Scholarlink

Using Support Vector Machines (SVM) and a variety of neurobiological parameters, such as genetic, demographic, motor, cognitive, psychiatric, functional, and imaging data, this study offers a prediction model for Huntington’s disease. The model seeks to improve prognosis and diagnosis accuracy for Huntington’s disease. The suggested model handles EEG, ECG, motor speech, MRI, and fNIRS data through preprocessing and feature extraction by utilizing machine-learning skills, namely SVM. With an accuracy of 93.7%, preliminary data show that SVM performs better than other methods. Additional scalability experiments confirm that SVM performs well even with larger datasets. The model has the potential to be an invaluable tool for early identification and tailored therapy in Huntington’s disease, as demonstrated by its accuracy, adaptability, and low mistake rate.

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

Huntington’s Disorder Prediction Using Hybrid Grid Search-SVM Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Saumya Pandey,
  • Sojal Srivastava

摘要

Using Support Vector Machines (SVM) and a variety of neurobiological parameters, such as genetic, demographic, motor, cognitive, psychiatric, functional, and imaging data, this study offers a prediction model for Huntington’s disease. The model seeks to improve prognosis and diagnosis accuracy for Huntington’s disease. The suggested model handles EEG, ECG, motor speech, MRI, and fNIRS data through preprocessing and feature extraction by utilizing machine-learning skills, namely SVM. With an accuracy of 93.7%, preliminary data show that SVM performs better than other methods. Additional scalability experiments confirm that SVM performs well even with larger datasets. The model has the potential to be an invaluable tool for early identification and tailored therapy in Huntington’s disease, as demonstrated by its accuracy, adaptability, and low mistake rate.