# Results\n## Two-Group Classification Performance\n## Multi-Class Performance and Limitations\n# Discussion\n# Conclusions\n# References","[{\"question\":\"What biological signal is analyzed to support classification in neurodevelopmental disorders?\",\"answer\":\"The analysis uses light-adapted electroretinogram (ERG) waveform signals, leveraging features from time-domain and signal analysis.\"},{\"question\":\"How are diagnostic groups defined in the study?\",\"answer\":\"Participants are grouped into ASD, ADHD, co-occurring ASD+ADHD, and control based on their clinical diagnoses.\"},{\"question\":\"What factors limit model performance when expanding to multiple classes?\",\"answer\":\"Model performance decreases for multi-class settings and is reported to depend on sex, becoming limited when all classes are included.\"}]","Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders - Classification with Machine Learning | PDF",1785735568,76,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"spectral-analysis-of-light-adapted-electroretinograms-in-neurodevelopmental-disorders-classification-with-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/spectral-analysis-of-light-adapted-electroretinograms-in-neurodevelopmental-disorders-classification-with-machine-learning/121416/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What biological signal is analyzed to support classification in neurodevelopmental disorders?","Question",{"text":75,"@type":76},"The analysis uses light-adapted electroretinogram (ERG) waveform signals, leveraging features from time-domain and signal analysis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are diagnostic groups defined in the study?",{"text":80,"@type":76},"Participants are grouped into ASD, ADHD, co-occurring ASD+ADHD, and control based on their clinical diagnoses.",{"name":82,"@type":73,"acceptedAnswer":83},"What factors limit model performance when expanding to multiple classes?",{"text":84,"@type":76},"Model performance decreases for multi-class settings and is reported to depend on sex, becoming limited when all classes are included.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":21,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]