A retrospective study on the predictive efficacy of SOBDA and VSRQ scales for prognosis in elderly COPD patients.

Abstract

This retrospective study aimed to compare the predictive efficacy of the shortness of breath with daily activities (SOBDA) and ventilatory response to exercise questionnaire (VSRQ) in forecasting respiratory-related adverse events in elderly patients with chronic obstructive pulmonary disease (COPD) over a 6-month follow-up period post-discharge. A total of 92 COPD patients, treated according to the 2022 GOLD report and Chinese National COPD treatment guidelines, were enrolled. SOBDA and VSRQ scores were collected upon admission and assessed daily for the first 7 days. A random forest model was used to evaluate the predictive value of these scores in relation to respiratory adverse events, with a training/testing group split at a 4:1 ratio. Five patients were excluded due to loss to follow-up or death, resulting in 87 patients in the final analysis. The primary endpoint was the occurrence of COPD exacerbations and respiratory failure. The random forest model using VSRQ scores as the response variable outperformed the SOBDA model in terms of predictive accuracy (AUC: 0.84 vs 0.65) and error rate (21.74% vs 22%). Both models demonstrated high accuracy in predicting the absence of adverse events (VSRQ: 85.72%, SOBDA: 83.67%) but showed limited sensitivity in predicting their occurrence (VSRQ: 35%, SOBDA: 40%). The VSRQ questionnaire demonstrated superior predictive performance compared to SOBDA, suggesting that VSRQ may be a useful tool for identifying high-risk elderly COPD patients and guiding clinical decision-making. Further studies are needed to confirm these findings and explore the broader applicability of VSRQ in COPD prognosis.