Abstract
Purpose
Thrombolysis, a timely and simple reperfusion therapy, does not have a sufficiently high success rate in patients with ST-segment elevation acute myocardial infarction (STEMI). This study aimed to explore the effect of a PCSK9 inhibitor on thrombolysis success rate in patients by applying a machine learning (ML) algorithm.
Methods
In total, 531 patients with STEMI treated with thrombolytic therapy were enrolled. Four commonly used ML algorithms were selected to develop models to predict the risk of thrombolysis failure in patients with STEMI. Cluster-based undersampling (CUS) has been proposed to alleviate the effects of imbalanced data. A comprehensive evaluation revealed the optimal model for further interpretation, and the effect of the PCSK9 inhibitor on thrombolysis in patients with STEMI was analyzed by combining the SHapley Additive exPlanations (SHAP) value.
Results
CUS significantly improved model performance. The accuracy, specificity, G-mean, and area under the receiver operating characteristic curve (AUC) were greater than those of the models trained using random undersampling by 10.63%, 14.32%, 2.66%, and 2.06%, respectively. The optimal model achieved 74.81% accuracy, 73.75% sensitivity, 74.95% specificity, 73.77% G-mean, and 80.99% AUC. The feature importance of the PCSK9 inhibitor was ranked as 7/27 with a negative SHAP value, indicating that it can reduce the risk of thrombolysis failure.
Conclusion
The proposed CUS can effectively alleviate class imbalances in medical data. The combination with a PCSK9 inhibitor has the potential to reduce the risk of thrombolysis failure in patients with STEMI, which has significant clinical implications.
Similar content being viewed by others
data availability
The data that supports the findings of this study are available upon reasonable request from the corresponding author. The data are not publicly available due to privacy concerns.
References
Virani, S. S., Alonso, A., Aparicio, H. J., Benjamin, E. J., Bittencourt, M. S., Callaway, C. W., Stroke Statistics, S. (2021). Heart Disease and Stroke Statistics-2021 Update: A Report From the American Heart Association. Circulation, 143(8), 254-e743. https://doi.org/10.1161/CIR.0000000000000950
O’Gara, P. T., Kushner, F. G., Ascheim, D. D., Casey, D. E., Jr., Chung, M. K., de Lemos, J. A., American College of Cardiology Foundation, American Heart Association Task Force on Practice, G. (2013). 2013 ACCF/AHA guideline for the management of ST-elevation myocardial infarction: A report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. Circulation, 127(4), e362-425. https://doi.org/10.1161/CIR.0b013e3182742cf6
Ibanez, B., James, S., Agewall, S., Antunes, M. J., Bucciarelli-Ducci, C., Bueno, H., Group, E. S. C. S. D. (2018). ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation: The Task Force for the management of acute myocardial infarction in patients presenting with ST-segment elevation of the European Society of Cardiology (ESC). European Heart Journal, 39(2), 119–177. https://doi.org/10.1093/eurheartj/ehx393
Fazel, R., Joseph, T. I., Sankardas, M. A., Pinto, D. S., Yeh, R. W., Kumbhani, D. J., & Nallamothu, B. K. (2020). Comparison of reperfusion strategies for ST-segment-elevation myocardial infarction: A multivariate network meta-analysis. Journal of American Heart Association, 9(12), e015186. https://doi.org/10.1161/JAHA.119.015186
Gurewich, V. (2016). Thrombolysis: A critical first-line therapy with an unfulfilled potential. American Journal of Medicine, 129(6), 573–575. https://doi.org/10.1016/j.amjmed.2015.11.033
Mentias, A., & Girotra, S. (2020). Pharmaco-invasive strategy: The answer to improving ST-elevation-myocardial infarction care. Journal of American Heart Association, 9(12), e016831. https://doi.org/10.1161/JAHA.120.016831
