# Clinical History, Spirometry, and CT Features Can Predict Dyspnea in Smokers with and without Spirometry-Defined COPD

## TL;DR

This study shows that combining clinical history, lung function tests, and CT scans can accurately predict shortness of breath in smokers, both with and without COPD.

## Contribution

A novel predictive model using clinical, spirometry, and CT data accurately identifies dyspnea in smokers with and without COPD.

## Key findings

- A predictive model achieved an area under the curve of 0.85 in test data and 0.80 in external validation.
- Dyspnea predictions require data from at least two of three domains: clinical history, spirometry, or chest CT.
- CT emphysema and systemic inflammation are more significant in COPD patients with GOLD stages 2–4.

## Abstract

Dyspnea is common in smokers with or without chronic obstructive pulmonary disease. Its multifactorial nature makes it challenging to identify specific factors causing dyspnea in smokers with and without chronic obstructive pulmonary disease.

The study aims to identify associations between clinical history, spirometry, and computed tomography findings related to dyspnea in smokers, and to develop and compare dyspnea models using different variable combinations.

Dyspnea was defined as a self-reported modified Medical Research Council dyspnea scale score ≥ 2. Participants from the COPDGene Study dataset were utilized and split into training and testing samples (80%/20%) to develop and validate a predictive model. The ECLIPSE Study was used for external validation. Bivariable and multivariable logistic regression analyses were used to examine factors associated with dyspnea. Predictive models were developed using Elastic Net.

The final prediction model demonstrated good predictive performance, achieving an area under the curve of 0.85 in the test set and 0.80 in the external dataset. We confirmed prior associations with dyspnea and identified novel interactions of multiple risk factors with chronic obstructive pulmonary disease severity.

Dyspnea in smokers with and without chronic obstructive pulmonary disease can be predicted with high accuracy using a model that utilizes clinical history, spirometry, and chest CT imaging. To make accurate predictions, data from at least two of the three variable domains (clinical history, spirometry, or chest CT imaging) was required.

The online version contains supplementary material available at 10.1007/s00408-026-00871-5.

Interaction models indicate that while chronic bronchitis and respiratory exacerbations have a greater impact on dyspnea in smokers with preserved spirometry compared to chronic obstructive pulmonary disease (COPD) patients, computed tomography (CT) emphysema and systemic inflammation are more pronounced in smokers with Global Initiative for COPD (GOLD) stages 2–4 COPD.Elastic Net models accurately predict dyspnea using clinical data, spirometry, and chest CT.To make accurate dyspnea predictions, data from at least 2 of the 3 domains (clinical history, spirometry, or chest CT) were required.

Interaction models indicate that while chronic bronchitis and respiratory exacerbations have a greater impact on dyspnea in smokers with preserved spirometry compared to chronic obstructive pulmonary disease (COPD) patients, computed tomography (CT) emphysema and systemic inflammation are more pronounced in smokers with Global Initiative for COPD (GOLD) stages 2–4 COPD.

Elastic Net models accurately predict dyspnea using clinical data, spirometry, and chest CT.

To make accurate dyspnea predictions, data from at least 2 of the 3 domains (clinical history, spirometry, or chest CT) were required.

The online version contains supplementary material available at 10.1007/s00408-026-00871-5.