{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T22:18:13Z","timestamp":1772749093977,"version":"3.50.1"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006477","name":"National Taiwan University","doi-asserted-by":"publisher","award":["#FD107016."],"award-info":[{"award-number":["#FD107016."]}],"id":[{"id":"10.13039\/501100006477","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec>\n<jats:title>Objective<\/jats:title>\n<jats:p>Accurate identification of children who will develop delay (DD) is challenging for therapists because recent studies have reported that children who underwent early intervention achieved more favorable outcomes than those who did not. In this study, we have investigated how the frequencies of three types of therapy, namely the physical therapy, the occupational therapy, and the speech therapy, received by a child can be exploited to predict whether the child suffers from DD or not. The effectiveness of the proposed approach is of high interest as these features can be obtained with essentially no cost and therefore a prediction model built accordingly can be employed to screen the subjects who may develop DD before advanced and costly diagnoses are carried out.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>This study has been conducted based on a data set comprising the records of 2,552 outpatients (N\u2009=\u200934,862 visits, mean age\u2009=\u200972.34 months) collected at a hospital in Taiwan from 2012 to 2016. We then built 3 types of machine learning based prediction models, namely the deep neural network models (DNN), the support vector machine (SVM) models, and the decision tree (DT) models, to evaluate the effectiveness of the proposed approach.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>Experimental results reveal that in terms of the F1 score, which is the harmonic mean of the sensitivity and the positive predictive value, the DT models outperformed the DNN models and the SVM models, if a high level of sensitivity is desired. In particular, the DT model developed in this study delivered the sensitivity at 0.902 and the positive predictive value at 0.723.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Conclusions<\/jats:title>\n<jats:p>What has been learned from this study is that the frequencies of the therapies that a child has received provide valuable information for predicting whether the child suffers from DD. Due to the performance observed in the experiments and the fact that these features can be obtained essentially without any cost, it is conceivable that the prediction models built accordingly can be wide exploited in clinical practices and significantly improve the treatment outcomes of the children who develop DD.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0324204","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:30:42Z","timestamp":1747762242000},"page":"e0324204","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Detection of pediatric developmental delay with machine learning technologies"],"prefix":"10.1371","volume":"20","author":[{"given":"Shin-Bo","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Hung","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng-Chin","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8270-0725","authenticated-orcid":true,"given":"Yen-Jen","family":"Oyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"issue":"8","key":"pone.0324204.ref001","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.1016\/j.jpedsurg.2012.01.010","article-title":"Long-term review of sutureless ward reduction in neonates with gastroschisis in the neonatal unit","volume":"47","author":"WW Choi","year":"2012","journal-title":"J Pediatr Surg"},{"key":"pone.0324204.ref002","author":"G Katuwal","year":"2017"},{"issue":"3","key":"pone.0324204.ref003","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1093\/inthealth\/ihaa044","article-title":"Early intervention for children with developmental disabilities in low and middle-income countries - the case for action","volume":"13","author":"T Smythe","year":"2021","journal-title":"Int Health"},{"issue":"3","key":"pone.0324204.ref004","doi-asserted-by":"crossref","first-page":"106","DOI":"10.3390\/reprodmed4020012","article-title":"A machine learning algorithm predicting infant psychomotor developmental delay using medical and social determinants","volume":"4","author":"D Waynforth","year":"2023","journal-title":"Reprod Med"},{"issue":"1","key":"pone.0324204.ref005","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1080\/10696679.2020.1860683","article-title":"Data, measurement, and causal inferences in machine learning: opportunities and challenges for marketing","volume":"29","author":"FJ Hair","year":"2021","journal-title":"J Mark Theory Pract"},{"issue":"4","key":"pone.0324204.ref006","article-title":"Use of machine learning to shorten observation-based screening and diagnosis of autism","volume":"2","author":"DP Wall","year":"2012","journal-title":"Transl Psychiatry"},{"key":"pone.0324204.ref007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1753-4631-4-S1-S1","article-title":"Classification