Abstract Background Pulmonary hypertension (PH) is a serious complication of chronic obstructive pulmonary disease (COPD), linked to worse prognosis and higher healthcare costs. Early detection is challenging due to non-specific symptoms and reliance on invasive diagnostics. This study aimed to develop and validate a non-invasive prediction model for PH in COPD patients using the PA: A ratio from routine chest CT. Methods A retrospective study included 320 COPD patients from the First Affiliated Hospital of Xinjiang Medical University (January–November 2024). The cohort comprised 170 males (53.1%) and 150 females (46.9%), with a median age of 70.5 years (IQR, 62–77). PH was diagnosed in 115 patients (35.9%) by echocardiography. Patients were randomly assigned to a training set (n = 224) or validation set (n = 96). LASSO regression selected key predictors, followed by logistic regression for model development. A nomogram was constructed, and performance assessed using ROC, AUC, calibration plots, and the Hosmer–Lemeshow test. Clinical utility was evaluated by decision curve analysis (DCA). Results Univariate analysis identified 19 variables associated with PH. LASSO regression reduced these to five predictors: BMI, PaCO₂, NT-proBNP, NLR, and PA: A. Multivariate logistic regression confirmed all five were independently associated with PH (P 0.05). DCA indicated favorable clinical utility across a wide range of thresholds. Conclusion The nomogram combining PA: A with key clinical variables accurately predicts PH in COPD patients. This non-invasive tool supports early detection and individualized risk assessment, with potential for routine clinical use.
Yan et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: