A prediction model for the death risk of aortic dissection based on machine learning and preoperative indicators_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

RONG Jianke ¹ , WANG Yeao ¹ , WEI Zhili ¹ , WAN Zunhui ² ,  DENG Yundan ²

1. The First Clinical Medical College of Lanzhou University, Lanzhou, 730000, P. R. China;
2. Department of Cardiovascular Surgery, The First Hospital of Lanzhou University, Lanzhou, 730000, P. R. China;

Corresponding?author：

DENG Yundan, Email: dengyundan_crij@163.com

Keywords：

Aortic dissection; machine learning; preoperative indicators; mortality risk prediction; SHAP theory; XGBoost algorithm

DOI：

10.7507/1007-4848.202504106

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To construct a preoperative objective index-based model for predicting the mortality risk of aortic dissection, aiming to provide a quick risk assessment tool for primary healthcare. Methods The patients with aortic dissection from the Medical Information Mart for Intensive Care (MIMIC-Ⅳ) database between 2008 and 2019 were included. These patients were randomly divided into a training set, a validation set, and a test set at a ratio of 7:2:1. Based on the Akaike information criterion (AIC), forward regression was used to select the risk factors for patients with post-dissection mortality, and the XGBoost algorithm was employed to establish the prediction model. The SHAP (SHapley Additive exPlanations) theory was used for interpretive analysis. Results Out of the 271 patients of aortic dissection, 158 were males and 113 were females, with a median age of 70.3 (58.8, 79.5) years. The training set, validation set, and test set consisted of 189, 54, and 28 patients, respectively. During the follow-up period, 99 (36.5%) deaths occurred. Forward stepwise regression based on the AIC, clinical relevance assessment and literature review, was employed to identify 18 preoperative independent predictors. An XGBoost prediction model was constructed accordingly. After grid search optimization, the model demonstrated good discrimination in both the validation set [area under the curve (AUC)=0.681] and the test set (AUC=0.735). The SHAP analysis indicated that age (mean |SHAP|=0.081), activated partial thromboplastin time (mean |SHAP|=0.065), and red cell distribution width (mean |SHAP|=0.038) were the top three predictive contributors. Conclusion The aortic dissection mortality risk prediction model constructed based on the XGBoost algorithm can effectively predict the incidence of mortality outcomes. Characteristic indicators such as age, activated partial thromboplastin time, and red cell distribution width can assist clinicians in identifying high-risk patients, making triage referral decisions, and optimizing preoperative interventions within the golden time window, ultimately aiming to reduce the mortality rate of patients with aortic dissection.

Citation： RONG Jianke, WANG Yeao, WEI Zhili, WAN Zunhui, DENG Yundan. A prediction model for the death risk of aortic dissection based on machine learning and preoperative indicators. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2026, 33(10): 1640-1649. doi: 10.7507/1007-4848.202504106 Copy

