Machine learning models for analyzing valvular heart disease combined with atrial fibrillation using electronic health records_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

LEI Nuoyangfan ¹ , TONG Qi ² , ZHANG Yiwen ¹ , WANG Zhengjie ² , LI Tao ² , PAN Fan ³ ,  QIAN Yongjun ² ,  ZHAO Qijun ¹

1. School of Computer Science (School of Software), Sichuan University, Chengdu, 610065, P. R. China;
2. Department of Cardiovascular Surgery, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
3. School of Electronic Information, Sichuan University, Chengdu, 610065, P. R. China;

Corresponding?author：

QIAN Yongjun, Email: qianyongjun@scu.edu.cn; ZHAO Qijun, Email: qjzhao@scu.edu.cn

Keywords：

Atrial fibrillation; valvular heart disease; machine learning; risk prediction; interpretable analysis

DOI：

10.7507/1007-4848.202204048

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To establish a machine learning based framework to rapidly screen out high-risk patients who may develop atrial fibrillation (AF) from patients with valvular heart disease and provide the information related to risk prediction to clinicians as clinical guidance for timely treatment decisions. Methods Clinical data were retrospectively collected from 1 740 patients with valvular heart disease at West China Hospital of Sichuan University and its branches, including 831 (47.76%) males and 909 (52.24%) females at an average age of 54 years. Based on these data, we built classical logistic regression, three standard machine learning models, and three integrated machine learning models for risk prediction and characterization analysis of AF. We compared the performance of machine learning models with classical logistic regression and selected the best two models, and applied the SHAP algorithm to provide interpretability at the population and single-unit levels. In addition, we provided visualization of feature analysis results. Results The Stack model performed best among all models (AF detection rate 85.6%, F1 score 0.753), while XGBoost outperformed the standard machine learning models (AF detection rate 71.9%, F1 score 0.732), and both models performed significantly better than the logistic regression model (AF detection rate 65.2%, F1 score 0.689). SHAP algorithm showed that left atrial internal diameter, mitral E peak flow velocity (Emv), right atrial internal diameter output per beat, and cardiac function class were the most important features affecting AF prediction. Both the Stack model and XGBoost had excellent predictive ability and interpretability. Conclusion The Stack model has the highest AF detection performance and comprehensive performance. The Stack model loaded with the SHAP algorithm can be used to screen high-risk patients for AF and reveal the corresponding risk characteristics. Our framework can be used to guide clinical intervention and monitoring of AF.

Citation： LEI Nuoyangfan, TONG Qi, ZHANG Yiwen, WANG Zhengjie, LI Tao, PAN Fan, QIAN Yongjun, ZHAO Qijun. Machine learning models for analyzing valvular heart disease combined with atrial fibrillation using electronic health records. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2022, 29(8): 953-962. doi: 10.7507/1007-4848.202204048 Copy

