Machine Learning Model for Predicting Risk of In-Hospital Mortality After Surgery in Congenital Heart Disease Patients

Overview

Journal Rev Cardiovasc Med

Specialty Cardiology & Vascular Diseases

Date 2024 Jul 30

PMID 39076183

Authors

Xinwei Du

Hao Wang

Shunmin Wang

Yi He

Jinghao Zheng

Haibo Zhang

Zedong Hao

Yiwei Chen

Zhiwei Xu

Zhaohui Lu

Affiliations

Soon will be listed here.

Abstract

Background: A machine learning model was developed to estimate the in-hospital mortality risk after congenital heart disease (CHD) surgery in pediatric patient.

Methods: Patients with CHD who underwent surgery were included in the study. A Extreme Gradient Boosting (XGBoost) model was constructed based onsurgical risk stratification and preoperative variables to predict the risk of in-hospital mortality. We compared the predictive value of the XGBoost model with Risk Adjustment in Congenital Heart Surgery-1 (RACHS-1) and Society of Thoracic Surgery-European Association for Cardiothoracic Surgery (STS-EACTS) categories.

Results: A total of 24,685 patients underwent CHD surgery and 595 (2.4%) died in hospital. The area under curve (AUC) of the STS-EACTS and RACHS-1 risk stratification scores were 0.748 [95% Confidence Interval (CI): 0.707-0.789, 0.001] and 0.677 (95% CI: 0.627-0.728, 0.001), respectively. Our XGBoost model yielded the best AUC (0.887, 95% CI: 0.866-0.907, 0.001), and sensitivity and specificity were 0.785 and 0.824, respectively. The top 10 variables that contribute most to the predictive performance of the machine learning model were saturation of pulse oxygen categories, risk categories, age, preoperative mechanical ventilation, atrial shunt, pulmonary insufficiency, ventricular shunt, left atrial dimension, a history of cardiac surgery, numbers of defects.

Conclusions: The XGBoost model was more accurate than RACHS-1 and STS-EACTS in predicting in-hospital mortality after CHD surgery in China.

Citing Articles

Using artificial intelligence to predict post-operative outcomes in congenital heart surgeries: a systematic review.

Mohammadi I, Rajai Firouzabadi S, Rajai Firouzabadi S, Hosseinpour M, Akhlaghpasand M, Hajikarimloo B BMC Cardiovasc Disord. 2024; 24(1):718.

PMID: 39702050 PMC: 11660586. DOI: 10.1186/s12872-024-04336-6.

Maximizing Survival in Pediatric Congenital Cardiac Surgery Using Machine Learning, Explainability, and Simulation Techniques.

Mauricio D, Cardenas-Grandez J, Uribe Godoy G, Rodriguez Mallma M, Maculan N, Mascaro P J Clin Med. 2024; 13(22).

PMID: 39598016 PMC: 11595128. DOI: 10.3390/jcm13226872.

Using Machine Learning and Feature Importance to Identify Risk Factors for Mortality in Pediatric Heart Surgery.

Kapsner L, Feisst M, Purbojo A, Prokosch H, Ganslandt T, Dittrich S Diagnostics (Basel). 2024; 14(22).

PMID: 39594254 PMC: 11592497. DOI: 10.3390/diagnostics14222587.

Performance of the Models Predicting In-Hospital Mortality in Patients with ST-Segment Elevation Myocardial Infarction with Predictors in Categorical and Continuous Forms.

Shakhgeldyan K, Kuksin N, Domzhalov I, Geltser B Sovrem Tekhnologii Med. 2024; 16(1):15-25.

PMID: 39421631 PMC: 11482098. DOI: 10.17691/stm2024.16.1.02.

References

Horer J, Kasnar-Samprec J, Cleuziou J, Strbad M, Wottke M, Kaemmerer H . Mortality Following Congenital Heart Surgery in Adults Can Be Predicted Accurately by Combining Expert-Based and Evidence-Based Pediatric Risk Scores. World J Pediatr Congenit Heart Surg. 2016; 7(4):425-35. DOI: 10.1177/2150135116656001. View

Yeh S, Chen H, Lu C, Wang J, Huang L, Huang S . Prevalence, mortality, and the disease burden of pediatric congenital heart disease in Taiwan. Pediatr Neonatol. 2013; 54(2):113-8. DOI: 10.1016/j.pedneo.2012.11.010. View

Wu M, Chen H, Lu C, Wang J, Huang S, Huang S . Prevalence of congenital heart disease at live birth in Taiwan. J Pediatr. 2010; 156(5):782-5. DOI: 10.1016/j.jpeds.2009.11.062. View

Jenkins K, Gauvreau K . Center-specific differences in mortality: preliminary analyses using the Risk Adjustment in Congenital Heart Surgery (RACHS-1) method. J Thorac Cardiovasc Surg. 2002; 124(1):97-104. DOI: 10.1067/mtc.2002.122311. View

