Development and validation of a prediction model for postoperative hepatic dysfunction after Stanford type A aortic dissection_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

ZHOU Sisi ¹ , WEI Zhanhua ¹ , ZHOU Jiali ² , HAN Xiujuan ³ , LENG Huijun ⁴ , CHENG Tong ¹ , ZHENG Yao ⁴ ,  CAI Zhongxiang ¹

1. Department of Nursing, Renmin Hospital of Wuhan University, Wuhan, 430060, P. R. China;
2. Department of Cardiology, Renmin Hospital of Wuhan University, Wuhan, 430060, P. R. China;
3. Department of Cardiovascular Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, P. R. China;
4. Department of Cardiovascular Surgery, Renmin Hospital of Wuhan University, Wuhan, 430060, P. R. China;

Corresponding?author：

CAI Zhongxiang, Email: tg20201228@163.com

Keywords：

Stanford type A aortic dissection; hepatic dysfunction; predictors; machine learning; prediction model; nomogram

DOI：

10.7507/1007-4848.202603063

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To develop and validate a prediction model for postoperative hepatic dysfunction after Stanford type A aortic dissection (TAAD), providing a reference for early identification and intervention. Methods We retrospectively enrolled the patients with TAAD who underwent surgical treatment at Renmin Hospital of Wuhan University from August 2022 to August 2025 and at Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology from December 2022 to June 2025. The dataset was randomly divided into a training set and a validation set at a ratio of 7.5 : 2.5. Independent predictors were identified using univariate analysis and multivariate logistic regression. Predictive models were developed using logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost). Model performance was assessed using receiver operating characteristic (ROC) curves, DeLong tests, calibration curves, and decision curve analysis (DCA). A nomogram was constructed based on the optimal model. Results A total of 482 patients were included, comprising 368 males and 114 females, with a median age of 54 (45, 62) years. Among them, 214 (44.4%) patients developed postoperative hepatic dysfunction. Multivariable analysis identified five independent predictors: preoperative serum creatinine level, pericardial effusion, postoperative mechanical ventilation duration, procalcitonin, and total bilirubin (all P<0.05). In the validation cohort, the area under the curve (AUC) values of the LR, RF, and XGBoost models were 0.741, 0.725, and 0.712, respectively, with the LR model demonstrating the best overall performance. The DeLong test showed no significant difference in AUC among the three models (P>0.05). Calibration curves demonstrated better agreement for the LR model. The DCA indicated that the LR model provided greater net benefit across a wider range of threshold probabilities. Conclusion Machine learning models do not outperform traditional LR in predicting postoperative hepatic dysfunction after TAAD. The LR model demonstrats more stable predictive performance and greater clinical utility. The nomogram developed based on this model may provide a reference for individualized clinical risk assessment.