Urban, D., Poss, J., Bohm, M., & Laufs, U. (2013). Targeting the proprotein convertase subtilisin/kexin type 9 for the treatment of dyslipidemia and atherosclerosis. Journal of the American College of Cardiology, 62(16), 1401–1408. https://doi.org/10.1016/j.jacc.2013.07.056
Glerup, S., Schulz, R., Laufs, U., & Schluter, K. D. (2017). Physiological and therapeutic regulation of PCSK9 activity in cardiovascular disease. Basic Research in Cardiology, 112(3), 32. https://doi.org/10.1007/s00395-017-0619-0
Sabatine, M. S., Giugliano, R. P., Keech, A., Honarpour, N., Wang, H., Liu, T., & Pedersen, T. R. (2016). Rationale and design of the further cardiovascular outcomes research with PCSK9 inhibition in subjects with elevated risk trial. American Heart Journal, 173, 94–101. https://doi.org/10.1016/j.ahj.2015.11.015
Barale, C., Bonomo, K., Frascaroli, C., Morotti, A., Guerrasio, A., Cavalot, F., & Russo, I. (2020). Platelet function and activation markers in primary hypercholesterolemia treated with anti-PCSK9 monoclonal antibody: A 12-month follow-up. Nutrition, Metabolism, and Cardiovascular Diseases, 30(2), 282–291. https://doi.org/10.1016/j.numecd.2019.09.012
Saha, D., & S, S., Sergeeva, E. G., Ionova, Z. I., Gorbach, A. V. (2015). Tissue factor and atherothrombosis. Current Pharmaceutical Design, 21(9), 1152–1157. https://doi.org/10.2174/1381612820666141013154946
Bandyopadhyay, D., Ashish, K., Hajra, A., Qureshi, A., & Ghosh, R. K. (2018). Cardiovascular outcomes of PCSK9 inhibitors: With special emphasis on its effect beyond LDL-cholesterol lowering. Journal of Lipids, 2018, 3179201. https://doi.org/10.1155/2018/3179201
Peczek, P., Lesniewski, M., Mazurek, T., Szarpak, L., Filipiak, K. J., & Gasecka, A. (2021). Antiplatelet effects of PCSK9 inhibitors in primary hypercholesterolemia. Life (Basel). https://doi.org/10.3390/life11060466
Qi, Z., Hu, L., Zhang, J., Yang, W., Liu, X., Jia, D., & Ge, J. (2021). PCSK9 (Proprotein convertase subtilisin/Kexin 9) enhances platelet activation, thrombosis, and myocardial infarct expansion by binding to platelet CD36. Circulation, 143(1), 45–61. https://doi.org/10.1161/CIRCULATIONAHA.120.046290
Nemati, S., Holder, A., Razmi, F., Stanley, M. D., Clifford, G. D., & Buchman, T. G. (2018). An interpretable machine learning model for accurate prediction of sepsis in the ICU. Critical Care Medicine, 46(4), 547–553. https://doi.org/10.1097/CCM.0000000000002936
Mortazavi, B. J., Downing, N. S., Bucholz, E. M., Dharmarajan, K., Manhapra, A., Li, S. X., & Krumholz, H. M. (2016). Analysis of machine learning techniques for heart failure readmissions. Circulation. Cardiovascular Quality and Outcomes, 9(6), 629–640. https://doi.org/10.1161/CIRCOUTCOMES.116.003039
Deo, R. C. (2015). Machine learning in medicine. Circulation, 132(20), 1920–1930. https://doi.org/10.1161/CIRCULATIONAHA.115.001593
Liu, Y., Zhang, Q., Zhao, G., Liu, G., & Liu, Z. (2020). Deep learning-based method of diagnosing hyperlipidemia and providing diagnostic markers automatically. Diabetes, Metabolic Syndrome and Obesity, 13, 679–691. https://doi.org/10.2147/DMSO.S242585
Commandeur, F., Slomka, P. J., Goeller, M., Chen, X., Cadet, S., Razipour, A., & Dey, D. (2020). Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: A prospective study. Cardiovascular Research, 116(14), 2216–2225. https://doi.org/10.1093/cvr/cvz321
Angraal, S., Mortazavi, B. J., Gupta, A., Khera, R., Ahmad, T., Desai, N. R., & Krumholz, H. M. (2020). Machine learning prediction of mortality and hospitalization in heart failure with preserved ejection fraction. JACC Heart Failure, 8(1), 12–21. https://doi.org/10.1016/j.jchf.2019.06.013
Zhang, Z., Ho, K. M., & Hong, Y. (2019). Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Critical Care, 23(1), 112. https://doi.org/10.1186/s13054-019-2411-z
Majhi, M. K., Pradhan, B. K., Sarkar, P., Sivaraman, J., & Pal, K. (2022). Can statistical and entropy-based features extracted from ECG signals efficiently differentiate the cannabis-consuming women population from the non-consumer? Medical Hypotheses, 167, 110952.