of ADHD patients on the basis of independent ERP components using a machine learning system","volume":"4","author":"A Mueller","year":"2010","journal-title":"Nonlinear Biomed Phys"},{"key":"pone.0324204.ref008","doi-asserted-by":"crossref","first-page":"15030","DOI":"10.1038\/npjschz.2015.30","article-title":"Automated analysis of free speech predicts psychosis onset in high-risk youths","volume":"1","author":"G Bedi","year":"2015","journal-title":"NPJ Schizophr"},{"issue":"8","key":"pone.0324204.ref009","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1002\/aur.1960","article-title":"Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder","volume":"11","author":"L Bishop-Fitzpatrick","year":"2018","journal-title":"Autism Res"},{"key":"pone.0324204.ref010","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1111\/j.1365-2788.2006.00904.x","article-title":"Behaviour and emotional problems in toddlers with pervasive developmental disorders and developmental delay: associations with parental mental health and family functioning","volume":"50","author":"S Herring","year":"2006","journal-title":"J Intellect Disabil Res"},{"key":"pone.0324204.ref011","volume-title":"Prediction of the autism spectrum disorder diagnosis with linear discriminant analysis classifier and K-nearest neighbor in children 2018 6th International Symposium on Digital Forensic and Security (ISDFS)","author":"O Altay","year":"2018"},{"key":"pone.0324204.ref012","doi-asserted-by":"crossref","DOI":"10.1109\/SIU.2018.8404223","article-title":"Early autism diagnosis of children with machine learning algorithms.","volume-title":"2018 26th Signal Processing and Communications Applications Conference (SIU)","author":"F B\u00fcy\u00fckoflaz","year":"2018"},{"key":"pone.0324204.ref013","volume-title":"Combining phenotypic and resting-state fMRI data for autism classification with recurrent neural networks 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018); 2018","author":"NC Dvornek","year":"2018"},{"key":"pone.0324204.ref014","volume-title":"Classify autism and control based on deep learning and community structure on resting-state fMRI 2018 IEEE 10th International Conference on Advanced Computational Intelligence (ICACI); 2018","author":"D Liao","year":"2018"},{"key":"pone.0324204.ref015","volume-title":"A novel CAD system for autism diagnosis using structural and functional MRI 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017); 2017; Melbourne (VIC","author":"O Dekhil","year":"2017"},{"key":"pone.0324204.ref016","first-page":"1611","volume-title":"Predictive models for ASD based on multiple cortical features 2011 IEEE 8th International Conference on Fuzzy Systems and Knowledge Discovery; 2011","author":"Y Jiao","year":"2011"},{"key":"pone.0324204.ref017","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.nicl.2017.08.017","article-title":"Identification of autism spectrum disorder using deep learning and the ABIDE dataset","volume":"17","author":"AS Heinsfeld","year":"2017","journal-title":"Neuroimage Clin"},{"issue":"8","key":"pone.0324204.ref018","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1111\/jcpp.12559","article-title":"Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion","volume":"57","author":"D Bone","year":"2016","journal-title":"J Child Psychol Psychiatry"},{"issue":"12","key":"pone.0324204.ref019","doi-asserted-by":"crossref","first-page":"4880","DOI":"10.1002\/hbm.22957","article-title":"Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks","volume":"36","author":"Y Jin","year":"2015","journal-title":"Hum Brain Mapp"},{"issue":"4","key":"pone.0324204.ref020","doi-asserted-by":"crossref","first-page":"683","DOI":"10.2319\/071508-371.1","article-title":"Prognosis prediction for Class III malocclusion treatment by feature wrapping method","volume":"79","author":"B-M Kim","year":"2009","journal-title":"Angle Orthod"},{"key":"pone.0324204.ref021","doi-asserted-by":"crossref","first-page":"960672","DOI":"10.3389\/fpsyt.2022.960672","article-title":"Application and research progress of machine learning in the diagnosis and treatment of neurodevelopmental disorders in children","volume":"13","author":"C Song","year":"2022","journal-title":"Front Psychiatry"},{"issue":"1","key":"pone.0324204.ref022","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41746-022-00598-6","article-title":"Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder","volume":"5","author":"JT Megerian","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"1","key":"pone.0324204.ref023","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s40708-023-00186-8","article-title":"Machine learning determination of applied behavioral analysis treatment plan type","volume":"10","author":"J Maharjan","year":"2023","journal-title":"Brain Inform"},{"issue":"4","key":"pone.0324204.ref024","doi-asserted-by":"crossref","DOI":"10.2196\/13822","article-title":"Detecting Developmental Delay and Autism Through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study","volume":"21","author":"Q Tariq","year":"2019","journal-title":"J