Construction and verification of risk prediction model for acute myocardial infarction with heart failure

doi:10.11958/20230055

Abstract

Abstract:

Objective To analyze the factors affecting of heart failure (HF) in patients with acute myocardial infarction (AMI), and use the selected indicators to construct a risk prediction model. Methods A total of 1 061 AMI patients were included, and they were divided into the model-constructed training set (786 cases) and the test set (275 cases). Lasso regression and multiple Logistic regression were used to build a predictive model for HF occurrence in AMI patients, and a Nomogram diagram was drawn. Receiver operating characteristic (ROC) curve and calibration curve were used to evaluate the discrimination and calibration of the model. Results Lasso regression and multiple Logistic regression were used to select 7 variables to establish the model, including age, heart rate (HR), ST segment deviation, N-telencephalic natriuretic peptide precursor (NT-proBNP), homocysteine (Hcy), fibrinogen (Fib) and left ventricular ejection fraction (LVEF). The regression equation for constructing predictive model by multivariate Logistic regression was Logit (P) =0.718×ST segment deviation+0.042×age+0.037×HR+0.000 294×NT-proBNP+0.040×Hcy+0.220×Fib-5.617×LVEF-5.781. The area under ROC curve of the training set was 0.846 (95%CI: 0.817-0.875), the sensitivity was 78.50% and the specificity was 76.60%. The calibration curve showed that the incidence of HF in the training set was basically consistent with the actual incidence. The test set was used to verify the model externally. The area under ROC curve was 0.848 (95%CI: 0.801-0.896), the sensitivity was 76.40% and the specificity was 78.00%. Conclusion The occurrence of HF in AMI patients is related to ST segment deviation, age, HR, NT-proBNP, Hcy, Fib and LVEF. The predictive model based on the above variables has high predictive efficacy and is helpful for early identification of such patients.

Key words: myocardial infarction, heart failure, risk factors, predict, nomograms, sensitivity and specificity

CLC Number:

R541

Figures/Tables 7

Tab.1 Comparison of clinical data between the HF group and the non-HF group

Fig.1 Lasso regression analysis of HF in AMI patients

Tab.2 Multivariate Logistic regression analysis for the occurrence of HF in AMI patients

变量	β	SE	Wald χ²	P	OR（95%CI）
ST段偏移	0.718	0.230	9.780	0.002	2.050（1.307~3.215）
年龄	0.042	0.009	23.471	<0.001	1.043（1.025~1.060）
HR	0.037	0.007	31.381	<0.001	1.038（1.025~1.052）
NT-proBNP	0.000 294	0.000 05	37.005	<0.001	1.000 3（1.000 2~1.000 4）
Hcy	0.040	0.010	15.208	<0.001	1.041（1.020~1.063）
Fib	0.220	0.103	4.561	0.033	1.247（1.018~1.526）
LVEF	-5.617	1.062	27.973	<0.001	0.004（0.000 5~0.029）
常数	-5.781	1.045	30.610	<0.001