1.	王杰, 吳偉, 程龍, 等. Ⅱ型雜交手術與孫氏手術治療急性Stanford A型主動脈夾層療效的單中心回顧性隊列研究. 中國胸心血管外科臨床雜志, 2025, 32(5): 663-669.Wang J, Wu W, Cheng L, et al. Efficacy of type Ⅱ hybrid surgery versus Sun's surgery in the treatment of acute Stanford type A aortic dissection: a retrospective cohort study in a single center. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 663-669.
2.	Chen P, Li H, Liu C, et al. Postoperative pulmonary complications in acute type A aortic dissection. BMC Surg, 2025, 25(1): 318.
3.	王祥宇, 張成鑫. 急性A型主動脈夾層主動脈根部處理方式的研究進展. 中國胸心血管外科臨床雜志, 2025, 32(8): 1189-1194.Wang XY, Zhang CX. Progress in the root treatment of acute type A aortic dissection. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(8): 1189-1194.
4.	Zhang Y, Marimekala D, Xing H, et al. Machine learning-based prediction of 1-year mortality using nutritional and inflammatory factors for type A acute aortic dissection with malperfusion. Front Cardiovasc Med, 2025, 12: 1539267.
5.	Zhou W, Wang G, Liu Y, et al. Outcomes and risk factors of postoperative hepatic dysfunction in patients undergoing acute type A aortic dissection surgery. J Thorac Dis, 2019, 11(8): 3225-3233.
6.	Wang Z, Ge M, Chen C, et al. Hepatic dysfunction in patients who received acute DeBakey type Ⅰ aortic dissection repair surgery: incidence, risk factors, and long-term outcomes. J Cardiothorac Surg, 2021, 16(1): 296.
7.	Kirov H, Caldonazo T, Audisio K, et al. Association of liver dysfunction with outcomes after cardiac surgery: a meta-analysis. Interact Cardiovasc Thorac Surg, 2022, 35(6): ivac280.
8.	Wang Z, Chen T, Ge M, et al. The risk factors and outcomes of preoperative hepatic dysfunction in patients who receive surgical repair for acute type A aortic dissection. J Thorac Dis, 2021, 13(10): 5638-5648.
9.	Xu Y, Liu LZ, Lu HQ, et al. Risk factors for postoperative hepatic dysfunction in overweight patients with acute type A aortic dissection. BMC Surg, 2024, 24(1): 305.
10.	Baysal A, Sagiroglu G, Dogukan M, et al. Investigation of risk factors related to the development of hepatic dysfunction in patients with a low and moderate cardiac risk during open-heart surgeries. Braz J Cardiovasc Surg, 2021, 36(2): 219-228.
11.	Sheng W, Qiao H, Wang Z, et al. Analysis of prognosis and risk factors for postoperative hepatic dysfunction in patients with acute type A aortic dissection. Anatol J Cardiol, 2023, 27(4): 197-204.
12.	Han X, Wang W, Gu T, et al. Development and validation of a predictive model for postoperative hepatic dysfunction in Stanford type A aortic dissection. Sci Rep, 2025, 15(1): 22126.
13.	Kamath PS, Wiesner RH, Malinchoc M, et al. A model to predict survival in patients with end-stage liver disease. Hepatology, 2001, 33(2): 464-470.
14.	Liang S, Liu Y, Zhang B, et al. Postoperative hepatic dysfunction after frozen elephant trunk for type A aortic dissection. Front Cardiovasc Med, 2021, 8: 739606.
15.	Xinsai L, Zhengye W, Xuan H, et al. Prediction model of acute kidney injury after different types of acute aortic dissection based on machine learning. Front Cardiovasc Med, 2022, 9: 984772.
16.	Xie LF, Lin XF, Xie YL, et al. Development of a machine learning-based model to predict major adverse events after surgery for type A aortic dissection complicated by malnutrition. Front Nutr, 2024, 11: 1428532.
17.	Ma Y, Yang X, Weng C, et al. Unsupervised machine learning model for phenogroup-based stratification in acute type A aortic dissection to identify postoperative acute gastrointestinal injury. Front Cardiovasc Med, 2025, 11: 1514751.
18.	Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med, 2019, 380(14): 1347-1358.
19.	Lin X, Xie L, Jiang D, et al. Hepatic dysfunction and adverse outcomes after total arch repair of acute type a aortic dissection: application of the MELD-XI score. BMC Cardiovasc Disord, 2022, 22(1): 491.
20.	Hoit BD. Pericardial effusion and cardiac tamponade pathophysiology and new approaches to treatment. Curr Cardiol Rep, 2023, 25(9): 1003-1014.
21.	Adler Y, Charron P. The 2015 ESC Guidelines on the diagnosis and management of pericardial diseases. Eur Heart J, 2015, 36(42): 2873-2874.
22.	Ge M, Wang Z, Chen T, et al. Risk factors for and outcomes of prolonged mechanical ventilation in patients received DeBakey typeⅠ aortic dissection repairment. J Thorac Dis, 2021, 13(2): 735-742.
23.	Liu Y, Cai X, Fang R, et al. Future directions in ventilator-induced lung injury associated cognitive impairment: a new sight. Front Physiol, 2023, 14: 1308252.
24.	Liu H, Luo Z, Liu L, et al. Early kinetics of procalcitonin in predicting surgical outcomes in type A aortic dissection patients. Chin Med J (Engl), 2017, 130(10): 1175-1181.
25.	周桑榆, 劉雁翔, 張博文, 等. 實驗室檢查在主動脈夾層臨床診療中的應用價值. 中國胸心血管外科臨床雜志, 2025, 32(5): 722-726.Zhou SY, Liu YX, Zhang BW, et al. The clinical utility of laboratory tests in patients with aortic dissection. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 722-726.
26.	Raveendran D, Penny-Dimri JC, Segal R, et al. The prognostic significance of postoperative hyperbilirubinemia in cardiac surgery: systematic review and meta-analysis. J Cardiothorac Surg, 2022, 17(1): 129.

