[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126388-en":3,"doc-seo-126388-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126388,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",7,"Healthcare","Autism detection using facial and motor analysis using machine learning","The study proposes an objective method for detecting autism spectrum disorders (ASD) by analyzing spatiotemporal facial and motor behavior using machine learning. It aims to automate ASD diagnosis that is often delayed by subjective expert observations at early ages. A hybrid CNN+LSTM model extracts spatial features from video frames and tracks temporal dynamics via recurrent layers. MediaPipe face mesh, pose, and hands provide 1,639 facial and movement parameters, achieving about 85–90% validation performance and AUC above 0.90.","Autism detection using facial and motor analysis using machine  \nlearning  \nAizat Amirbay1, Nurlan Baigabylov2, Ayagoz Mukhanova1, Kuralay Mukhambetova2, Elyor Zaitov3, Roza Burganova4, Khayriniso Khusanova3, Feruza Akhmedova3  \n1Department of Information Systems, Faculty of Information Technology, L.N. Gumilyov Eurasian National University, Astana,  \nKazakhstan  \n2Department of Sociology, Faculty of Social Sciences, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan 3Department of Sociology, Faculty of Social Sciences, National University of Uzbekistan named after Mirzo Ulugbek, Tashkent,  \nUzbekistan  \n4Department of Social Work and Tourism, Esil University, Astana, Kazakhstan  \n\n| Article history:\u003Cbr>Received Mar 20, 2025 Revised Aug 8, 2025 Accepted Sep 1, 2025 | This paper proposes a method for detecting autism spectrum disorders (ASD) through the analysis of facial and motor features using machine learning. The aim is to develop an algorithm for automatic ASD diagnosis based on spatiotemporal behavioral patterns. Traditional diagnostic methods rely on subjective expert observations, often delaying intervention. To address this, a hybrid convolutional neural network and long short-term memory (CNN+LSTM) model was employed. Convolutional layers extracted spatial features from video frames, while recurrent layers tracked temporal dynamics. Using MediaPipe face mesh, pose, and hands models, 1,639 parameters were obtained, including facial and pose coordinates, hand landmarks, mouth aspect ratio (MAR), and motion energy. The dataset comprised 100 children, aged 5–9 years (50 with ASD, 50 typically developing (TD)) . Stratified cross-validation was applied to ensure subjectindependent evaluation. Results showed 90% accuracy on the training set, 85–90% on validation, and an area under the curve (AUC) greater than 0.90, confirming model stability. Data visualization highlighted significant differences in motor activity and emotional expression between groups. The proposed approach demonstrates the potential for robust and objective ASD detection. It can be applied in clinical and educational contexts to improve early diagnosis and timely intervention.\u003Cbr>This is an open access article under the CC BY-SA license.\u003Cbr> |\n| --- | --- |\n| Keywords:\u003Cbr>Autism spectrum disorders Early diagnosis\u003Cbr>Facial analysis\u003Cbr>Long short-term memory Mouth aspect ratio Spatiotemporal patterns |  |\n\nCorresponding Author:  \nNurlan Baigabylov  \nDepartment of Sociology, Faculty of Social Sciences, L.N. Gumilyov Eurasian National University 010000 Astana, Kazakhstan  \n[Email: baigabylov_no@enu.kz](Email: baigabylov_no@enu.kz)  \nArticle Info ABSTRACT  \n1. INTRODUCTION  \nThis study reports outcomes within the area of medical diagnostics, specifically concerned with the application of novel technologies for identification and investigation of diseases [1]-[3], such as prediction of autism spectrum disorders (ASD) [4] . ASD is a neurodevelopmental disorder that manifests itself during early childhood and involves social deficits, difficulties in communication, and atypical patterns of behavior [5], [6] . Its diagnosis is problematic since, at the early stages, behavioral signs may be weakly expressed [7], but key characteristics include avoidance of eye contact, lack of or excessive expression of emotions [8], and repetitive stereotypical movements.  \nEarly detection of this disorder plays a key role in ensuring early intervention and correctional programs that promote the social adaptation of children [9] . However, the complexity of diagnosis at early stages significantly limits the possibilities of timely provision of necessary assistance, emphasizing the relevance of research aimed at developing objective methods for identifying ASD [10] . Traditional diagnostic methods are based on subjective observations of parents and specialists, which increases the likelihood of late detection of the disorder and reduces the accuracy of diagnosis [11] ","cbCaioRrzt0vd5fl","https://ap.wps.com/l/cbCaioRrzt0vd5fl","pdf",1958775,10,1,16,"English","en",105,"# Abstract\n# 1. Introduction\n## Early detection and diagnostic challenges\n## Machine learning and computer vision approach\n## Study objective and feature extraction pipeline","[{\"question\":\"What problem does the study target in autism diagnosis?\",\"answer\":\"The study addresses delays and reduced accuracy caused by subjective early-stage observations of experts and parents, when behavioral signs may be weak.\"},{\"question\":\"Which model architecture is used for ASD detection?\",\"answer\":\"A hybrid convolutional neural network and long short-term memory (CNN+LSTM) model is used to extract spatial features and model temporal dynamics from video data.\"},{\"question\":\"How are facial and motor features obtained and represented?\",\"answer\":\"MediaPipe face mesh, pose, and hands models generate 1,639 quantitative parameters, including facial/pose coordinates, mouth aspect ratio (MAR), and motion energy.\"}]","Autism detection using facial and motor analysis using machine learning | PDF",1785904795,40,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"autism-detection-using-facial-and-motor-analysis-using-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/healthcare/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/autism-detection-using-facial-and-motor-analysis-using-machine-learning/126388/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the study target in autism diagnosis?","Question",{"text":77,"@type":78},"The study addresses delays and reduced accuracy caused by subjective early-stage observations of experts and parents, when behavioral signs may be weak.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which model architecture is used for ASD detection?",{"text":82,"@type":78},"A hybrid convolutional neural network and long short-term memory (CNN+LSTM) model is used to extract spatial features and model temporal dynamics from video data.",{"name":84,"@type":75,"acceptedAnswer":85},"How are facial and motor features obtained and represented?",{"text":86,"@type":78},"MediaPipe face mesh, pose, and hands models generate 1,639 quantitative parameters, including facial/pose coordinates, mouth aspect ratio (MAR), and motion energy.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,119,124,129,132,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":118},"healthcare",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":20,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]