[Abstract] Objective: To investigate the value of N-terminal pro-brain natriuretic peptide (NT-proBNP) and high-sensitivity cardiac troponin T (hs-cTnT) in predicting long-term mortality risk in patients with acute ischemic stroke (AIS) and to develop and validate predictive models. Methods: This study is a single-center, retrospective study. AIS patients who underwent thrombectomy at the First Affiliated Hospital of Nanjing Medical University between January 2022 and December 2022 were enrolled and followed up for two years. Cox regression and LASSO regression were used to identify factors associated with all-cause mortality. Three predictive models were constructed: basic model, Model 1 (basic model + NT-proBNP), and Model 2 (basic model + hs-cTnT), and their predictive performances were compared. Results: A total of 230 AIS patients were included in the final analysis and were randomly assigned to the training set (n=146) and testing set (n=84). During the follow-up period, 83 all-cause deaths were recorded, with a mortality rate of 37.2%. Multivariate Cox regression showed that each 1000 pg/mL increase in NT-proBNP was associated with a 27% higher risk of 2-year all-cause death (HR = 1.27, 95% CI: 1.15-1.40, p < 0.001). In contrast, ln(hs-cTnT) was not significantly associated with mortality risk (HR = 1.11, 95% CI: 0.89-1.38, p = 0.372). Cox regression and LASSO identified the following mortality-related variables: history of atrial fibrillation, postoperative national institutes of health stroke scale (NIHSS), baseline hemoglobin, white blood cell count, and random blood glucose. These were used to build basic model. Area under the curve (AUC) of basic model was 0.816 in the training set and 0.778 in the testing set. Model 1 had an AUC of 0.866 in the training set and 0.799 in the testing set, showing improved predictive performance. Model 2 had an AUC of 0.811 in the training set and 0.788 in the testing set, with no significant improvement. Conclusion: NT-proBNP is an independent predictor of all-cause mortality in AIS patients and can enhance the predictive ability of mortality risk based on traditional clinical parameter models, contributing to the individualized management of AIS patients.