Neurological deterioration occurs in 8%-40% of patients with acute posterior circulation cerebral infarction (APCCI), leading to higher disability and mortality. We developed and validated a prognostic model integrating dynamic physiological indicators and quantitative neuroimaging indicators for early risk stratification. We retrospectively enrolled patients with APCCI from Peking University Shenzhen Hospital into training set (n = 447) and testing set (n = 94). The model incorporates quantitative neuroimaging (mean apparent diffusion coefficient value (MAV) of infarct lesions) and dynamic physiological monitoring (systolic blood pressure variability), combining qualitative and quantitative approaches to better characterize infarction and hemodynamic instability. A nomogram was constructed and evaluated using discrimination, calibration, and clinical decision curve analysis (DCA). The model demonstrated moderate discrimination, with an AUC of 0.74 (95% CI: 0.62–0.86) in the testing set, and ideal calibration (Brier score 0.15). DCA confirmed superior clinical benefit within an 8%–56% threshold range. Both MAV and blood pressure variability were significant predictors, highlighting their added prognostic value beyond conventional factors. The prognostic model effectively identifies APCCI patients at risk of neurological deterioration by incorporating innovative neuroimaging and dynamic monitoring indicators. Temporal validation shows promising performance in the validation cohort, and further multi-center validation is warranted for clinical adoption.
Guo et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: