Employing a random forest model to forecast the likelihood of coronary artery lesions in Kawasaki disease: a study centered on four biomarkers

Background:Kawasaki disease is an acute immune vasculitis,which is more common in children under 5 years old.Kawasaki disease mainly affects the cardiovascular system,especially the coronary arteries.Once coronary artery damage occurs,it can significantly impact the patient’s prognosis.Therefore,in some countries and regions,Kawasaki disease has become a common acquired heart disease.Methods:First,univariate analysis was conducted on each predictive factor.Then,Least Absolute Shrinkage and Selection Operator and random forest algorithms were used to screen all predictive factors,and the prediction model was evaluated using receiver operating characteristic curve,calibration curve,and Decision Curve Analysis.Results:This study,based on data from 228 Kawasaki disease patients,utilized a random forest model to identify four predictive factors:white blood cell count,creatine kinase isoenzyme MB,albumin,and neutrophil count.These factors were used to construct a prediction model,which achieved an area under the curve of 0.743.Conclusions:We developed a forest plot based on white blood cell count,creatine kinase isoenzyme MB,albumin,and neutrophil count to effectively predict the occurrence of coronary artery lesions in Kawasaki disease.

AST-to-ALT ratio and coronary artery lesions among patients with Kawasaki disease

Background The aim of this study was to explore the associations between the aspartate aminotransferase-to-alanine aminotransferase ratio(AST/ALT)and coronary artery lesions(CALs)among patients with Kawasaki disease(KD).Methods Medical records of KD patients presenting to a single center between January 2019 and December 2020 were retrospectively collected and analyzed.Univariate,multivariable-adjusted analyses,subgroup analyses,restricted cubic spline test,and fitted curves were used to evaluate the associations between AST/ALT and CALs.Results A total of 831 patients were enrolled,of which 201(24.2%)had CALs on admission and 21(2.5%)developed CALs de novo after intravenous immunoglobulin(IVIG).Multivariable-adjusted analyses models revealed that a lower AST/ALT was associated with an increased risk of CALs on admission when AST/ALT was a continuous variable(P=0.007)and when it was a categorical variable(P for trend=0.004).Each unit increase in AST/ALT was associated with a 22%lower risk of CALs on admission(odds ratio=0.78,95%confidence interval 0.65-0.94).A negative linear relationship was noted between AST/ALT and the risk of CALs on admission in both observed and fitted models.However,such associations were not observed in AST/ALT and CALs de novo after IVIG.None of the variables significantly modified the association between AST/ALT and CALs on admission and CALs de novo after IVIG(P>0.05).Conclusion Our findings suggested that AST/ALT was a risk factor of CALs,but was not associated with progressive CALs.

Analysis of the characteristics of coronary artery lesions in patients with obstructive sleep apnea-hypopnea syndrome and influencing factors

Objective:The current study involved an analysis of the characteristics of coronary artery lesions of patients with obstructive sleep apnea-hypopnea syndrome(OSAHS)and the correspond-ing influencing factors.Methods:One hundred twenty patients were selected by sleep apnea monitoring and coronary angiography.According to the apnea-hypopnea index(AHI),the patients were divided into the following 3 groups:patients with an AHI<10 times/h as the control group(n=25);patients with an AHI=10~15 times/h as the mild OSAHS group(n=32);and patients with an AHI>15 times/h as the moderate-to-severe OSAHS group(n=63).The clinical and laboratory test data of patients in each group were collected.A single-factor ANOVA and multi-factor logistic regression analysis were performed on the study data to analyze the coronary artery lesions in patients with OSAHS and the corresponding influencing factors.Results:(1)With respect to smoking,alcohol consumption,BMI,blood glucose,blood lipids,and blood pressure among the three groups,there were no significant differences between the three groups;however,age did differ among the three groups(P<0.05).(2)The incidence of anterior descending artery,right coronary artery,single-vessel,and coronary artery lesions as determined by coronary angiography was significantly different(P<0.05).The incidence of these vascular lesions in the moderate-to-severe group was higher than the mild group,and the incidence of coro-nary artery lesions in the moderate-to-severe group was higher(P<0.0167).(3)Based on multi-factor logistic regression analysis,alcohol consumption(OR=7.058;95%CI,1.953-25.508),age(OR=1.845;95%CI,1.121-3.038),and the AHI(OR=2.404;95%CI,1.088-5.314)were the major risk factors for coronary artery lesions.Alcohol consumption(OR=12.114;95%CI,3.058-47.979)and the AHI(OR=3.052;95%CI,1.210-7.694)were the risk factors for single-vessel disease.Age(OR=2.812;95%CI,1.236-6.400)was the major risk factor for multi-vessel disease.Conclusion:The probability of coronary artery lesions increased with OSAHS severity.The main manifestation of the increased possibility was single-vessel coronary artery lesions.In single-vessel disease,the anterior descending branch and the right coronary artery were the most vulner-able,which may be related to the anatomic distribution.Alcohol consumption,age,and AHI are the major risk factors for coronary artery lesions.Alcohol consumption and AHI are major risk factors for single-vessel disease.Age is the main risk factor for multi-vessel disease.

A Case Summary of the Application of a Drug-eluting Stent Combined with a Drug-Coated Balloon in Left Main Coronary Artery Disease

Objective:To evaluate the clinical efficacy of a drug-eluting stent(DES)combined with a drug-coated balloon(DCB)in the treatment of left main coronary artery bifurcation lesions.Methods:A retrospective analysis was conducted on the clinical data of eight patients with left main coronary artery bifurcation lesions treated with a DES combined with a DCB who were admitted to our hospital from July 2016 to July 2017.These eight patients all underwent DES treatment for their left main coronary artery and left anterior descending coronary artery lesions,and DCB treatment at the ostium of the left circumflex artery;six of the patients underwent surgical procedures under the guidance of intravascular ultrasonography.Immediate postoperative angiography was used to evaluate the patency of the diseased vessels,and the restenosis rate at the 6-month follow-up after the operation and the incidence of serious clinical events within 6 months were assessed as well.Results:The use of a DES combined with a DCB in the treatment of left main coronary artery bifurcation lesions had a low restenosis rate(left main coronary artery(8.4±5.3)%,left anterior descending coronary artery(18.2±5.0)%,left circumflex artery(30.5±16.5)%).No serious clinical events occurred in any patients.Conclusion:A DES combined with a DCB is a safe and effective interventional treatment for left main artery coro-nary bifurcation lesions.

Usefulness of uric acid for predicting rapid coronay artery lesion progression after percutaneous coronary intervention

Background Rapid progression of non-culprit coronary artery lesion happens in some patients after percutaneous coronary intervention(PCI). However,the incidence and prognostic factors for progression of coronary lesion are not clarified.Methods The patients who underwent two coronary angiography(CAG)from January2015 to January 2017 in our hospital were selected as objects of this retrospective study.According to the results of the second CAG,they were divided into control group(No restenosis in the stent,no change or improvement of out-stent lesions,n=42)and lesion progression group(Aggravation of out-stent lesions,n = 29). The clinical data of patients between the two groups were analyzed by statistics.Results The change of Lipoprotein(a)(Lp(a))and uric acid(UA)in lesion progression group were significantly different from control group(P=0.004 and P=0.037). Regression analysis showed that,the change of UA was an independent predictive factor of coronary artery lesion progression in a short time(6~12 months)after PCI(odds ratio[OR]:1.007;95%confidence interval[CI]:(1.000,1.013);P=0.042). Conclusion UA is an independent predictive factor of non-culprit coronary artery lesion after stent implanting.