1.	Lippi G, Sanchis-Gomar F, Cervellin G. Global epidemiology of atrial fibrillation: An increasing epidemic and public health challenge. Int J Stroke, 2021, 16(2): 217-221.
2.	Dilaveris PE, Kennedy HL. Silent atrial fibrillation: Epidemiology, diagnosis, and clinical impact. Clin Cardiol, 2017, 40(6): 413-418.
3.	Schnabel RB, Sullivan LM, Levy D, et al. Development of a risk score for atrial fibrillation (Framingham Heart Study): A community-based cohort study Lancet, 2009, 373(9665): 739-745.
4.	Chamberlain AM, Agarwal SK, Folsom AR, et al. A clinical risk score for atrial fibrillation in a biracial prospective cohort (from the Atherosclerosis Risk in Communities study). Am J Cardiol, 2011, 107(1): 85-91.
5.	Alonso A, Krijthe BP, Aspelund T, et al. Simple risk model predicts incidence of atrial fibrillation in a racially and geographically diverse population: The CHARGE‐AF consortium. J Am Heart Ass, 2013, 2(2): e000102.
6.	Li Y G, Pastori D, Farcomeni A, et al. A simple clinical risk score (C2HEST) for predicting incident atrial fibrillation in Asian subjects: Derivation in 471, 446 Chinese subjects, with internal validation and external application in 451, 199 Korean subjects. Chest, 2019, 155(3): 510-518.
7.	Suenari K, Chao TF, Liu CJ, et al. Usefulness of HATCH score in the prediction of new-onset atrial fibrillation for Asians. Medicine, 2017, 96(1): e5597.
8.	Tseng AS, Noseworthy PA. Prediction of atrial fibrillation using machine learning: A review. Front Physiol, 2021, 12: 752317.
9.	Hill NR, Ayoubkhani D, McEwan P, et al. Predicting atrial fibrillation in primary care using machine learning. PLoS one, 2019, 14(11): e0224582.
10.	Tiwari P, Colborn KL, Smith DE, et al. Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation. JAMA Netw Open, 2020, 3(1): e1919396-e1919396.
11.	Sekelj S, Sandler B, Johnston E, et al. Detecting undiagnosed atrial fibrillation in UK primary care: Validation of a machine learning prediction algorithm in a retrospective cohort study. Eur J Prev Cardiol, 2021, 28(6): 598-605.
12.	Nakatani Y, Sakamoto T, Yamaguchi Y, et al. Left atrial wall thickness is associated with the low-voltage area in patients with paroxysmal atrial fibrillation. J Interv Card Electrophysiol, 2020, 58(3): 315-321.
13.	Siebermair J, Suksaranjit P, McGann CJ, et al. Atrial fibrosis in non–atrial fibrillation individuals and prediction of atrial fibrillation by use of late gadolinium enhancement magnetic resonance imaging. J Cardiovasc Electrophysiol, 2019, 30(4): 550-556.
14.	Dawwas GK, Barnes GD. Outcomes of direct oral anticoagulants in patients with atrial fibrillation and valvular heart disease. Curr Cardiol Rep, 2022: 1-8.
15.	吳越峰, 王琪, 吳明. 機器學習技術在食管癌研究領域中應用的現狀與展望. 中國胸心血管外科臨床雜志, 2022, 29(6): 770-776.
16.	Batista GE, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations. newsletter, 2004, 6(1): 20-29.
17.	Breiman L. Bagging predictors. Machine Learning, 1996, 24(2): 123-140.
18.	Bühlmann P, Yu B. Boosting Wiley Interdisciplinary Reviews. Computational Statistics, 2010, 2(1): 69-74.
19.	Breiman L. Random forests. Machine Learning, 2001, 45(1): 5-32.
20.	Chen T, Guestrin C. Xgboost: A scalable tree boosting system//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016: 785-794.
21.	Ke G, Meng Q, Finley T, et al. Lightgbm: A highly efficient gradient boosting decision tree. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017, 30: 3146-1354.
22.	Lundberg SM, Lee S I. A unified approach to interpreting model predictions. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017, 30: 4765-4774.
23.	Fawcett T. An introduction to ROC analysis pattern recognition letters, 2006, 27(8): 861-874.
24.	Ozenne B, Subtil F, Maucort-Boulch D. The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol, 2015, 68(8): 855-859.
25.	Boyd K, Eng KH, Page CD. Area under the precision-recall curve: point estimates and confidence intervals//Joint European conference on machine learning and knowledge discovery in databases. Springer: Berlin, Heidelberg, 2013. 451-466.
26.	Seewoester T, Spampinato RA, Sommer P, et al. Left atrial size and total atrial emptying fraction in atrial fibrillation progression. Heart Rhythm, 2019, 16(11): 1605-1610.
27.	Cui Q, Zhang W, Wang H, et al. Left and right atrial size and the occurrence predictors in patients with paroxysmal atrial fibrillation. Int J Cardiol, 2008, 130(1): 69-71.
28.	Burstein B, Nattel S. Atrial fibrosis: Mechanisms and clinical relevance in atrial fibrillation. J Am Coll Cardiol, 2008, 51(8): 802-809.
29.	Qiu D, Peng L, Ghista DN, et al. Left atrial remodeling mechanisms associated with atrial fibrillation. Cardiovasc Eng Technol, 2021, 12(3): 361-372.
30.	Vaziri SM, Larson MG, Benjamin EJ, et al. Echocardiographic predictors of nonrheumatic atrial fibrillation. The Framingham Heart Study. Circulation, 1994, 89(2): 724-730.
31.	Kalifa J, Jalife J, Zaitsev AV, et al. Intra-atrial pressure increases rate and organization of waves emanating from the superior pulmonary veins during atrial fibrillation. Circulation, 2003, 108(6): 668-671.
32.	van Brakel TJ, van der Krieken T, Westra SW, et al. Fibrosis and electrophysiological characteristics of the atrial appendage in patients with atrial fibrillation and structural heart disease. J Interv Card Electrophysiol, 2013, 38(2): 85-93.
33.	Staerk L, Sherer JA, Ko D, et al. Atrial fibrillation: Epidemiology, pathophysiology, and clinical outcomes. Circ Res, 2017, 120(9): 1501-1517.
34.	Jorfida M, Antolini M, Cerrato E, et al. Cryptogenic ischemic stroke and prevalence of asymptomatic atrial fibrillation: A prospective study. J Cardiovasc Med (Hagerstown), 2016, 17(12): 863-869.
35.	Christensen LM, Krieger DW, H?jberg S, et al. Paroxysmal atrial fibrillation occurs often in cryptogenic ischaemic stroke. Final results from the SURPRISE study. Eur J Neurol, 2014, 21(6): 884-889.
36.	何凱悅, 楊翠微. 基于心外膜標測的心房易顫性評估. 生物醫學工程學雜志, 2020, 37(3): 487-495, 501.

