Scholarlink

<p>Mental health is a key determinant of overall well-being, influencing emotions, cognition, and behavior. Poor mental health can disrupt daily functioning and is often shaped by factors such as stress, trauma, and genetics. Early diagnosis and timely intervention are critical to improving outcomes. This study proposes an optimized ensemble machine learning approach, enhanced with Random Search Hyperparameter Optimization, to predict mental health conditions at an early stage. Using the publicly available Kaggle mental health dataset, the model was trained and evaluated following the CRISP-DM methodology. The optimized ensemble model achieved a classification accuracy of 83.33%, outperforming individual models and existing techniques. To facilitate practical use, the trained model was deployed as a web-based application using the Python Flask framework, offering an accessible and cost-effective solution for early mental health screening.</p>

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

CRISP-DM-guided hyperparameter-optimized ensemble model for mental health diagnosis

  • 期刊论文

  • 发表日期：

    2025年12月27日

查看全文
  • Ramesh Saha

摘要

Mental health is a key determinant of overall well-being, influencing emotions, cognition, and behavior. Poor mental health can disrupt daily functioning and is often shaped by factors such as stress, trauma, and genetics. Early diagnosis and timely intervention are critical to improving outcomes. This study proposes an optimized ensemble machine learning approach, enhanced with Random Search Hyperparameter Optimization, to predict mental health conditions at an early stage. Using the publicly available Kaggle mental health dataset, the model was trained and evaluated following the CRISP-DM methodology. The optimized ensemble model achieved a classification accuracy of 83.33%, outperforming individual models and existing techniques. To facilitate practical use, the trained model was deployed as a web-based application using the Python Flask framework, offering an accessible and cost-effective solution for early mental health screening.