Independent Risk Factors and Predictive Modeling of Pulmonary Embolism in Patients with Acute Ischemic Stroke

Objective: To investigate independent risk factors for pulmonary embolism (PE) in patients with acute ischemic stroke (AIS) and to develop a nomogram for PE risk prediction. Methods: We retrospectively analyzed clinical data from 214 AIS patients admitted between January 2017 and January 2025, including a training set (n = 150) and an independent validation set (n = 64). Demographic characteristics, medical history, cerebral infarction features, and laboratory parameters were collected. Independent risk factors for PE were identified using univariate and multivariate logistic regression analyses. A nomogram was constructed and internally validated using bootstrap resampling (1,000 iterations) and externally validated by temporal separation. Model performance was assessed using the concordance index (C-index), receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Results: Prolonged prothrombin time (PT), decreased serum albumin and globulin levels, elevated serum urea, and a history of cancer were identified as independent risk factors for PE in AIS patients (P < 0.01). The nomogram demonstrated excellent discrimination, with a C-index of 0.933 (95% CI: 0.893–0.974) in the training set and 0.902 (95% CI: 0.823–0.981) in the validation set. Calibration curves showed good agreement between predicted and observed outcomes, and DCA indicated meaningful clinical benefit. A total score ≥99 (predicted probability ≥50%) was defined as the high-risk threshold. Conclusions: Prolonged PT, hypoalbuminemia, hypoglobulinemia, elevated serum urea and history of cancer are independent risk factors for PE in AIS patients. The nomogram prediction model is helpful for early identification of patients with high risk of PE after AIS.