Med Internet Res"},{"key":"pone.0324204.ref025","doi-asserted-by":"crossref","DOI":"10.1176\/appi.books.9780890425596","volume-title":"Diagnostic and statistical manual of mental disorders: DSM-5","author":"Association American Psychiatric","year":"2013"},{"issue":"9","key":"pone.0324204.ref026","doi-asserted-by":"crossref","first-page":"5287","DOI":"10.19082\/5287","article-title":"Study of the C677T and 1298AC polymorphic genotypes of MTHFR Gene in autism spectrum disorder","volume":"9","author":"F El-Baz","year":"2017","journal-title":"Electron Physician"},{"key":"pone.0324204.ref027","doi-asserted-by":"crossref","first-page":"103375","DOI":"10.1016\/j.compbiomed.2019.103375","article-title":"A review of feature selection methods in medical applications","volume":"112","author":"B Remeseiro","year":"2019","journal-title":"Comput Biol Med"},{"key":"pone.0324204.ref028","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An introduction to statistical learning","author":"G James","year":"2013"},{"issue":"5","key":"pone.0324204.ref029","doi-asserted-by":"crossref","first-page":"3482","DOI":"10.1016\/j.eswa.2009.10.040","article-title":"A hybrid approach based on the combination of variable selection using decision trees and case-based reasoning using the Mahalanobis distance for bankruptcy prediction","volume":"37","author":"S Cho","year":"2010","journal-title":"Expert Syst Appl"},{"issue":"392","key":"pone.0324204.ref030","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1080\/01621459.1985.10478211","article-title":"The number of classes in chi-squared goodness-of-fit tests","volume":"80","author":"W Kallenberg","year":"1985","journal-title":"J Am Stat Assoc"},{"key":"pone.0324204.ref031","volume-title":"Data mining with decision trees: theory and applications","author":"O Maimon","year":"2014"},{"key":"pone.0324204.ref032","article-title":"Rectified decision trees: towards interpretability, compression, and empirical soundness","author":"J Bai","year":"2019","journal-title":"arXiv"},{"issue":"2","key":"pone.0324204.ref033","first-page":"168","article-title":"Classification assessment methods","volume":"17","author":"A Tharwat","year":"2020","journal-title":"Appl Comput Inform"},{"issue":"1","key":"pone.0324204.ref034","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/0377-2217(95)00246-4","article-title":"A comparison of neural networks and linear scoring models in the credit union environment","volume":"95","author":"VS Desai","year":"1996","journal-title":"Eur J Oper Res"},{"issue":"11","key":"pone.0324204.ref035","article-title":"Comparing machine learning with case-control models to identify confirmed dengue cases","volume":"14","author":"T-S Ho","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pone.0324204.ref036","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1038\/s41598-021-03687-w","article-title":"Machine learning for emerging infectious disease field responses","volume":"12","author":"H-YR Chiu","year":"2022","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0324204.ref037","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11222-009-9153-8","article-title":"Estimation of prediction error by using K-fold cross-validation","volume":"21","author":"T Fushiki","year":"2011","journal-title":"Stat Comput"},{"issue":"8","key":"pone.0324204.ref038","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/TKDE.2019.2912815","article-title":"Reliable accuracy estimates from k-fold cross-validation","volume":"32","author":"TT Wong","year":"2019","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"10","key":"pone.0324204.ref039","doi-asserted-by":"crossref","DOI":"10.2196\/21299","article-title":"Diagnostic Accuracy of Web-Based COVID-19 Symptom Checkers: Comparison Study","volume":"22","author":"N Munsch","year":"2020","journal-title":"J Med Internet Res"},{"key":"pone.0324204.ref040","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"pone.0324204.ref041","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"JA Hanley","year":"1982","journal-title":"Radiology"},{"issue":"8","key":"pone.0324204.ref042","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"T Fawcett","year":"2006","journal-title":"Pattern Recognit Lett"},{"issue":"12","key":"pone.0324204.ref043","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s00127-010-0294-z","article-title":"Social and demographic factors that influence the diagnosis of autistic spectrum disorders","volume":"46","author":"G Russell","year":"2011","journal-title":"Soc Psychiatry Psychiatr Epidemiol"},{"issue":"6","key":"pone.0324204.ref044","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1203\/PDR.0b013e31819e7203","article-title":"Epidemiology of pervasive developmental disorders","volume":"65","author":"E Fombonne","year":"2009","journal-title":"Pediatr Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:31:00Z","timestamp":1747762260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324204"}},"subtitle":[],"editor":[{"given":"Zeheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0324204","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]}}}