Stojadinovic, M., Milicevic, B., & Jankovic, S. (2023). Improved prediction of significant prostate cancer following repeated prostate biopsy by the random forest classifier. Journal of Medical and Biological Engineering, 43(1), 83–92.
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., & Lee, S. I. (2018). Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng, 2(10), 749–760. https://doi.org/10.1038/s41551-018-0304-0
Wang, K., Tian, J., Zheng, C., Yang, H., Ren, J., Liu, Y., & Zhang, Y. (2021). Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP. Computers in Biology and Medicine, 137, 4813. https://doi.org/10.1016/j.compbiomed.2021.104813
Athanasiou, M., Sfrintzeri, K., Zarkogianni, K., Thanopoulou, A. C., & Nikita, K. S. (2020). An explainable XGBoost–based approach towards assessing the risk of cardiovascular disease in patients with Type 2 Diabetes Mellitus. In 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE).
Lin, W.-C., Tsai, C.-F., Hu, Y.-H., & Jhang, J.-S. (2017). Clustering-based undersampling in class-imbalanced data. Information Sciences, 409, 17–26.
Zhao, J., Zhao, P., Li, C., & Hou, Y. (2021). Optimized machine learning models to predict in-hospital mortality for patients with ST-segment elevation myocardial infarction. Therapeutics and Clinical Risk Management, 17, 951–961. https://doi.org/10.2147/TCRM.S321799
He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284.
Mehran, R., Rao, S. V., Bhatt, D. L., Gibson, C. M., Caixeta, A., Eikelboom, J., & White, H. (2011). Standardized bleeding definitions for cardiovascular clinical trials: A consensus report from the Bleeding Academic Research Consortium. Circulation, 123(23), 2736–2747. https://doi.org/10.1161/CIRCULATIONAHA.110.009449
Tokodi, M., Schwertner, W. R., Kovacs, A., Toser, Z., Staub, L., Sarkany, A., & Kosztin, A. (2020). Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: The SEMMELWEIS-CRT score. European Heart Journal, 41(18), 1747–1756. https://doi.org/10.1093/eurheartj/ehz902
Wang, K., Tian, J., Zheng, C., Yang, H., Ren, J., Li, C., & Zhang, Y. (2021). Improving risk identification of adverse outcomes in chronic heart failure using SMOTE+ ENN and machine learning. Risk Management and Healthcare Policy, 14, 2453.
DiCiccio, T. J., & Efron, B. (1996). Bootstrap confidence intervals. Statistical Science, 11(3), 189–228.
Claridge-Chang, A., & Assam, P. N. (2016). Estimation statistics should replace significance testing. Nature Methods, 13(2), 108–109.
Bagirov, A. M., Aliguliyev, R. M., & Sultanova, N. (2023). Finding compact and well-separated clusters: Clustering using silhouette coefficients. Pattern Recognition, 135, 109144.
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., & Kim, J. (2018). Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nature biomedical engineering, 2(10), 749–760.
Štrumbelj, E., & Kononenko, I. (2014). Explaining prediction models and individual predictions with feature contributions. Knowledge and information systems, 41(3), 647–665.
Xia, W., & Feng, X.-Y. (2018). Fragmented QRS (fQRS) complex predicts adverse cardiac events of ST-segment elevation myocardial infarction patients undergoing percutaneous coronary intervention and thrombolysis. Medical Science Monitor: International Medical Journal of Experimental and Clinical Research, 24, 4634.
