Constructing a predictive model for children with autism spectrum disorder based on whole brain magnetic resonance radiomics: a machine learning study.
Xi Chen, Jiaxuan Peng, Zihan Zhang, Qiaowei Song, Dongxue Li, Gongyong Zhai, Wanyun Fu, Zhenyu Shu
{"title":"Constructing a predictive model for children with autism spectrum disorder based on whole brain magnetic resonance radiomics: a machine learning study.","authors":"Xi Chen, Jiaxuan Peng, Zihan Zhang, Qiaowei Song, Dongxue Li, Gongyong Zhai, Wanyun Fu, Zhenyu Shu","doi":"10.3174/ajnr.A8939","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and purpose: </strong>Autism spectrum disorder (ASD) diagnosis remains challenging and could benefit from objective imaging-based approaches. This study aimed to construct a prediction model using whole-brain imaging radiomics and machine learning to identify children with ASD.</p><p><strong>Materials and methods: </strong>We analyzed 223 subjects (120 with ASD) from the ABIDE database, randomly divided into training and test sets (7:3 ratio), and an independent external test set of 87 participants from Georgetown University and University of Miami. Radiomics features were extracted from white matter, gray matter, and cerebrospinal fluid from whole-brain MR images. After feature dimensionality reduction, we screened clinical predictors using multivariate logistic regression and combined them with radiomics signatures to build machine learning models. Model performance was evaluated using ROC curves and by stratifying subjects into risk subgroups.</p><p><strong>Results: </strong>Radiomics markers achieved AUCs of 0.78, 0.75, and 0.74 in training, test, and external test sets, respectively. Verbal intelligence quotient(VIQ) emerged as a significant ASD predictor. The decision tree algorithm with radiomics markers performed best, with AUCs of 0.87, 0.84, and 0.83; sensitivities of 0.89, 0.84, and 0.86; and specificities of 0.70, 0.63, and 0.66 in the three datasets, respectively. Risk stratification using a cut-off value of 0.4285 showed significant differences in ASD prevalence between subgroups across all datasets (training: χ<sup>2</sup>=21.325; test: χ<sup>2</sup>=5.379; external test: χ<sup>2</sup>=21.52m, P<0.05).</p><p><strong>Conclusions: </strong>A radiomics signature based on whole-brain MRI features can effectively identify ASD, with performance enhanced by incorporating VIQ data and using a decision tree algorithm, providing a potential adaptive strategy for clinical practice.</p><p><strong>Abbreviations: </strong>ASD = Autism Spectrum Disorder; MRI = Magnetic Resonance Imaging; SVM = support vector machine; KNN = K-nearest neighbor; VIQ = Verbal intelligence quotient; FIQ = Full-Scale intelligence quotient; ROC = Receiver Operating Characteristic; AUC = Area under Curve.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AJNR. American journal of neuroradiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3174/ajnr.A8939","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Background and purpose: Autism spectrum disorder (ASD) diagnosis remains challenging and could benefit from objective imaging-based approaches. This study aimed to construct a prediction model using whole-brain imaging radiomics and machine learning to identify children with ASD.
Materials and methods: We analyzed 223 subjects (120 with ASD) from the ABIDE database, randomly divided into training and test sets (7:3 ratio), and an independent external test set of 87 participants from Georgetown University and University of Miami. Radiomics features were extracted from white matter, gray matter, and cerebrospinal fluid from whole-brain MR images. After feature dimensionality reduction, we screened clinical predictors using multivariate logistic regression and combined them with radiomics signatures to build machine learning models. Model performance was evaluated using ROC curves and by stratifying subjects into risk subgroups.
Results: Radiomics markers achieved AUCs of 0.78, 0.75, and 0.74 in training, test, and external test sets, respectively. Verbal intelligence quotient(VIQ) emerged as a significant ASD predictor. The decision tree algorithm with radiomics markers performed best, with AUCs of 0.87, 0.84, and 0.83; sensitivities of 0.89, 0.84, and 0.86; and specificities of 0.70, 0.63, and 0.66 in the three datasets, respectively. Risk stratification using a cut-off value of 0.4285 showed significant differences in ASD prevalence between subgroups across all datasets (training: χ2=21.325; test: χ2=5.379; external test: χ2=21.52m, P<0.05).
Conclusions: A radiomics signature based on whole-brain MRI features can effectively identify ASD, with performance enhanced by incorporating VIQ data and using a decision tree algorithm, providing a potential adaptive strategy for clinical practice.
Abbreviations: ASD = Autism Spectrum Disorder; MRI = Magnetic Resonance Imaging; SVM = support vector machine; KNN = K-nearest neighbor; VIQ = Verbal intelligence quotient; FIQ = Full-Scale intelligence quotient; ROC = Receiver Operating Characteristic; AUC = Area under Curve.