Scholarlink

The common sleep disorder known as sleep apnea is characterized by periodic pauses in breathing, typically caused by either airway obstruction (obstructive sleep apnea) or a failure of the brain to send appropriate signals to the muscles that control breathing (central sleep apnea). Significant health concerns are connected with this disorder, which has been linked to a number of comorbidities, such as diabetes, hypertension, cardiovascular disease, and cognitive impairment. Despite its prevalence and negative effects, sleep apnea remains underdiagnosed and undertreated. The study engages machine learning algorithms to detect sleep apnea with higher accuracy. The random forest classifier achieved 92.3% accuracy for identifying the problem from ECG data. And as 1D CNN model with accuracy 95% with ECG data for early diagnosis. These findings undercover the machine learning approaches that are cost efficient and more accurate. The study concludes that the use of machine learning techniques in clinical practice can significantly enhance the early detection and management of sleep apnea, reducing the potential health risks and improving patient outcomes.

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

Detection of Sleep Apnea Using Random Forest Classifier and 1D Deep Convolutional Neural Network (CNN)

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Akanksha Kochhar,
  • Ananya Sharma,
  • Shivani Goyal,
  • Archie Vijay,
  • Khushi,
  • Moolchand Sharma

摘要

The common sleep disorder known as sleep apnea is characterized by periodic pauses in breathing, typically caused by either airway obstruction (obstructive sleep apnea) or a failure of the brain to send appropriate signals to the muscles that control breathing (central sleep apnea). Significant health concerns are connected with this disorder, which has been linked to a number of comorbidities, such as diabetes, hypertension, cardiovascular disease, and cognitive impairment. Despite its prevalence and negative effects, sleep apnea remains underdiagnosed and undertreated. The study engages machine learning algorithms to detect sleep apnea with higher accuracy. The random forest classifier achieved 92.3% accuracy for identifying the problem from ECG data. And as 1D CNN model with accuracy 95% with ECG data for early diagnosis. These findings undercover the machine learning approaches that are cost efficient and more accurate. The study concludes that the use of machine learning techniques in clinical practice can significantly enhance the early detection and management of sleep apnea, reducing the potential health risks and improving patient outcomes.