A dynamic nomogram for predicting early post-stroke disorder of consciousness among stroke patients: model development and temporal validation
Year: 2026
Type: article
Abstract: Objective This study aims to develop and validate a dynamic nomogram for the early prediction of post-stroke disorders of consciousness, tailored for general ward settings where rapid risk assessment without reliance on laboratory results is urgently needed. Methods This study enrolled 502 stroke patients as the modeling cohort, which was randomly divided into a training set ( n = 354) and an internal validation set ( n = 148) at a 7:3 ratio. An additional 186 stroke patients were recruited as a temporal validation cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariate logistic regression were applied to screen independent risk factors and construct the predictive model. The model performance was comprehensively evaluated using receiver operating characteristic (ROC) curves, calibration plots, decision curve analysis (DCA), and the Youden index. The study further constructed a dynamic nomogram to enable real-time risk calculation. Results The incidence of disorder of consciousness was 20.52% in the modeling cohort and 24.19% in the temporal validation cohort. Four independent predictors were identified: age, smoking status, systolic blood pressure, and National Institutes of Health Stroke Scale (NIHSS) score. The nomogram exhibited favorable discriminatory capacity, with area under the ROC curve (AUC) values of 0.860, 0.852, and 0.764 in the training, internal validation, and temporal validation sets, respectively. DCA demonstrated satisfactory clinical net benefit within the threshold probability range of 0.1–0.3. An illustrative threshold of 0.30 is presented for reference in general ward settings. Conclusion This dynamic nomogram, built on four readily available clinical indicators obtainable at admission without waiting for laboratory or imaging results, shows reasonable discrimination and calibration. This model may serve as an exploratory reference tool for early risk stratification of post-stroke disorders of consciousness in general wards. Further prospective studies are required to verify its clinical utility.
Source: Frontiers in Neurology
Language: English
Subfield: Clinical Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W7225789524