1.	Erbel R, Aboyans V, Boileau C, et al. 2014 ESC guidelines on the diagnosis and treatment of aortic diseases: document covering acute and chronic aortic diseases of the thoracic and abdominal aorta of the adult. The Task Force for the Diagnosis and Treatment of Aortic Diseases of the European Society of Cardiology (ESC)[J]. Eur Heart J, 2014, 35(41): 2873-2926.
2.	Gouveia E Melo R, Mour?o M, Caldeira D, et al. A systematic review and meta-analysis of the incidence of acute aortic dissections in population-based studies[J]. J Vasc Surg, 2022, 75(2): 709-720.
3.	Helder MRK, Schaff HV, Day CN, et al. Regional and temporal trends in the outcomes of repairs for acute type A aortic dissections[J]. Ann Thorac Surg, 2020, 109(1): 26-33.
4.	Sayed A, Munir M, Bahbah EI. Aortic dissection: a review of the pathophysiology, management and prospective advances[J/OL]. Curr Cardiol Rev, 2021, 17(4): e230421186875. DOI: 10.2174/1573403X16666201014142930.
5.	Kienzl D, Prosch H, T?pker M, et al. Imaging of non-cardiac, non-traumatic causes of acute chest pain[J]. Eur J Radiol, 2012, 81(12): 3669-3674.
6.	Evangelista A, Isselbacher EM, Bossone E, et al. Insights from the International Registry of Acute Aortic Dissection[J]. Circulation, 2018, 137(17): 1846-1860.
7.	Luo JC, Zhong J, Duan WX, et al. Early risk stratification of acute type A aortic dissection: development and validation of a predictive score[J]. Cardiovasc Diagn Ther, 2020, 10(6): 1827-1838.
8.	Czerny M, Siepe M, Beyersdorf F, et al. Prediction of mortality rate in acute type A dissection: the German Registry for Acute Type A Aortic Dissection score[J]. Eur J Cardiothorac Surg, 2020, 58(4): 700-706.
9.	Nashef SAM, Roques F, Sharples LD, et al. EuroSCORE Ⅱ[J]. Eur J Cardiothorac Surg, 2012, 41(4): 734-745.
10.	Kalender M, Adademir T, Tasar M, et al. Validation of EuroSCOREⅡ risk model for coronary artery bypass surgery in high-risk patients[J]. Pol J Cardio Thorac Surg, 2014, 3: 252-256.
11.	Aas K, Jullum M, L?land A. Explaining individual predictions when features are dependent: more accurate approximations to Shapley values[J/OL]. Artif Intell, 2021, 298: 103502. DOI: 10.1016/j.artint.2021.103502.
12.	Shi P, Tsai CL. A note on the unification of the Akaike information criterion[J]. J R Stat Soc Ser B Stat Methodol, 1998, 60(3): 551-558.
13.	Johnson AEW, Bulgarelli L, Shen L, et al. MIMIC-Ⅳ, a freely accessible electronic health record dataset[J/OL]. Sci Data, 2023, 10(1): 1. DOI: 10.1038/s41597-022-01899-x.
14.	Zeinali M, Shahmorad S, Mirnia K. Hermite and piecewise cubic Hermite interpolation of fuzzy data[J]. J Intell Fuzzy Syst, 2014, 26(6): 2889-2898.
15.	Zhang J, Xiong W, Yang J, et al. Enhanced machine learning models for predicting one-year mortality in individuals suffering from type A aortic dissection[J]. J Thorac Cardiovasc Surg, 2025, 169(4): 1191-1200.e3.
16.	Ertu?rul E, Baytar Z, ?atal ?, et al. Performance tuning for machine learning-based software development effort prediction models[J]. Turk J Electr Eng Comput Sci, 2019: 1308-1324.
17.	Carrel T, Sundt TM, von Kodolitsch Y, et al. Acute aortic dissection[J]. Lancet, 2023, 401(10378): 773-788.
18.	Trimarchi S, Eagle KA, Nienaber CA, et al. Role of age in acute type A aortic dissection outcome: report from the International Registry of Acute Aortic Dissection (IRAD)[J]. J Thorac Cardiovasc Surg, 2010, 140(4): 784-789.
19.	Fritze O, Romero B, Schleicher M, et al. Age-related changes in the elastic tissue of the human aorta[J]. J Vasc Res, 2012, 49(1): 77-86.
20.	Markson F, Orji R, Yusuf MH, et al. A retrospective study on the impact of protein energy malnutrition on in-hospital outcomes of patients with aortic dissection[J/OL]. J Am Coll Cardiol, 2023, 81(8): 2081. DOI: 10.1016/S0735-1097(23)02525-1.
21.	Murao S, Umemura Y, Mori H, et al. Prevalence and clinical impact of disseminated intravascular coagulation in acute aortic dissection: a nationwide cohort study[J/OL]. Res Pract Thromb Haemost, 2025, 9(1): 102656. DOI: 10.1016/j.rpth.2024.102656.
22.	Arima D, Suematsu Y, Yamada R, et al. Relationship of acute type A aortic dissection and disseminated intravascular coagulation[J]. J Vasc Surg, 2022, 75(5): 1553-1560. e1.
23.	Masubuchi T, Yoshitani K, Minami K, et al. Transfusion characteristics and hemostatic conditions in octogenarians undergoing emergency surgery for acute aortic dissection: a retrospective study[J/OL]. JA Clin Rep, 2020, 6(1): 52. DOI: 10.1186/s40981-020-00358-z.
24.	Salvagno GL, Sanchis-Gomar F, Picanza A, et al. Red blood cell distribution width: a simple parameter with multiple clinical applications[J]. Crit Rev Clin Lab Sci, 2015, 52(2): 86-105.
25.	Lippi G, Sanchis-Gomar F, Mattiuzzi C. Systematic literature review and critical analysis of RDW in patients with aortic pathologies[J/OL]. Curr Probl Cardiol, 2024, 49(5): 102476. DOI: 10.1016/j.cpcardiol.2024.102476.
26.	Baptista ML, Goebel K, Henriques EMP. Relation between prognostics predictor evaluation metrics and local interpretability SHAP values[J/OL]. Artif Intell, 2022, 306: 103667. DOI: 10.1016/j.artint.2022.103667.