1. 王杰, 吳偉, 程龍, 等. Ⅱ型雜交手術與孫氏手術治療急性Stanford A型主動脈夾層療效的單中心回顧性隊列研究. 中國胸心血管外科臨床雜志, 2025, 32(5): 663-669.Wang J, Wu W, Cheng L, et al. Efficacy of type Ⅱ hybrid surgery versus Sun's surgery in the treatment of acute Stanford type A aortic dissection: a retrospective cohort study in a single center. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 663-669.
2. Chen P, Li H, Liu C, et al. Postoperative pulmonary complications in acute type A aortic dissection. BMC Surg, 2025, 25(1): 318.
3. 王祥宇, 張成鑫. 急性A型主動脈夾層主動脈根部處理方式的研究進展. 中國胸心血管外科臨床雜志, 2025, 32(8): 1189-1194.Wang XY, Zhang CX. Progress in the root treatment of acute type A aortic dissection. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(8): 1189-1194.
4. Zhang Y, Marimekala D, Xing H, et al. Machine learning-based prediction of 1-year mortality using nutritional and inflammatory factors for type A acute aortic dissection with malperfusion. Front Cardiovasc Med, 2025, 12: 1539267.
5. Zhou W, Wang G, Liu Y, et al. Outcomes and risk factors of postoperative hepatic dysfunction in patients undergoing acute type A aortic dissection surgery. J Thorac Dis, 2019, 11(8): 3225-3233.
6. Wang Z, Ge M, Chen C, et al. Hepatic dysfunction in patients who received acute DeBakey type Ⅰ aortic dissection repair surgery: incidence, risk factors, and long-term outcomes. J Cardiothorac Surg, 2021, 16(1): 296.
7. Kirov H, Caldonazo T, Audisio K, et al. Association of liver dysfunction with outcomes after cardiac surgery: a meta-analysis. Interact Cardiovasc Thorac Surg, 2022, 35(6): ivac280.
8. Wang Z, Chen T, Ge M, et al. The risk factors and outcomes of preoperative hepatic dysfunction in patients who receive surgical repair for acute type A aortic dissection. J Thorac Dis, 2021, 13(10): 5638-5648.
9. Xu Y, Liu LZ, Lu HQ, et al. Risk factors for postoperative hepatic dysfunction in overweight patients with acute type A aortic dissection. BMC Surg, 2024, 24(1): 305.
10. Baysal A, Sagiroglu G, Dogukan M, et al. Investigation of risk factors related to the development of hepatic dysfunction in patients with a low and moderate cardiac risk during open-heart surgeries. Braz J Cardiovasc Surg, 2021, 36(2): 219-228.
11. Sheng W, Qiao H, Wang Z, et al. Analysis of prognosis and risk factors for postoperative hepatic dysfunction in patients with acute type A aortic dissection. Anatol J Cardiol, 2023, 27(4): 197-204.
12. Han X, Wang W, Gu T, et al. Development and validation of a predictive model for postoperative hepatic dysfunction in Stanford type A aortic dissection. Sci Rep, 2025, 15(1): 22126.
13. Kamath PS, Wiesner RH, Malinchoc M, et al. A model to predict survival in patients with end-stage liver disease. Hepatology, 2001, 33(2): 464-470.
14. Liang S, Liu Y, Zhang B, et al. Postoperative hepatic dysfunction after frozen elephant trunk for type A aortic dissection. Front Cardiovasc Med, 2021, 8: 739606.
15. Xinsai L, Zhengye W, Xuan H, et al. Prediction model of acute kidney injury after different types of acute aortic dissection based on machine learning. Front Cardiovasc Med, 2022, 9: 984772.
16. Xie LF, Lin XF, Xie YL, et al. Development of a machine learning-based model to predict major adverse events after surgery for type A aortic dissection complicated by malnutrition. Front Nutr, 2024, 11: 1428532.
17. Ma Y, Yang X, Weng C, et al. Unsupervised machine learning model for phenogroup-based stratification in acute type A aortic dissection to identify postoperative acute gastrointestinal injury. Front Cardiovasc Med, 2025, 11: 1514751.
18. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med, 2019, 380(14): 1347-1358.
19. Lin X, Xie L, Jiang D, et al. Hepatic dysfunction and adverse outcomes after total arch repair of acute type a aortic dissection: application of the MELD-XI score. BMC Cardiovasc Disord, 2022, 22(1): 491.
20. Hoit BD. Pericardial effusion and cardiac tamponade pathophysiology and new approaches to treatment. Curr Cardiol Rep, 2023, 25(9): 1003-1014.
21. Adler Y, Charron P. The 2015 ESC Guidelines on the diagnosis and management of pericardial diseases. Eur Heart J, 2015, 36(42): 2873-2874.
22. Ge M, Wang Z, Chen T, et al. Risk factors for and outcomes of prolonged mechanical ventilation in patients received DeBakey typeⅠ aortic dissection repairment. J Thorac Dis, 2021, 13(2): 735-742.
23. Liu Y, Cai X, Fang R, et al. Future directions in ventilator-induced lung injury associated cognitive impairment: a new sight. Front Physiol, 2023, 14: 1308252.
24. Liu H, Luo Z, Liu L, et al. Early kinetics of procalcitonin in predicting surgical outcomes in type A aortic dissection patients. Chin Med J (Engl), 2017, 130(10): 1175-1181.
25. 周桑榆, 劉雁翔, 張博文, 等. 實驗室檢查在主動脈夾層臨床診療中的應用價值. 中國胸心血管外科臨床雜志, 2025, 32(5): 722-726.Zhou SY, Liu YX, Zhang BW, et al. The clinical utility of laboratory tests in patients with aortic dissection. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(5): 722-726.
26. Raveendran D, Penny-Dimri JC, Segal R, et al. The prognostic significance of postoperative hyperbilirubinemia in cardiac surgery: systematic review and meta-analysis. J Cardiothorac Surg, 2022, 17(1): 129.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Latest ArticlesDevelopment and validation of a prediction model for postoperative hepatic dysfunction after Stanford type A aortic dissection

Abstract Full text Figures/Tables Video References Cited by

Format

Content