{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:00:48Z","timestamp":1793480448296,"version":"4.5.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"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>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Early Autism spectrum disorder (ASD) diagnosis is critical for intervention, yet current methods rely on subjective clinical observations. This study develops objective tools to classify ASD severity using 3D motor movement analysis, addressing motor abnormalities as core diagnostic features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A Random Forest (RF) model classified three severity levels using 463 motor features from 25 Kinect V2 joint points. Data from 109 children (50 typical, 50 moderate ASD, 9 severe ASD) were validated via 5-fold cross-validation and two held-out test sets (20% each). Shapley Additive Explanations (SHAP) analysis identified critical motor biomarkers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved 84.6\u00b110.9% accuracy (5-fold cross-validation) and 86.4% accuracy (internal and held-out test sets). For severe ASD, the model achieved 100% classification accuracy on synthetic test data (4\/4 cases; 95% CI: 39.8%-100.0%). However, this result represents a methodological proof-of-concept rather than clinical validation, as severe ASD features were synthetically generated from moderate ASD data and the model has not been validated on real Kinect-derived severe ASD motor data. SHAP analysis identified wrist movements, knee trajectories, and elbow-to-foot distances as key motor biomarkers for severity classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This Kinect-based approach with RF and SHAP offers effective, interpretable ASD severity assessment for typical and moderate ASD classes, with promising methodological foundations for severe ASD pending validation on real data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1751654","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T12:20:46Z","timestamp":1774268446000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SHAP-based explainable AI framework for autism severity classification using 3D motor biomarkers"],"prefix":"10.3389","volume":"17","author":[{"given":"Yelda","family":"F\u0131rat","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Mudanya University","place":["Bursa, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15585\/mmwr.ss7202a1","article-title":"Prevalence and characteristics of autism spectrum disorder among children aged 8 years \u2014 Autism and Developmental Disabilities Monitoring Network, 11 sites, United States 2023","volume":"72","author":"Maenner","year":"2023","journal-title":"MMWR Surveillance Summaries"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-023-05948-1","article-title":"Motor impairments in children with autism spectrum disorder: a systematic review and meta-analysis","volume":"54","author":"Kangarani-Farahani","year":"2024","journal-title":"J Autism Dev Disord"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2025.106002","article-title":"A scoping review of the motor impairments in autism spectrum disorder","volume":"169","author":"da Silva","year":"2025","journal-title":"Neurosci Biobehav Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s44192-025-00232-3","article-title":"Explainable AI in early autism detection: a literature review of interpretable machine learning approaches","volume":"5","author":"Agrawal","year":"2025","journal-title":"Discover Ment Health"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/biology14070832","article-title":"Increased temporal variability of gait in ASD: a motion capture and machine learning analysis","volume":"14","author":"Goldthorp","year":"2025","journal-title":"Biology"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.smhs.2023.10.007","article-title":"Clinical gait analysis in older children with autism spectrum disorder","volume":"6","author":"Wu","year":"2024","journal-title":"Sports Med Health Sci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1038\/s41598-025-85348-w","article-title":"Early detection of autism spectrum disorder: gait deviations and machine learning","volume":"15","author":"Ganai","year":"2025","journal-title":"Sci Rep"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.3390\/electronics14112231","article-title":"Autism spectrum disorder detection using skeleton-based body movement analysis via dual-stream deep learning","volume":"14","author":"Shin","year":"2025","journal-title":"Electronics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"29","DOI":"10.4103\/jmss.jmss_19_24","article-title":"Diagnosis of autism in children based on their gait pattern and movement signs using the Kinect sensor","volume":"14","author":"Yazdi","year":"2024","journal-title":"J Med Signals Sensors"},{"key":"B10","article-title":"Automated tracking and quantification of autistic behavioral symptoms using Microsoft Kinect","volume":"220","author":"Kang","year":"2016","journal-title":"Stud Health Technol Informatics"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4342","DOI":"10.3390\/s21134342","article-title":"Skeleton driven action recognition using an image-based spatial-temporal representation and convolution neural network","volume":"21","author":"Silva","year":"2021","journal-title":"Sensors"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.5061\/dryad.s7h44j150","article-title":"Three dimensional dataset combining gait and full body movement of children with autism spectrum disorders collected by Kinect v2 camera [Data set","author":"Al-Jubouri","year":"2020","journal-title":"Dryad Digital Repository"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e2432851","DOI":"10.1001\/jamanetworkopen.2024.32851","article-title":"Automated analysis of stereotypical movements in videos of children with autism spectrum disorder","volume":"7","author":"Barami","year":"2024","journal-title":"JAMA Netw Open"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106288","article-title":"Analyzing lower body movements using