1. Erbel R, Aboyans V, Boileau C, et al. 2014 ESC guidelines on the diagnosis and treatment of aortic diseases: document covering acute and chronic aortic diseases of the thoracic and abdominal aorta of the adult. The Task Force for the Diagnosis and Treatment of Aortic Diseases of the European Society of Cardiology (ESC)[J]. Eur Heart J, 2014, 35(41): 2873-2926.
2. Gouveia E Melo R, Mour?o M, Caldeira D, et al. A systematic review and meta-analysis of the incidence of acute aortic dissections in population-based studies[J]. J Vasc Surg, 2022, 75(2): 709-720.
3. Helder MRK, Schaff HV, Day CN, et al. Regional and temporal trends in the outcomes of repairs for acute type A aortic dissections[J]. Ann Thorac Surg, 2020, 109(1): 26-33.
4. Sayed A, Munir M, Bahbah EI. Aortic dissection: a review of the pathophysiology, management and prospective advances[J/OL]. Curr Cardiol Rev, 2021, 17(4): e230421186875. DOI: 10.2174/1573403X16666201014142930.
5. Kienzl D, Prosch H, T?pker M, et al. Imaging of non-cardiac, non-traumatic causes of acute chest pain[J]. Eur J Radiol, 2012, 81(12): 3669-3674.
6. Evangelista A, Isselbacher EM, Bossone E, et al. Insights from the International Registry of Acute Aortic Dissection[J]. Circulation, 2018, 137(17): 1846-1860.
7. Luo JC, Zhong J, Duan WX, et al. Early risk stratification of acute type A aortic dissection: development and validation of a predictive score[J]. Cardiovasc Diagn Ther, 2020, 10(6): 1827-1838.
8. Czerny M, Siepe M, Beyersdorf F, et al. Prediction of mortality rate in acute type A dissection: the German Registry for Acute Type A Aortic Dissection score[J]. Eur J Cardiothorac Surg, 2020, 58(4): 700-706.
9. Nashef SAM, Roques F, Sharples LD, et al. EuroSCORE Ⅱ[J]. Eur J Cardiothorac Surg, 2012, 41(4): 734-745.
10. Kalender M, Adademir T, Tasar M, et al. Validation of EuroSCOREⅡ risk model for coronary artery bypass surgery in high-risk patients[J]. Pol J Cardio Thorac Surg, 2014, 3: 252-256.
11. Aas K, Jullum M, L?land A. Explaining individual predictions when features are dependent: more accurate approximations to Shapley values[J/OL]. Artif Intell, 2021, 298: 103502. DOI: 10.1016/j.artint.2021.103502.
12. Shi P, Tsai CL. A note on the unification of the Akaike information criterion[J]. J R Stat Soc Ser B Stat Methodol, 1998, 60(3): 551-558.
13. Johnson AEW, Bulgarelli L, Shen L, et al. MIMIC-Ⅳ, a freely accessible electronic health record dataset[J/OL]. Sci Data, 2023, 10(1): 1. DOI: 10.1038/s41597-022-01899-x.
14. Zeinali M, Shahmorad S, Mirnia K. Hermite and piecewise cubic Hermite interpolation of fuzzy data[J]. J Intell Fuzzy Syst, 2014, 26(6): 2889-2898.
15. Zhang J, Xiong W, Yang J, et al. Enhanced machine learning models for predicting one-year mortality in individuals suffering from type A aortic dissection[J]. J Thorac Cardiovasc Surg, 2025, 169(4): 1191-1200.e3.
16. Ertu?rul E, Baytar Z, ?atal ?, et al. Performance tuning for machine learning-based software development effort prediction models[J]. Turk J Electr Eng Comput Sci, 2019: 1308-1324.
17. Carrel T, Sundt TM, von Kodolitsch Y, et al. Acute aortic dissection[J]. Lancet, 2023, 401(10378): 773-788.
18. Trimarchi S, Eagle KA, Nienaber CA, et al. Role of age in acute type A aortic dissection outcome: report from the International Registry of Acute Aortic Dissection (IRAD)[J]. J Thorac Cardiovasc Surg, 2010, 140(4): 784-789.
19. Fritze O, Romero B, Schleicher M, et al. Age-related changes in the elastic tissue of the human aorta[J]. J Vasc Res, 2012, 49(1): 77-86.
20. Markson F, Orji R, Yusuf MH, et al. A retrospective study on the impact of protein energy malnutrition on in-hospital outcomes of patients with aortic dissection[J/OL]. J Am Coll Cardiol, 2023, 81(8): 2081. DOI: 10.1016/S0735-1097(23)02525-1.
21. Murao S, Umemura Y, Mori H, et al. Prevalence and clinical impact of disseminated intravascular coagulation in acute aortic dissection: a nationwide cohort study[J/OL]. Res Pract Thromb Haemost, 2025, 9(1): 102656. DOI: 10.1016/j.rpth.2024.102656.
22. Arima D, Suematsu Y, Yamada R, et al. Relationship of acute type A aortic dissection and disseminated intravascular coagulation[J]. J Vasc Surg, 2022, 75(5): 1553-1560. e1.
23. Masubuchi T, Yoshitani K, Minami K, et al. Transfusion characteristics and hemostatic conditions in octogenarians undergoing emergency surgery for acute aortic dissection: a retrospective study[J/OL]. JA Clin Rep, 2020, 6(1): 52. DOI: 10.1186/s40981-020-00358-z.
24. Salvagno GL, Sanchis-Gomar F, Picanza A, et al. Red blood cell distribution width: a simple parameter with multiple clinical applications[J]. Crit Rev Clin Lab Sci, 2015, 52(2): 86-105.
25. Lippi G, Sanchis-Gomar F, Mattiuzzi C. Systematic literature review and critical analysis of RDW in patients with aortic pathologies[J/OL]. Curr Probl Cardiol, 2024, 49(5): 102476. DOI: 10.1016/j.cpcardiol.2024.102476.
26. Baptista ML, Goebel K, Henriques EMP. Relation between prognostics predictor evaluation metrics and local interpretability SHAP values[J/OL]. Artif Intell, 2022, 306: 103667. DOI: 10.1016/j.artint.2022.103667.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

A prediction model for the death risk of aortic dissection based on machine learning and preoperative indicators

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content