ILA and Emphysema: Integrating Pulmonary and Cardiovascular Health
The AI-CVD™ initiative includes advanced emphysema scoring, highlighting the critical interplay between pulmonary and cardiovascular health. By quantifying emphysema in lung scans, AI-CVD™ provides valuable insights into the risks of chronic obstructive pulmonary disease (COPD) and atrial fibrillation (AF), fostering integrated care approaches.
Correlation with COPD and Atrial Fibrillation
Emphysema is closely linked to Chronic obstructive pulmonary disease (COPD), a progressive lung disease that significantly impacts quality of life and increases the risk of cardiovascular diseases. Studies have shown that patients with COPD have a higher prevalence of atrial fibrillation (AF), a common cardiac arrhythmia 3. The presence of emphysema can exacerbate systemic inflammation and oxidative stress, contributing to the development and progression of AF3.
AI-CVD™ Emphysema Index on 5800 MESA Cases: RUL (Right Upper Lobe)
Emphysema Scoring in AI-CVD™
Emphysema is a chronic lung condition characterized by damage to the alveoli, leading to breathing difficulties and reduced oxygen exchange.
AI-CVD™ utilizes advanced imaging algorithms to quantify emphysema in lung scans, providing a detailed assessment of lung health. This quantification is achieved by measuring the percentage of low attenuation areas (%LAA) in the lungs, which are indicative of emphysema severity.
AI-Derived Upper Lobe Lung Analysis Predicts Incident COPD and Atrial Fibrillation
Lung hypodensity, defined as regions of the lung parenchyma with attenuation values below −950 Hounsfield units (HU), is a known radiologic surrogate for emphysema and an established risk factor for chronic obstructive pulmonary disease (COPD) with emerging evidence as an atrial fibrillation (AF) risk factor. While prior studies have utilized semi-automated methods to quantify these low-attenuation areas, advances in artificial intelligence (AI) may enhance precision and reproducibility.
​
We aimed to evaluate whether AI-derived lung hypodensity, quantified as the percentage of voxels below −950 HU on cardiac computed tomography (CT) scans, is associated with the risk of developing COPD in a multi-ethnic, community-based population without baseline respiratory disease.
​
AI-driven measure of lung hypodensity on cardiac CT (percentage of lung voxels below −950 HU) is hypothesized to be an independent predictor of subsequent COPD. If validated, this opportunistic screening tool could facilitate earlier identification of individuals at elevated risk for COPD, enabling targeted preventive strategies and closer clinical surveillance.
Figure 1: Examples of artificial intelligence-cardiovascular disease liver segmentations in a typical coronary artery calcium (CAC) scan along with the distribution of liver attenuation index (LAI) in Multi Ethnic Study of Atherosclerosis (MESA)-1.
Figure 6: 15-year cardiovascular disease (CVD) incidence by liver attenuation index (LAI) and Agatston coronary artery calcium (CAC) score.
