Risk factors associated with major adverse cardiac and cerebrovascular events following percutaneous coronary intervention: a 10-year follow-up comparing random survival forest and Cox proportional-hazards model
Tóm tắt
Due to the limited number of studies with long term follow-up of patients undergoing Percutaneous Coronary Intervention (PCI), we investigated the occurrence of Major Adverse Cardiac and Cerebrovascular Events (MACCE) during 10 years of follow-up after coronary angioplasty using Random Survival Forest (RSF) and Cox proportional hazards models. The current retrospective cohort study was performed on 220 patients (69 women and 151 men) undergoing coronary angioplasty from March 2009 to March 2012 in Farchshian Medical Center in Hamadan city, Iran. Survival time (month) as the response variable was considered from the date of angioplasty to the main endpoint or the end of the follow-up period (September 2019). To identify the factors influencing the occurrence of MACCE, the performance of Cox and RSF models were investigated in terms of C index, Integrated Brier Score (IBS) and prediction error criteria. Ninety-six patients (43.7%) experienced MACCE by the end of the follow-up period, and the median survival time was estimated to be 98 months. Survival decreased from 99% during the first year to 39% at 10 years' follow-up. By applying the Cox model, the predictors were identified as follows: age (HR = 1.03, 95% CI 1.01–1.05), diabetes (HR = 2.17, 95% CI 1.29–3.66), smoking (HR = 2.41, 95% CI 1.46–3.98), and stent length (HR = 1.74, 95% CI 1.11–2.75). The predictive performance was slightly better by the RSF model (IBS of 0.124 vs. 0.135, C index of 0.648 vs. 0.626 and out-of-bag error rate of 0.352 vs. 0.374 for RSF). In addition to age, diabetes, smoking, and stent length, RSF also included coronary artery disease (acute or chronic) and hyperlipidemia as the most important variables. Machine-learning prediction models such as RSF showed better performance than the Cox proportional hazards model for the prediction of MACCE during long-term follow-up after PCI.
Tài liệu tham khảo
Kim AS, Johnston SC. Global variation in the relative burden of stroke and ischemic heart disease. Circulation. 2011;124(3):314–23. https://doi.org/10.1161/CIRCULATIONAHA.111.018820.
Athappan G, Ponniah T. Clinical outcomes of dialysis patients after implantation of DES: meta-analysis and systematic review of literature. Miner Cardioangiol. 2009;57(3):291–7.
Jukema JW, Verschuren JJ, Ahmed TA, Quax PH. Restenosis after PCI. Part 1: pathophysiology and risk factors. Nat Rev Cardiol. 2011;9(1):53–62. https://doi.org/10.1038/nrcardio.2011.132.
Kim MS, Dean LS. In-stent restenosis. Cardiovasc Ther. 2011;29(3):190–8. https://doi.org/10.1111/j.1755-5922.2010.00155.X.
Ashrith G, Elayda MA, Wilson JM. Revascularization options in patients with chronic kidney disease. Tex Heart Inst J. 2010;37(1):9–18.
Kleinbaum DG. Survival analysis, a self-learning text. Biometrical J. 1998;40:107–8.
Cox D. Regression models and life-tables. J R Stat Soc. 1972;34:187–220.
Breiman L. Random forests. Mach Learn. 2001;45:5–32.
Meng J, Li P, Zhang Q, Yang Z, Fu S. A four-long noncoding RNA signature in predicting breast cancer survival. J Exp Clin Cancer Res. 2014;33:84.
Noori S, Nourijelyani K, Mohammad K, Niknam M, Mahmoudi M, Andonian L, et al. Random forests analysis: a modern statistical method for screening in high-dimensional studies and its application in a population-based genetic association study. J North Khorasan Univ Med Sci. 2012;3:93–101 ((in Persian)).
Kawaguchi A, Yajima N, Tsuchiya N, Homma J, Sano M, Natsumeda M, et al. Gene expression signature-based prognostic risk score in patients with glioblastoma. Cancer Sci. 2013;104:1205–10.
Miao F, Cai YP, Zhang YT, Li CY. Is random survival forest an alternative to Cox proportional model on predicting cardiovascular disease? In 6th European conference of the international federation for medical and biological engineering; 2015. Springer.