1. Lippi G, Sanchis-Gomar F, Cervellin G. Global epidemiology of atrial fibrillation: An increasing epidemic and public health challenge. Int J Stroke, 2021, 16(2): 217-221.
2. Dilaveris PE, Kennedy HL. Silent atrial fibrillation: Epidemiology, diagnosis, and clinical impact. Clin Cardiol, 2017, 40(6): 413-418.
3. Schnabel RB, Sullivan LM, Levy D, et al. Development of a risk score for atrial fibrillation (Framingham Heart Study): A community-based cohort study Lancet, 2009, 373(9665): 739-745.
4. Chamberlain AM, Agarwal SK, Folsom AR, et al. A clinical risk score for atrial fibrillation in a biracial prospective cohort (from the Atherosclerosis Risk in Communities study). Am J Cardiol, 2011, 107(1): 85-91.
5. Alonso A, Krijthe BP, Aspelund T, et al. Simple risk model predicts incidence of atrial fibrillation in a racially and geographically diverse population: The CHARGE‐AF consortium. J Am Heart Ass, 2013, 2(2): e000102.
6. Li Y G, Pastori D, Farcomeni A, et al. A simple clinical risk score (C2HEST) for predicting incident atrial fibrillation in Asian subjects: Derivation in 471, 446 Chinese subjects, with internal validation and external application in 451, 199 Korean subjects. Chest, 2019, 155(3): 510-518.
7. Suenari K, Chao TF, Liu CJ, et al. Usefulness of HATCH score in the prediction of new-onset atrial fibrillation for Asians. Medicine, 2017, 96(1): e5597.
8. Tseng AS, Noseworthy PA. Prediction of atrial fibrillation using machine learning: A review. Front Physiol, 2021, 12: 752317.
9. Hill NR, Ayoubkhani D, McEwan P, et al. Predicting atrial fibrillation in primary care using machine learning. PLoS one, 2019, 14(11): e0224582.
10. Tiwari P, Colborn KL, Smith DE, et al. Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation. JAMA Netw Open, 2020, 3(1): e1919396-e1919396.
11. Sekelj S, Sandler B, Johnston E, et al. Detecting undiagnosed atrial fibrillation in UK primary care: Validation of a machine learning prediction algorithm in a retrospective cohort study. Eur J Prev Cardiol, 2021, 28(6): 598-605.
12. Nakatani Y, Sakamoto T, Yamaguchi Y, et al. Left atrial wall thickness is associated with the low-voltage area in patients with paroxysmal atrial fibrillation. J Interv Card Electrophysiol, 2020, 58(3): 315-321.
13. Siebermair J, Suksaranjit P, McGann CJ, et al. Atrial fibrosis in non–atrial fibrillation individuals and prediction of atrial fibrillation by use of late gadolinium enhancement magnetic resonance imaging. J Cardiovasc Electrophysiol, 2019, 30(4): 550-556.
14. Dawwas GK, Barnes GD. Outcomes of direct oral anticoagulants in patients with atrial fibrillation and valvular heart disease. Curr Cardiol Rep, 2022: 1-8.
15. 吳越峰, 王琪, 吳明. 機器學習技術在食管癌研究領域中應用的現狀與展望. 中國胸心血管外科臨床雜志, 2022, 29(6): 770-776.
16. Batista GE, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations. newsletter, 2004, 6(1): 20-29.
17. Breiman L. Bagging predictors. Machine Learning, 1996, 24(2): 123-140.
18. Bühlmann P, Yu B. Boosting Wiley Interdisciplinary Reviews. Computational Statistics, 2010, 2(1): 69-74.
19. Breiman L. Random forests. Machine Learning, 2001, 45(1): 5-32.