Larrazabal L, Jenkins K, Gauvreau K, Vida V, Benavidez O, Gaitan G . Improvement in congenital heart surgery in a developing country: the Guatemalan experience. Circulation. 2007; 116(17):1882-7. DOI: 10.1161/CIRCULATIONAHA.107.695403. View

Chandler H, Kirsch R . Management of the Low Cardiac Output Syndrome Following Surgery for Congenital Heart Disease. Curr Cardiol Rev. 2015; 12(2):107-11. PMC: 4861938. DOI: 10.2174/1573403x12666151119164647. View

Li H, Ge J . Cardiovascular diseases in China: Current status and future perspectives. Int J Cardiol Heart Vasc. 2017; 6:25-31. PMC: 5497168. DOI: 10.1016/j.ijcha.2014.10.002. View

Cheng H, Almodovar M, Laussen P, Wypij D, Polito A, Brown D . Outcomes and risk factors for mortality in premature neonates with critical congenital heart disease. Pediatr Cardiol. 2011; 32(8):1139-46. DOI: 10.1007/s00246-011-0036-3. View

Benjamin E, Blaha M, Chiuve S, Cushman M, Das S, Deo R . Heart Disease and Stroke Statistics-2017 Update: A Report From the American Heart Association. Circulation. 2017; 135(10):e146-e603. PMC: 5408160. DOI: 10.1161/CIR.0000000000000485. View

10.

Boethig D, Jenkins K, Hecker H, Thies W, Breymann T . The RACHS-1 risk categories reflect mortality and length of hospital stay in a large German pediatric cardiac surgery population. Eur J Cardiothorac Surg. 2004; 26(1):12-7. DOI: 10.1016/j.ejcts.2004.03.039. View

11.

Spector L, Menk J, Knight J, McCracken C, Thomas A, Vinocur J . Trends in Long-Term Mortality After Congenital Heart Surgery. J Am Coll Cardiol. 2018; 71(21):2434-2446. PMC: 5978758. DOI: 10.1016/j.jacc.2018.03.491. View

12.

Volkova A, Ruggles K . Predictive Metagenomic Analysis of Autoimmune Disease Identifies Robust Autoimmunity and Disease Specific Microbial Signatures. Front Microbiol. 2021; 12:621310. PMC: 7969817. DOI: 10.3389/fmicb.2021.621310. View

13.

Nachom P, Ratanasit N . Incidence and Predictors of Long-Term Adverse Outcomes in Patients with Rheumatic Mitral Stenosis in Sinus Rhythm. J Med Assoc Thai. 2016; 99(4):374-80. View

14.

Ohuchi H, Miyazaki A, Negishi J, Hayama Y, Nakai M, Nishimura K . Hemodynamic determinants of mortality after Fontan operation. Am Heart J. 2017; 189:9-18. DOI: 10.1016/j.ahj.2017.03.020. View

15.

Kilic A, Goyal A, Miller J, Gjekmarkaj E, Tam W, Gleason T . Predictive Utility of a Machine Learning Algorithm in Estimating Mortality Risk in Cardiac Surgery. Ann Thorac Surg. 2019; 109(6):1811-1819. DOI: 10.1016/j.athoracsur.2019.09.049. View

16.

Ngiam K, Khor I . Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 2019; 20(5):e262-e273. DOI: 10.1016/S1470-2045(19)30149-4. View

17.

Jalali A, Lonsdale H, Do N, Peck J, Gupta M, Kutty S . Deep Learning for Improved Risk Prediction in Surgical Outcomes. Sci Rep. 2020; 10(1):9289. PMC: 7283236. DOI: 10.1038/s41598-020-62971-3. View

18.

Hoffman T, Wernovsky G, Atz A, Kulik T, Nelson D, Chang A . Efficacy and safety of milrinone in preventing low cardiac output syndrome in infants and children after corrective surgery for congenital heart disease. Circulation. 2003; 107(7):996-1002. DOI: 10.1161/01.cir.0000051365.81920.28. View

19.

Chang Junior J, Binuesa F, Caneo L, Turquetto A, Arita E, Barbosa A . Improving preoperative risk-of-death prediction in surgery congenital heart defects using artificial intelligence model: A pilot study. PLoS One. 2020; 15(9):e0238199. PMC: 7473591. DOI: 10.1371/journal.pone.0238199. View

20.

OConnor M, Glatz A, Rossano J, Shaddy R, Ryan R, Ravishankar C . Cumulative Effect of Preoperative Risk Factors on Mortality After Pediatric Heart Transplantation. Ann Thorac Surg. 2018; 106(2):561-566. DOI: 10.1016/j.athoracsur.2018.03.044. View