Scholarlink

Heart murmurs play an irreplaceable role in the assessment of cardiac conditions. The type of heart murmur is an important characteristic of cardiovascular diseases (CVDs). This study aims to classify the types of heart murmurs in patients using Support Vector Machine (SVM) from phonocardiogram (PCG) signals and to determine whether the patient’s heart is normal. The study used heart sound recordings from the CirCor DigiScope dataset, which provides labels for murmur classification, pitch, quality, timing, and more. To incorporate physiological information into the model’s judgment and consider the impact of age on heart development, this study focused on subjects labeled “Child.“ Additionally, due to the limited number of subjects with diastolic murmurs, the research focused solely on the evaluation of systolic murmurs. Since heart murmurs are a type of noise, we further calculate the first and second derivatives of the Mel spectrogram features as our characteristics. Finally, we use support vector machines for classification to determine whether the subject is a patient with heart murmurs. Ultimately, the precision of the diagnosis for patients reaches 82.7%.

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

Development of a Classification Model for Pediatric Cardiac Abnormality Detection Through the Integration of Child Physiological Data and Phonocardiogram Features

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yu-Yu Yen,
  • Chun Chang,
  • Jui-Hung Kao,
  • Woei-Chyn Chu

摘要

Heart murmurs play an irreplaceable role in the assessment of cardiac conditions. The type of heart murmur is an important characteristic of cardiovascular diseases (CVDs). This study aims to classify the types of heart murmurs in patients using Support Vector Machine (SVM) from phonocardiogram (PCG) signals and to determine whether the patient’s heart is normal. The study used heart sound recordings from the CirCor DigiScope dataset, which provides labels for murmur classification, pitch, quality, timing, and more. To incorporate physiological information into the model’s judgment and consider the impact of age on heart development, this study focused on subjects labeled “Child.“ Additionally, due to the limited number of subjects with diastolic murmurs, the research focused solely on the evaluation of systolic murmurs. Since heart murmurs are a type of noise, we further calculate the first and second derivatives of the Mel spectrogram features as our characteristics. Finally, we use support vector machines for classification to determine whether the subject is a patient with heart murmurs. Ultimately, the precision of the diagnosis for patients reaches 82.7%.