20. Chen T, Guestrin C. Xgboost: A scalable tree boosting system//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016: 785-794.
21. Ke G, Meng Q, Finley T, et al. Lightgbm: A highly efficient gradient boosting decision tree. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017, 30: 3146-1354.
22. Lundberg SM, Lee S I. A unified approach to interpreting model predictions. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017, 30: 4765-4774.
23. Fawcett T. An introduction to ROC analysis pattern recognition letters, 2006, 27(8): 861-874.
24. Ozenne B, Subtil F, Maucort-Boulch D. The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol, 2015, 68(8): 855-859.
25. Boyd K, Eng KH, Page CD. Area under the precision-recall curve: point estimates and confidence intervals//Joint European conference on machine learning and knowledge discovery in databases. Springer: Berlin, Heidelberg, 2013. 451-466.
26. Seewoester T, Spampinato RA, Sommer P, et al. Left atrial size and total atrial emptying fraction in atrial fibrillation progression. Heart Rhythm, 2019, 16(11): 1605-1610.
27. Cui Q, Zhang W, Wang H, et al. Left and right atrial size and the occurrence predictors in patients with paroxysmal atrial fibrillation. Int J Cardiol, 2008, 130(1): 69-71.
28. Burstein B, Nattel S. Atrial fibrosis: Mechanisms and clinical relevance in atrial fibrillation. J Am Coll Cardiol, 2008, 51(8): 802-809.
29. Qiu D, Peng L, Ghista DN, et al. Left atrial remodeling mechanisms associated with atrial fibrillation. Cardiovasc Eng Technol, 2021, 12(3): 361-372.
30. Vaziri SM, Larson MG, Benjamin EJ, et al. Echocardiographic predictors of nonrheumatic atrial fibrillation. The Framingham Heart Study. Circulation, 1994, 89(2): 724-730.
31. Kalifa J, Jalife J, Zaitsev AV, et al. Intra-atrial pressure increases rate and organization of waves emanating from the superior pulmonary veins during atrial fibrillation. Circulation, 2003, 108(6): 668-671.
32. van Brakel TJ, van der Krieken T, Westra SW, et al. Fibrosis and electrophysiological characteristics of the atrial appendage in patients with atrial fibrillation and structural heart disease. J Interv Card Electrophysiol, 2013, 38(2): 85-93.
33. Staerk L, Sherer JA, Ko D, et al. Atrial fibrillation: Epidemiology, pathophysiology, and clinical outcomes. Circ Res, 2017, 120(9): 1501-1517.
34. Jorfida M, Antolini M, Cerrato E, et al. Cryptogenic ischemic stroke and prevalence of asymptomatic atrial fibrillation: A prospective study. J Cardiovasc Med (Hagerstown), 2016, 17(12): 863-869.
35. Christensen LM, Krieger DW, H?jberg S, et al. Paroxysmal atrial fibrillation occurs often in cryptogenic ischaemic stroke. Final results from the SURPRISE study. Eur J Neurol, 2014, 21(6): 884-889.
36. 何凱悅, 楊翠微. 基于心外膜標測的心房易顫性評估. 生物醫學工程學雜志, 2020, 37(3): 487-495, 501.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Machine learning models for analyzing valvular heart disease combined with atrial fibrillation using electronic health records

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content