Early Risk Prediction Model for Stroke-Heart Syndrome Following Endovascular Therapy

Stroke-heart syndrome (SHS) significantly impacts patient prognosis, and reperfusion treatment strategies may have an impact on the occurrence of SHS following acute ischemic stroke (AIS). This study aimed to develop a nomogram-based SHS prediction model for anterior circulation stroke patients after endovascular therapy (EVT), addressing the current gap in early risk stratification of this population. This retrospective study enrolled 218 AIS patients who underwent EVT between January 2013 and June 2021, with an observed SHS incidence of 13.8% within the first two weeks post-EVT. We used the least absolute shrinkage and selection operator regression and multivariate logistic regression analysis to identify variables strongly associated with SHS. The results showed that age (OR 1.060, 95% CI 1.021-1.100, P = 0.002), hyperlipidemia (OR 3.400, 95% CI 1.289-8.968, P = 0.013), creatinine (OR 1.023, 95% CI 1.000-1.046, P = 0.049), and total anterior circulation infarct (TACI, OR 4.875, 95% CI 1.984-11.980, P = 0.001) were significantly associated with SHS and were subsequently incorporated into the construction of a nomogram-based prediction model. The area under receiver-operating characteristic curve (AUC), calibration curve, Hosmer-Lemeshow test, and Brier score were employed to comprehensively assess the accuracy and calibration of this model. The results demonstrate that the model exhibits good discriminatory ability (AUC = 0.812), calibration (Hosmer-Lemeshow test P = 0.855, Brier score = 0.098), and robustness (internal cross-validation AUC = 0.811). Furthermore, we assessed neurological outcomes at 3 months post-stroke using the modified Rankin Scale and found that SHS was independently associated with an increased risk of unfavorable functional outcome (OR 3.267, 95% CI 1.159-9.212, P = 0.025). In conclusion, SHS significantly increases the risk of unfavorable outcomes in AIS patients undergoing EVT. The nomogram, incorporating age, hyperlipidemia, TACI, and creatinine, exhibits strong predictive accuracy for early SHS; nevertheless, multicenter prospective validation is warranted prior to clinical implementation.