Scholarlink

Respiratory diseases impose a significant health burden worldwide, affecting millions of individuals. Timely and accurate prediction of chronic respiratory conditions is essential for enhancing healthcare interventions and reducing the impact of these diseases on public health. In this research paper, we present a comprehensive analysis of chronic respiratory diseases in New Mexico, USA, using a dataset obtained from the local health department. Our study aims to predict respiratory diseases and compare the performance of eight machine learning algorithms and one deep learning model based on accuracy, precision, recall, F1-score, and time performance metrics. The dataset comprises over 37,000 records, encompassing various attributes such as name, age, sex, diseases, treatment, and nature, which are updated regularly on a quarterly basis. We explore the application of traditional machine learning algorithms in predicting respiratory diseases. Among these algorithms, the Light Gradient Boosting Machine (LGBMClassifier) emerges as the top-performing model, demonstrating impressive accuracy, precision, recall, and F1-score.

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

Performance Evaluation of Machine Learning and Deep Learning Models for Respiratory Disease Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Qasem M. M. Zarandah,
  • Salwani Mohd Daud,
  • Samy S. Abu-Naser

摘要

Respiratory diseases impose a significant health burden worldwide, affecting millions of individuals. Timely and accurate prediction of chronic respiratory conditions is essential for enhancing healthcare interventions and reducing the impact of these diseases on public health. In this research paper, we present a comprehensive analysis of chronic respiratory diseases in New Mexico, USA, using a dataset obtained from the local health department. Our study aims to predict respiratory diseases and compare the performance of eight machine learning algorithms and one deep learning model based on accuracy, precision, recall, F1-score, and time performance metrics. The dataset comprises over 37,000 records, encompassing various attributes such as name, age, sex, diseases, treatment, and nature, which are updated regularly on a quarterly basis. We explore the application of traditional machine learning algorithms in predicting respiratory diseases. Among these algorithms, the Light Gradient Boosting Machine (LGBMClassifier) emerges as the top-performing model, demonstrating impressive accuracy, precision, recall, and F1-score.