machine learning for early autism detection","volume":"94","author":"Aljabiri","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.10.011","article-title":"Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders","volume":"144","author":"Rad","year":"2018","journal-title":"Signal Processing"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s40489-024-00435-4","article-title":"Using machine learning for motion analysis to early detect autism spectrum disorder: a systematic review","author":"Simeoli","year":"2024","journal-title":"Rev J Autism Dev Disord"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500059","article-title":"Bimodal feature analysis with deep learning for autism spectrum disorder detection","volume":"34","author":"Colonnese","year":"2024","journal-title":"Int J Neural Syst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/s41398-024-02802-5","article-title":"Machine learning classification of autism spectrum disorder based on reciprocity in naturalistic social interactions","volume":"14","author":"Koehler","year":"2024","journal-title":"Trans Psychiatry"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e2429229","DOI":"10.1001\/jamanetworkopen.2024.29229","article-title":"Machine learning prediction of autism spectrum disorder from a minimal set of medical and background information","volume":"7","author":"Rajagopalan","year":"2024","journal-title":"JAMA Network Open"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12111136","article-title":"A scoping review of AI-based approaches for detecting autism traits using voice and behavioral data","volume":"12","author":"Rakotomanana","year":"2025","journal-title":"Bioengineering"},{"key":"B21","doi-asserted-by":"publisher","first-page":"17048","DOI":"10.1038\/s41598-023-43478-z","article-title":"A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework","volume":"13","author":"Ali","year":"2023","journal-title":"Sci Rep"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.12.044","article-title":"Subtyping cognitive profiles in autism spectrum disorder using a functional RF algorithm","volume":"172","author":"Feczko","year":"2018","journal-title":"NeuroImage"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071118","article-title":"Diagnostic biomarker exploration of autistic patients with different ages and different verbal intelligence quotients based on RF model","volume":"9","author":"Ke","year":"2021","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2024.110315","article-title":"Early detection of autism spectrum disorder using explainable AI and optimized teaching strategies","volume":"413","author":"Alzakari","year":"2025","journal-title":"J Neurosci Methods"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.618277","article-title":"Interpretable machine learning reveals dissimilarities between subtypes of autism spectrum disorder","volume":"12","author":"Garbulowski","year":"2021","journal-title":"Front Genet"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/1394830","article-title":"Interpretable learning approaches in resting-state functional connectivity analysis: the case of autism spectrum disorder","volume":"2020","author":"Hu","year":"2020","journal-title":"Comput Math Methods Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"7839","DOI":"10.1038\/s41598-021-87455-w","article-title":"Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification","volume":"11","author":"Harrison","year":"2021","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awt208","article-title":"Atypical basic movement kinematics in autism spectrum conditions","volume":"136","author":"Cook","year":"2013","journal-title":"Brain"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-015-2379-8","article-title":"Use of machine learning to identify children with autism and their motor abnormalities","volume":"45","author":"Crippa","year":"2015","journal-title":"J Autism Dev Disord"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1038\/srep31107","article-title":"Toward the autism motor signature: gesture patterns during smart tablet gameplay identify children with autism","volume":"6","author":"Anzulewicz","year":"2016","journal-title":"Sci Rep"},{"key":"B31","doi-asserted-by":"publisher","first-page":"e0182652","DOI":"10.1371\/journal.pone.0182652","article-title":"Applying machine learning to identify autistic adults using imitation: an exploratory study","volume":"12","author":"Li","year":"2017","journal-title":"PloS One"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/aur.70049","article-title":"Effective autism classification through grasping kinematics","volume":"18","author":"Freud","year":"2025","journal-title":"Autism Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"15069","DOI":"10.1038\/s41598-021-94378-z","article-title":"Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in young children","volume":"11","author":"Kojovic","year":"2021","journal-title":"Sci Rep"},{"key":"B34","doi-asserted-by":"publisher","first-page":"30283","DOI":"10.1038\/s41598-024-81652-z","article-title":"Using deep learning to classify developmental differences in reaching and placing movements in children with and without autism spectrum disorder","volume":"14","author":"Su","year":"2024","journal-title":"Sci Rep"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126295","article-title":"Introducing 3DCNN ResNets for ASD full-body kinematic assessment: A comparison with hand-crafted features","volume":"270","author":"Altozano","year":"2025","journal-title":"Expert Syst Applications"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"arXiv preprint arXiv:1705.07874"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1751654\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T12:20:47Z","timestamp":1774268447000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1751654\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":36,"alternative-id":["10.3389\/fpsyt.2026.1751654"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1751654","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]},"article-number":"1751654"}}