Bagai, A., Dangas, G. D., Stone, G. W., & Granger, C. B. (2014). Reperfusion strategies in acute coronary syndromes. Circulation Research, 114(12), 1918–1928.
Boden, W. E., Eagle, K., & Granger, C. B. (2007). Reperfusion strategies in acute ST-segment elevation myocardial infarction: A comprehensive review of contemporary management options. Journal of the American College of Cardiology, 50(10), 917–929. https://doi.org/10.1016/j.jacc.2007.04.084
D’Ascenzo, F., De Filippo, O., Gallone, G., Mittone, G., Deriu, M. A., Iannaccone, M., group, P. s. (2021). Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): A modelling study of pooled datasets. Lancet, 397(10270), 199–207. https://doi.org/10.1016/S0140-6736(20)32519-8
Yamashita, T., Wakata, Y., Nakaguma, H., Nohara, Y., Hato, S., Kawamura, S., & Soejima, H. (2022). Machine learning for classification of postoperative patient status using standardized medical data. Computer Methods in Programs and Biomedicine, 214, 6583. https://doi.org/10.1016/j.cmpb.2021.106583
Senturk, Z. K. (2020). Early diagnosis of Parkinson’s disease using machine learning algorithms. Medical Hypotheses, 138, 109603.
Gao, Y., Qiu, Y., Wu, J., Diao, W., Zhang, H., Wang, S., & Jiang, L. (2018). Acute-phase plasma PCSK9 levels and recurrent cardiovascular events in a Chinese acute myocardial infarction cohort. Cardiology, 141(2), 88–97. https://doi.org/10.1159/000493785
Li, H., Wei, Y., Yang, Z., Zhang, S., Xu, X., Shuai, M., & Li, J. (2020). Safety, tolerability, pharmacokinetics, and pharmacodynamics of alirocumab in healthy Chinese subjects: A randomized, double-blind, placebo-controlled, ascending single-dose study. American Journal of Cardiovascular Drugs, 20(5), 489–503. https://doi.org/10.1007/s40256-020-00394-1
Kosmas, C. E., Skavdis, A., Sourlas, A., Papakonstantinou, E. J., Pena Genao, E., Echavarria Uceta, R., & Guzman, E. (2020). Safety and Tolerability of PCSK9 Inhibitors: Current Insights. Clin Pharmacol, 12, 191–202. https://doi.org/10.2147/CPAA.S288831
Acknowledgements
This study was funded by the Tianjin Key Research Program of Traditional Chinese Medicine (2022001), the Tianjin Research Innovation Project for Postgraduate Students (2022BKY105), National Natural Science Foundation of China (62206197), and Applied and Basic Research by Multi-input Foundation of Tianjin (21JCYBJC00820). We would like to thank Editage (www.editage.cn) for English language editing.
Author information
Authors and Affiliations
Contributions
All authors contributed to the conception and design of this study. Material preparation, data collection, and analyses were performed by PZ, JZ, and YH. The first draft of the manuscript was written by PZ, and all authors commented on the following versions of the manuscript. All authors have read and approved the final version of the manuscript.
Corresponding authors
Ethics declarations
Competing Interests
The authors have no relevant financial or non-financial interests to disclose.
Ethical Approval
This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the medical ethics committee of Tianjin Chest Hospital (approval number: 2020KY-007-01).
Consent to Participate
This was a retrospective study that used previous clinical treatment records, without using biological samples, without direct contact with patients, and without involving the personal privacy of patients. Therefore, this study was exempted from informed consent by the Medical Ethics Committee of Tianjin Chest Hospital.
Consent to Publish
This study does not contain any individual personal data in any form.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, P., Zhou, J., Liu, C. et al. An Explainable Machine-Learning Model to Analyze the Effects of a PCSK9 Inhibitor on Thrombolysis in STEMI Patients. J. Med. Biol. Eng. 43, 339–349 (2023). https://doi.org/10.1007/s40846-023-00796-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40846-023-00796-x