Nomogram Model for Identifying the Risk of Coronary Heart Disease in Patients with Chronic Obstructive Pulmonary...

Area of Science:

• Cardiology
• Pulmonology
• Artificial Intelligence in Medicine

Background:

• Chronic Obstructive Pulmonary Disease (COPD) is associated with an increased risk of Coronary Heart Disease (CHD).
• Accurate risk stratification for CHD in COPD patients is crucial for timely intervention.

Purpose of the Study:

• To develop and validate a deep learning radiomics (DLR) nomogram for individualized CHD risk assessment in the COPD population.
• To integrate clinical, radiomics, and deep learning features for enhanced predictive performance.

Main Methods:

• Retrospective study of 543 COPD patients from two centers.
• Extraction of radiomics features from CT images and generation of deep learning features using ResNet50.
• Development of a combined predictive model integrating clinical, radiomics, and DLR features.

Main Results:

• The DLR nomogram demonstrated optimal predictive performance (Internal AUC: 0.800; External AUC: 0.761).
• The integrative nomogram showed significant AUC improvement over clinical and radiomics-only models in external validation.
• Decision curve analysis confirmed the nomogram's clinical utility for decision-making.

Conclusions:

• The developed nomogram effectively integrates diverse data types for superior CHD risk prediction in COPD.
• This tool holds promise for early intervention and improved management strategies for CHD in COPD patients.