Development and external validation of a machine learning model for cardiovascular risk prediction in individuals with chronic lung disease: Evidence from CHARLS and ELSA - Scorecard - MDSpire
Advertisement
Development and external validation of a machine learning model for cardiovascular risk prediction in individuals with chronic lung disease: Evidence from CHARLS and ELSA
Clinical Scorecard: Creation and external assessment of a machine learning approach for predicting cardiovascular risk in patients with chronic lung disorders: Insights from CHARLS and ELSA
At a Glance
Category
Detail
Condition
Chronic Lung Diseases (CLD) and Cardiovascular Disease (CVD)
Key Mechanisms
Chronic hypoxia, systemic inflammation, vascular dysfunction, and medication-related adverse effects promote CVD in CLD patients.
Target Population
Patients aged 45 years and older with self-reported chronic lung disease or asthma.
Care Setting
Primary care and telemedicine settings.
Key Highlights
COPD is the fourth leading cause of death worldwide, with projected prevalence reaching 600 million cases by 2050.
Patients with CLD have a significantly elevated risk of cardiovascular disease, which is a leading cause of hospitalization and mortality.
Machine learning algorithms, particularly XGBoost, show promise in predicting CVD risk in the CLD population.
Guideline-Based Recommendations
Diagnosis
CVD is determined based on self-reported physician diagnoses including heart diseases and stroke.
Management
Develop CVD risk prediction models tailored to the CLD population.
Monitoring & Follow-up
Utilize machine learning models for early identification of high-risk individuals.
Risks
Chronic lung diseases contribute to multisystem comorbidities and increase the risk of cardiovascular events.
Patient & Prescribing Data
Adults aged 45 years and older with chronic lung disease or asthma.
Integration of multidimensional variables for precise risk stratification.
Clinical Best Practices
Employ machine learning technologies for CVD risk prediction in patients with CLD.
Utilize external validation data to enhance model robustness and generalizability.
