AUTHOR=Naman Tuersunjiang , Abuduhalike Refukaiti , Yakufu Mubalake , Bawudun Ayixigu , Sun Juan , Mahemuti Ailiman 

TITLE=Development and validation of a predictive model of the impact of single nucleotide polymorphisms in the ICAM-1 gene on the risk of ischemic cardiomyopathy

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.977340

DOI=10.3389/fcvm.2022.977340

ISSN=2297-055X

ABSTRACT=Abstract

Object：this study was aimed to explore the correlation between polymorphism of SNPs in ICAM-1 and ICM, and to establish the diagnostic model for ICM by polymorphism of the variants of ICAM-1gene. and investigate predictive value of Polymorphism of variants in ICAM-1on the clinical outcomes patients with ICM. 
Method：252 ICM patients and 280 healthy people that had no blood connection with each other were enrolled in this study. All participants were genotyped of SNPs in ICAM-1 gene polymorphisms by polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) approach. A nomogram model using ICAM-1 genetic variation and clinical variables was established based on a developing dataset of 371 people. The least absolute shrinkage and selection operator regression model was used to optimize feature selection for the ICM risk model. Multivariate logistic regression analysis was applied to build a predicting model incorporating the feature selected in the least absolute shrinkage and selection operator regression model. Discrimination,calibration and clinical usefulness of the predicting model were assessed using the AUC value ROC, calibration plot and decision curve analysis. internal validation was assessed using the booststrapping validation. 
Result: Predictors contained in the prediction nomogram included Age, smoking, Diabetes,LDL-C, Hemoglobin, NT-pro BNP, Ejection Fraction, rs5491. Individuals with mutant AT genotype in rs5491 had a 5.816 fold higer risk of ICM compared with individuals carried AA genotype. The nomogram model had a good discrimination ability,the AUC value of ROC was 0.978(95% CI:0.967-0.989, p<0.001) in the modeling group and 0.983(95% CI:0.969-0.998, p<0.001) in the validation group respectively. And had good calibration with Hihg consiten in Hosmer-Lemeshow test(Pmedeling goup=0.937, Pvaldating goup=0.910). Decision curve analysis showed that the ICM nomogram was cilinically useful when the treshhold probabilities ranged from 0.0 to1.0. 
Conclusion: AT genotype of ICAM-1 gene rs5491 was associated with a higher risk of ICM. Individuals with mutant AT genotype had a 5.816 fold higer risk of ICM compared with individuals carried AA genotype, ICM patients with AT genotype hade higher risk of cardiogenic death. We established a novel nomogram model that can provide individualaized prediction for ICM.