Scholarlink

Autism Spectrum Disorder (ASD) is a neurocognitive condition that affects social interaction, communication, expressive abilities, and behavioral patterns. The early diagnosis and intervention significantly improve learning, communication, and quality of life outcomes. This study aims to the early and accurate diagnosis of ASD using machine learning (ML) techniques based on behavioral and demographic data obtained from Kaggle. We used naïve Bayes (NB), k-nearest neighbors (KNN), and support vector machines (SVM) as base learners, as well as boosting-based ensembles (AdaBoost, LightGBM, XGBoost); a hybrid-kernel SVM variant; and a stacking ensemble. The results of the study indicate that among all methods, the stacking classifier outperformed all other methods, achieving an accuracy of 99.74%. These findings demonstrate the potential of stacking ensembles in developing intelligent systems to support early ASD diagnosis and intervention planning. Future research could focus on validating this approach on larger and more diverse clinical datasets (e.g., neuroimaging biomarkers, generative AI, or advanced ML frameworks) to enhance robustness, generalizability, and clinical applicability.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid Kernel SVM and Boosting Approaches for Accurate Autism Spectrum Disorder Screening

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Usman Ali,
  • Shaiza Shahid,
  • Misbah,
  • Shahzad Ali,
  • Sheraz Aslam,
  • Kainat Mustafa

摘要

Autism Spectrum Disorder (ASD) is a neurocognitive condition that affects social interaction, communication, expressive abilities, and behavioral patterns. The early diagnosis and intervention significantly improve learning, communication, and quality of life outcomes. This study aims to the early and accurate diagnosis of ASD using machine learning (ML) techniques based on behavioral and demographic data obtained from Kaggle. We used naïve Bayes (NB), k-nearest neighbors (KNN), and support vector machines (SVM) as base learners, as well as boosting-based ensembles (AdaBoost, LightGBM, XGBoost); a hybrid-kernel SVM variant; and a stacking ensemble. The results of the study indicate that among all methods, the stacking classifier outperformed all other methods, achieving an accuracy of 99.74%. These findings demonstrate the potential of stacking ensembles in developing intelligent systems to support early ASD diagnosis and intervention planning. Future research could focus on validating this approach on larger and more diverse clinical datasets (e.g., neuroimaging biomarkers, generative AI, or advanced ML frameworks) to enhance robustness, generalizability, and clinical applicability.