Trikalinos TA, Alsheikh-Ali AA, Tatsioni A, Nallamothu BK, Kent DM. Percutaneous coronary interventions for non-acute coronary artery disease: a quantitative 20-year synopsis and a network meta-analysis. Lancet. 2009;373(9667):911–8.
Shwaran H, Kogalur UB. Random survival forests for R. R News. 2007;7:25–31.
Brier GW. Verification of forecasts expressed in terms of probability. Month Weather Rev. 1950;78:1–3.
Aghajani H, Nezami P, Shafiee A, Jalali A, Nezami A, Nozari Y, Pourhosseini H, et al. Predictors of long-term major adverse cardiac events following percutaneous coronary intervention in the elderly. Arch Iran Med. 2018;21(8):344–8.
Zhou Y, Zhu R, Chen X, Xu X, Wang Q, Jiang L, et al. Machine learning-based cardiovascular event prediction for percutaneous coronary. JACC Cardiovasc Interv. 2019. https://doi.org/10.1016/S0735-1097(19)30735-1.
Meliga E, Garcia-Garcia HM, Valgimigli M, Biondi-Zoccai G, O.Maree A. Longest available clinical outcomes after drug-eluting stent implantation for unprotected left main coronary artery disease: the DELFT (drug eluting stent for LeFT main) registry. JACC Cardiovasc Interv. 2008;51(23):2212–9.
Ebrahimzadeh F, Salehi Veisi M, Hajizadeh E, Namdari M. Prediction of coronary artery restenosis in patients undergoing angioplasty. J Babol Univ Med Sci. 2018;20(5):30–7.
Ebrahimzadeh F, Hajizadeh E, Baghestani A, Nasseryan J. Timing the incidence of restenosis and some effective factors in patients undergoing angioplasty using extended cox regression model. J Mazandaran Univ Med Sci. 2017;26(146):56–67 ((in Persian)).
Farshidi H, Abdi A, Madani A, Moshiri Sh, Ghasemi A, Hakimian R. Major adverse cardiovascular event (MACE) after percutaneous coronary intervention in one-year follow-up study. Electron Phys. 2018;10(2):6383–9. https://doi.org/10.19082/6383.
Tsai IT, Wang CP, Lu YC, Hung YC, Wu CC, Lu LF, et al. The burden of major adverse cardiac events in patients with coronary artery disease. BMC Cardiovasc Disord. 2017;17:1. https://doi.org/10.1186/s12872-016-0436-7.
Horst B, Rihal CS, Holmes DR, Bresnahan JF, Prasad A, Gau G, et al. Drug-eluting or bare-metal stents for coronary artery disease. N Engl J Med. 2016;375:1242–52. https://doi.org/10.1016/j.jcin.2008.11.010.
De Felice F, Fiorilli R, Parma A, Nazzaro M, Musto C, Sbraga F, et al. 3-year clinical outcome of patients with chronic total occlusion treated with drug-eluting stents. JACC Cardiovasc Interv. 2009;2(12):1260–5. https://doi.org/10.1016/j.jcin.2009.09.013.
Cai A, Dillon Ch, Hillegass WB, Beasley M, Brott BC, Bittner VA, et al. Risk of major adverse cardiovascular events and major hemorrhage among white and black patients undergoing percutaneous coronary intervention. J Am Heart Assoc. 2019;8:e012874. https://doi.org/10.1161/JAHA.119.012874.
Duggal B, Subramanian J, Duggal M, Singh P, Rajivlochan M, Saunik S, et al. Survival outcomes post percutaneous coronary intervention: why the hype about stent type? Lessons from a healthcare system in India. PLoS ONE. 2018. https://doi.org/10.1371/journal.pone.0196830.
Diéguez AR, Cid Álvarez AB, Nouche RT, Ávila Carrillo A, Álvarez Álvarez B, Gómez Peña F, et al. Drug-eluting versus bare-metal stents in primary PCI. Analysis of an 8-year registry. REC Interv Cardiol. 2019. https://doi.org/10.24875/RECICE.M19000008.
Melberg T, Kjell Nygard O, Kier-Jan Kuiper K, Nordrehaug JE. Competing risk analysis of events 10 years after revascularization. Scand Cardiovasc J. 2010;44:279–88. https://doi.org/10.3109/14017431003698531.