Phenotyping of risk factors and prediction of inhospital mortality in patients with coronary artery disease after coronary artery bypass grafting based on explainable artificial intelligence methods

Aim. To develop predictive models of inhospital mortality (IHM) in patients with coronary artery disease after coronary artery bypass grafting (CABG), taking into account the results of phenotyping of preoperative risk factors.

Material and methods. This retrospective study was conducted based on the data of 999 electronic health records of patients (805 men, 194 women) aged 35 to 81 years with a median (Me) of 63 years who underwent on-pump elective isolated CABG. Two groups of patients were distinguished, the first of which was represented by 63 (6,3%) patients who died in the hospital during the first 30 days after CABG, the second — 936 (93,7%) with a favorable outcome. Preoperative clinical and functional status was assessed using 102 factors. Chi-squares, Fisher, Mann-Whitney methods were used for data processing and analysis. Threshold values of predictors were determined by methods, including maximizing the ratio of true positive IHM cases to false positive ones. Multivariate logistic regression (MLR) was used to develop predictive models. Model accuracy was assessed using 3 following metrics: area under the ROC curve (AUC), sensitivity (Sens), and specificity (Spec).

Results. An analysis of preoperative status of patients made it possible to identify 28 risk factors for IHM, combined into 7 phenotypes. The latter formed the feature space of IHM prognostic model, in which each feature demonstrates the patient’s compliance with a certain risk factor phenotype. The author’s MLR model had high quality metrics (AUC-0,91; Sen-0,9 and Spec-0,85).

Conclusion. The developed data processing and analysis algorithm ensured high quality of preoperative risk factors identification and IHM prediction after CABG. Prospects for further research on this issue are related to the improvement of explainable artificial intelligence technologies, which allow developing infor­mation systems for managing clinical practice risks.

1. Squiers JJ, Schaffer JM, Banwait JK, et al. Long-Term Survival After On-Pump and Off-Pump Coronary Artery Bypass Grafting. Ann Thorac Surg. 2022;113(6):1943-52. doi:10.1016/j.athoracsur.2021.07.037.

2. Nashef SA, Roques F, Sharples LD, et al. EuroSCORE II. European journal of cardiothoracic surgery: official journal of the European Association for Cardio-thoracic Surgery. 2012;41(4):734-45. doi:10.1093/ejcts/ezs043.

3. Vassileva CM, Aranki S, Brennan JM, et al. Evaluation of The Society of Thoracic Surgeons Online Risk Calculator for Assessment of Risk inук Patients Presenting for Aortic Valve Replacement After Prior Coronary Artery Bypass Graft: An Analysis Using the STS Adult Cardiac Surgery Database. The Annals of thoracic surgery. 2015;100(6):2109-16. doi:10.1016/j.athoracsur.2015.04.149.

4. 2018 ESC/EACTS guidelines on myocardial revascularization. Russian Journal of Cardiology. 2019;(8):151-226. (In Russ.) doi:10.15829/1560-4071-2019-8-151-226.

5. Valente F, Henriques J, Paredes S, et al. A new approach for interpretability and reliability in clinical risk prediction: Acute coronary syndrome scenario. Artificial intelligence in medicine. 2021;117:102-13. doi:10.1016/j.artmed.2021.102113.

6. Geltser BI, Shahgeldyan KJ, Rublev VY, et al. Machine Learning Methods for Prediction of Hospital Mortality in Patients with Coronary Heart Disease after Coronary Artery Bypass Grafting. Kardiologiia. 2020;60(10):38-46. (In Russ.) doi:10.18087/cardio.2020.10.n1170.

7. Johnson KW, Torres SJ, Glicksberg BS, et al. Artificial Intelligence in Cardiology. Journal of the American College of Cardiology. 2018;71(23):2668-79. doi:10.1016/j.jacc.2018.03.521.

8. Galderisi M, Cosyns B, Edvardsen T, et al. Standardization of adult transthoracic echocardiography reporting in agreement with recent chamber quantification, diastolic function, and heart valve disease recommendations: an expert consensus document of the European Association of Cardiovascular Imaging. Eur Heart J Cardiovasc Imaging. 2017;18(12):1301-10. doi:10.1093/ehjci/jex244.

9. Molnar C. Interpretable Machine Learning. A Guide for Making Black Box Models Explainable. 2022. 328 р. ISBN-13: 979-8411463330. Available at: https://christophm.github.io/interpretable-ml-book/.

10. Shakhgeldyan KI, Rublev VY, Geltser BI, et al. Predictive potential assessment of preoperative risk factors for atrial fibrillation in patients with coronary artery disease after coronary artery bypass grafting. The Siberian Journal of Clinical and Experimental Medicine. 2020;35(4):128-36. (In Russ.) doi:10.29001/2073-8552-2020-35-4-128-136.

11. Geltser BI, Rublev VYu, Tsivanyuk MM, Shakhgeldyan KI. Machine learning in predicting immediate and long-term outcomes of myocardial revascularization: a systematic review. Russian Journal of Cardiology. 2021;26(8):4505. (In Russ.) doi:10.15829/15604071-2021-4505.

12. Geltser BI, Shakhgeldyan KI, Rublev VYu, et al. Algorithm for selecting predictors and prognosis of atrial fibrillation in patients with coronary artery disease after coronary artery bypass grafting. Russian Journal of Cardiology. 2021;26(7):4522. (In Russ.) doi:10.15829/1560-4071-2021-4522.

13. Shakhgeldyan K, Geltser B, Rublev V, et al. Feature Selection Strategy for Intrahospital Mortality Prediction after Coronary Artery Bypass Graft Surgery on an Unbalanced Sample. Proceedings of the 4th International Conference on Computer Science and Application Engineering. 2020;1-7. doi:10.1145/3424978.3425090.

14. Jo YY, Cho Y, Lee SY, et al. Explainable artificial intelligence to detect atrial fibrillation using electrocardiogram. International journal of cardiology. 2021;328:104-10. doi:10.1016/j.ijcard.2020.11.053.

15. Taniguchi H, Takata T, Takechi M, et al. Explainable Artificial Intelligence Model for Diagnosis of Atrial Fibrillation Using Holter Electrocardiogram Waveforms. International heart journal. 2021;62(3):534-9. doi:10.1536/ihj.21-094.