Fig.2 Nomogram of prediction model for HF in AMI patients

Fig.3 ROC curve of prediction model for HF in AMI patients

Fig.4 Calibration curve of prediction model for HF in AMI patients

Fig.5 ROC curve of HF in AMI patients in the test set

References 21

[1]	BAHIT M C, KOCHAR A, GRANGER C B. Post-myocardial infarction heart failure[J]. JACC Heart Fail, 2018, 6(3):179-186. doi:10.1016/j.jchf.2017.09.015.
[2]	SULO G, IGLAND J, VOLLSET S E, et al. Heart failure complicating acute myocardial infarction;burden and timing of occurrence:A nation-wide analysis including 86 771 patients from the cardiovascular disease in Norway (CVDNOR)project[J]. J Am Heart Assoc, 2016, 5:e002667. doi:10.1161/JAHA.115.002667.
[3]	王婧, 全济坤, 刘小玉, 等. 心力衰竭生物标志物的研究进展[J]. 中西医结合心脑血管病杂志, 2022, 20(16):2956-2957.
	WANG J, QUAN J K, LIU X Y, et al. Research progress of biomarkers in heart failure[J]. Chinese Journal of Integrative Medicine on Cardio/Cerebrovascular Disease, 2022, 20(16):2956-2957. doi:10.12102/ji.ssn.1672-1349.2022.16.014.
[4]	高润霖. 急性心肌梗死诊断和治疗指南[J]. 中华心血管病杂志, 2001, 29(12):710-725.
	GAO R L. Guidelines for diagnosis and treatment of acute myocardial infarction[J]. Chin J Cardiol, 2001, 29(12):710-725.
[5]	中国医疗保健国际交流促进会急诊医学分会, 中华医学会急诊医学分会, 中国医师协会急诊医师分会, 等. 急性心力衰竭中国急诊管理指南(2022)[J]. 中国急救医学, 2022, 42(8):648-670.
	Emergency branch of China international erchange and promotive association for medical and healthcare,Chinese society of emergency medicine, Chinese association of emergency physicians, et al. Guideline for emergency management of acute heart failure in China(2022)[J]. Chin J Crit Care Med, 2022, 42(8):648-670. doi:10.3969/j.issn.1002-1949.2022.08.002.
[6]	中国医师协会心血管内科医师分会, 中国心血管健康联盟, 心肌梗死后心力衰竭防治专家共识工作组. 2020心肌梗死后心力衰竭防治专家共识[J]. 中国循环杂志, 2020, 35(12):1166-1180.
	Branch of Cardiovascular Physicians,Chinese Medical Doctor Association, China Cardiovascular Health Alliance, The Expert Consensus Working Group on the Prevention and Treatment of Heart Failure After Myocardial Infarction. 2020 expert consensus on the prevention and treatment of heart failure after myocardial infarction[J]. Chinese Circulation Journal, 2020, 35(12):1166-1180. doi:10.3969/j.issn.1000-3614.2020.12.002.
[7]	杨艳敏, 朱俊, 谭慧琼, 等. 中国ST段抬高的急性心肌梗死临床特征及治疗现状[J]. 中华医学杂志, 2005, 85(31):2176-2182.
	YANG Y M, ZHU J, TAN H Q, et al. Clinical characteristics and management of patients with ST segment elevation myocardial infarction in China: survey of 7510 cases[J]. Natl Med J China, 2005, 85(31):2176-2182.
[8]	JENČA D, MELEMOVSKY V, STEHLIK J, et al. Heart failure after myocardial infarction:incidence and predictors[J]. ESC Heart Fail, 2021, 8(1):222-237. doi:10.1002/ehf2.13144.
[9]	LI C, ZHANG Q, FENG D, et al. First post-discharge heart rate and long-term prognosis in patients with acute myocardial infarction[J]. Rev Cardiovasc Med, 2022, 23(1):24. doi:10.31083/j.rcm2301024.
[10]	BAJIC Z, SOBOT T, SKRBIC R, et al. Homocysteine,vitamins B6 and folic acid in experimental models of myocardial infarction and heart failure-how strong is that link?[J]. Biomolecules, 2022, 12:536. doi:10.3390/biom12040536.
[11]	MEYER M R, RADOVANOVIC D, PEDRAZZINI G, et al. Differences in presentation and clinical outcomes between left or right bundle branch block and ST segment elevation in patients with acute myocardial infarction[J]. Eur Heart J Acute Cardiovasc Care, 2020, 9(8):848-856. doi:10.1177/2048872620905101.
[12]	AWAN M S, DAUD M Y, KHAN M, et al. Association of degree of ST segment depression with inhospital mortality in patients with non-ST elevation myocardial infarction[J]. J Ayub Med Coll Abbottabad, 2019, 31(1):36-38.
[13]	NOMAN A, BALASUBRAMANIAM K, DAS R, et al. Admission heart rate predicts mortality following primary percutaneous coronary intervention for ST-elevation myocardial infarction:an observational study[J]. Cardiovasc Ther, 2013, 31(6):363-369. doi:10.1111/1755-5922.12031.
[14]	CAO Z, JIA Y, ZHU B. BNP and NT-proBNP as diagnostic biomarkers for cardiac dysfunction in both clinical and forensic medicine[J]. Int J Mol Sci, 2019, 20:1820. doi:10.3390/ijms20081820.
[15]	KIM S E, CHO D H, SON J W, et al. Impact of NT-proBNP on prognosis of acute decompensated chronic heart failure versus de novo heart failure[J]. Int J Cardiol, 2022, 363:163-170. doi:10.1016/j.ijcard.2022.06.055.
[16]	JIN N, HUANG L, HONG J, et al. Elevated homocysteine levels in patients with heart failure:a systematic review and meta-analysis[J]. Medicine(Baltimore), 2021, 100(33):e26875. doi:10.1097/MD.0000000000026875.
[17]	SI J, LI X W, WANG Y, et al. Relationship between serum homocysteine levels and long-term outcomes in patients with ST-segment elevation myocardial infarction[J]. Chin Med J(Engl), 2019, 132(9):1028-1036. doi:10.1097/CM9.0000000000000159.
[18]	PIETERS M, FERREIRA M, DE MAAT D M P M, et al. Biomarker association with cardiovascular disease and mortality-the role of fibrinogen. A report from the NHANES study[J]. Thromb Res, 2021, 198:182-189. doi:10.1016/j.thromres.2020.12.009.
[19]	JIANG P, GAO Z, ZHAO W, et al. Relationship between fibrinogen levels and cardiovascular events in patients receiving percutaneous coronary intervention: a large single-center study[J]. Chin Med J, 2019, 132(8):914-921. doi:10.1097/CM9.0000000000000181.
[20]	HALL T S, VON LUEDER T G, ZANNAD F, et al. Relationship between left ventricular ejection fraction and mortality after myocardial infarction complicated by heart failure or left ventricular dysfunction[J]. Int J Cardiol, 2018, 272:260-266. doi:10.1016/j.ijcard.2018.07.137.
[21]	刘畅. GWTG-HF风险评分对心脏重症监护病房患者全因死亡的预测价值[D]. 杭州: 浙江大学, 2021.
	LIU C. Predictive value of GWTG-HF risk score for all-cause mortality in cardiac intensive care unit patients[D]. Hanzghou: Zhejiang University, 2021.