Related Experiment Video
Updated: Jan 18, 2026

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Prediction model for cardiovascular mortality risk in asthma patients based on machine learning
Yuxi Wang1, Linxia Fang1, Quanfang Liu1
1Department of Pneumology, Hangzhou Lin'an Traditional Chinese Medicine Hospital, Hangzhou, China.
A new machine learning model accurately predicts cardiovascular disease mortality in asthma patients using clinical and pulmonary function data. This tool aids in early risk identification and personalized prevention strategies for asthma individuals.
Area of Science:
- Cardiology
- Pulmonology
- Data Science
Background:
- Asthma is a prevalent chronic respiratory condition.
- Cardiovascular disease (CVD) mortality is a significant public health issue.
- Personalized CVD risk prediction tools are lacking for asthma patients.
Purpose of the Study:
- Develop and validate a machine learning model to predict incident CVD mortality in individuals with asthma.
- Compare the model's performance against existing risk scores (ASCVD, Framingham).
Main Methods:
- Utilized NHANES data (2007-2012) from 2,033 adult asthma participants.
- Selected predictors using LASSO and Cox regression; trained six machine learning algorithms.
- Assessed model discrimination and calibration; interpreted feature importance with SHAP values.
Main Results:
- Twelve key variables including clinical and pulmonary function indices (FENO, PEF) were identified as predictors.
- The developed model demonstrated strong calibration and discrimination (C-index: 0.863 training, 0.832 validation).
- The pulmonary function-augmented model outperformed ASCVD and Framingham risk scores.
Conclusions:
- A novel machine learning model integrating clinical and pulmonary function data accurately predicts CVD mortality in asthma patients.
- This tool facilitates early identification of high-risk individuals.
- Enables personalized preventive strategies for cardiovascular health in asthma management.
Related Concept Videos
Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
Asthma-I: Introduction
Asthma: Pathogenesis and Management
Asthma is classified as allergic and non-allergic. Allergens such as dust mites, pollen, and pet dander trigger allergic asthma, while factors like cold air, intense emotions, or exercise can induce non-allergic asthma.
Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
Asthma-III: Symptoms and Complications
Classification of Asthma
