Key result
Clinical-psychological nomogram identifies sleep disturbance in CAD patients with an AUC of ~0.91.
Why the study?
Sleep disturbance is highly prevalent in CAD and may worsen progression and cardiovascular risk, making the identification of affected patients clinically important.
Does a nomogram based on clinical and psychological factors accurately diagnose sleep disturbance in patients with coronary artery disease?
Cross-Sectional (n=256)
No
Does a nomogram based on clinical and psychological factors accurately diagnose sleep disturbance in patients with coronary artery disease?
A nomogram incorporating female sex, hypertension, hyperlipidemia, atrial fibrillation, and psychological scores can accurately identify sleep disturbance in patients with coronary artery disease.
Answers are grounded in this paper and cite their sources.
Nomogram may help identify sleep disturbance in CAD; leaves open clinical adoption pending prospective validation.
Introduction. Sleep disturbance is highly prevalent in patients with coronary artery disease (CAD) and may aggravate disease progression and increase cardiovascular risk. Identifying affected patients is clinically important for improving prognosis. This study aimed to develop and validate a nomogram-based diagnostic model for assessing sleep disturbance in CAD patients, providing an intuitive clinical assessment tool. Methods. This cross-sectional study enrolled 256 CAD patients, divided into a training cohort (n = 179) and a temporal validation cohort (n = 77). Sleep disturbance was assessed using the Pittsburgh Sleep Quality Index (PSQI), with a cutoff > 7. Candidate predictors included demographics, lifestyle factors, comorbidities, and psychological status (SDS/SAS scores). LASSO regression was used for predictor selection, followed by multivariable logistic regression to construct a nomogram. Model performance was evaluated by discrimination (AUC), calibration (calibration curves and Hosmer-Lemeshow test), and clinical utility (decision curve analysis). Results. Six predictors were selected by LASSO regression with non-zero coefficients at the optimal lambda: female sex, hypertension, hyperlipidemia, atrial fibrillation, SDS score, and SAS score. The multivariable logistic regression model showed that these factors were significantly associated with sleep disturbance status. The nomogram demonstrated excellent discriminative ability in the training cohort (AUC = 0.918, 95% CI: 0.899–0.935) and promising discriminative ability in the validation cohort (AUC = 0.906, 95% CI: 0.883–0.928). However, the validation cohort was small (n = 77), and the confidence intervals around the validation AUC were correspondingly wide, indicating some uncertainty in the estimate. Calibration curves showed high consistency between predicted probabilities and actual observed proportions, confirmed by Hosmer-Lemeshow goodness-of-fit tests (training: χ2 = 3.747, p = 0.879; validation: χ2 = 3.662, p = 0.886). Decision curve analysis demonstrated high net benefit across threshold probabilities from 1% to 99% in the training cohort and 1% to 93% in the validation cohort. Conclusions. A nomogram for assessing sleep disturbance in CAD patients was developed and temporally validated, showing promising diagnostic performance. However, no patient outcome data were collected, and only single-center validation was performed. These findings should be considered preliminary, and external multi-center validation in larger cohorts is needed before clinical implementation.
No takes yet. Share an insight, caveat, or question.
Tu et al. (2026) conducted a cross-sectional in Coronary Artery Disease (n=256). Nomogram diagnostic model was evaluated on Discrimination of the nomogram for assessing sleep disturbance in the validation cohort (AUC 0.906, 95% CI 0.883-0.928). A nomogram incorporating clinical and psychological factors demonstrated excellent discrimination for assessing sleep disturbance in patients with coronary artery disease, achieving a validation AUC of 0.906.
Synapse has enriched 10 related papers. Consider them for comparative context: