Prediction of Major Adverse Cardiac Events After Transcatheter Aortic Valve Implantation: A Machine Learning Approach with GRACE Score.

Objectives: Predictive risk scores have a significant impact on patient selection and assessing the likelihood of complications following interventions in patients with severe aortic stenosis (AS). This study aims to explore the utility of machine learning (ML) techniques in predicting 30-day major adverse cardiac events (MACE) by analyzing parameters, including the Global Registry of Acute Coronary Events (GRACE) score. Methods: This retrospective, multi-center, observational study enrolled 453 consecutive patients diagnosed with severe AS who underwent transcatheter aortic valve implantation (TAVI) from April 2020 to January 2023. The primary outcome was defined as a composition of MACE comprising periprocedural myocardial infarction (MI), cerebrovascular events (CVE), and all-cause mortality during the 1-month follow-up period after the procedure. Conventional binomial logistic regression and ML models were utilized and compared for prediction purposes. Results: The study population had a mean age of 76.1, with 40.8% being male. The primary endpoint was observed in 7.5% of cases. Among the individual components of the primary endpoint, the rates of all-cause mortality, MI, and CVE were reported as 4.2%, 2.4%, and 1.9%, respectively. The ML-based Extreme Gradient Boosting (XGBoost) model with the GRACE score demonstrated superior discriminative performance in predicting the primary endpoint, compared to both the ML model without the GRACE score and the conventional regression model [Area Under the Curve (AUC)= 0.98 (0.91-0.99), AUC= 0,87 (0.80-0.98), AUC= 0.84 (0.79-0.96)]. Conclusion: ML techniques hold the potential to enhance outcomes in clinical practice, especially when utilized alongside established clinical tools such as the GRACE score.

Body fat percentage and infarct size in patients with non-ST segment elevation myocardial infarction.

OBJECTIVE: Obesity is a global health problem that increases the risk of coronary artery disease (CAD). However in studies, it has been observed that when the disease develops, obese patients have a more favorable prognosis than leaner patients. This is called the "obesity paradox." This study aims to evaluate the effect of obesity assessed with body fat percentage (BFP) and relative fat mass (RFM) besides body mass index (BMI) on infarct size (IS) estimated from peak creatine kinase-MB (CK-MB) levels in patients with non-ST-segment elevation myocardial infarction (NSTEMI). METHODS: Patients with a diagnosis of NSTEMI who underwent coronary angiography between January 2017 and January 2022 were retrospectively evaluated. Patients without available anthropometric data to calculate BMI, BFP, and RFM and serial CK-MB measurements were excluded from the study. BMI was calculated using weight(kg)/(height[m])2 formula. Patients were dichotomized as obese (BMI≥30 kg/m2) and non-obese (BMI<30 kg/m2) to compare baseline characteristics. BFP and RFM were calculated from anthropometric data. Linear regression analysis was performed to define predictors of IS. RESULTS: Final study population consisted of 748 NSTEMI patients (mean age was 59.3±11.2 years, 76.3% were men, 36.1% of the patients were obese). Obese patients were more likely to be female, hypertensive, and diabetic. Smoking was less frequently observed in obese patients. Peak CK-MB levels were similar among groups. Obese patients had higher in-hospital left ventricular ejection fraction, and less severe CAD was observed in coronary angiographies of these patients. Multivariable regression analysis identified diabetes mellitus, systolic blood pressure, white blood cell count, hemoglobin, and BFP (ß=-4.8, 95% CI=-8.7; -0.3, p=0.03) as independent predictors of IS. CONCLUSION: Higher BFP is associated with smaller IS in NSTEMI patients. These findings support the obesity paradox in this patient group, but further, randomized controlled studies are required.

The prognostic impact of inflammation in patients with decompensated acute heart failure, as assessed using the pan-immune inflammation value (PIV).

There is increasing evidence that composite scores based on blood counts, which are reflectors of uncontrolled inflammation in the development and progression of heart failure, can be used as prognostic biomarkers in heart failure patients. The prognostic effects of pan-immune inflammation (PIV) as an independent predictor of in-hospital mortality in patients with acute heart failure (AHF) were evaluated based on this evidence. The data of 640 consecutive patients hospitalized for New York Heart Association (NYHA) class 2-3-4 AHF with reduced ejection fraction were analyzed and 565 patients were included after exclusion. The primary outcome was in hospital all-cause death. Secondary outcomes were defined as the following in-hospital events: Acute kidney injury (AKI), malignant arrhythmias, acute renal failure (ARF) and stroke. The PIV was computed using hemogram parameters such as lymphocytes, neutrophils, monocytes and platelets. Patients were categorized as low or high PIV group according to the median value, which was 382.8. A total of 81 (14.3%) in-hospital deaths, 31 (5.4%) AKI, 34 (6%) malignant arrhythmias, 60 (10.6%) ARF and 11 (2%) strokes were reported. Patients with high PIV had a higher in-hospital mortality rate than patients with low PIV (OR: 1.51, 95% CI, 1.26-1.80, p < 0.001). Incorporating PIV into the full model significantly improved model performance (odds ratio X2, p < 0.001) compared to the baseline model constructed with other inflammatory markers. PIV is a potent predictor of prognosis with better performance than other well-known inflammatory markers for patients with AHF.

Impact of Naples Prognostic Score on midterm all-cause mortality in patients with decompensated heart failure.

Aim: This work was designed to investigate the relationship between cardiac outcomes and Naples Prognostic Score (NPS) among heart failure (HF) patients. Materials & methods: This retrospective observational study enrolled 298 consecutive individuals hospitalized for New York Heart Association class 3-4 HF. The primary outcome was all-cause mortality. Secondary outcomes were rehospitalization and in-hospital death. Results: The high NPS group had a statistically greater rate of all-cause mortality (p < 0.001). In Cox regression analysis, integrating NPS considerably improved the performance of the full model over the baseline model (adjusted hazard ratio = 2.28; p = 0.004). Based on time-dependent receiver operating characteristic curve analysis, the NPS model outperformed the baseline and CONUT score models in discriminatory power in predicting the probability of survival. Conclusion: NPS was associated with short- and midterm mortality as well as rehospitalization.

Heart failure is a serious condition that affects millions of individuals around the world. This study was designed to investigate whether there is a relationship between Naples Prognostic Score (NPS) and worse outcomes in heart failure patients. A total of 298 patients with advanced heart failure were included in the study. Patients with a high NPS are more likely to pass away and need to be readmitted to the hospital. NPS also predicted survival more accurately than some other variables at an average of 15 months follow-up. In conclusion, NPS was found to be useful in predicting short- and medium-term mortality and readmissions in patients with advanced heart failure.

Post percutaneous coronary intervention hemoglobin levels predict in-hospital mortality in patients with STEMI treated with primary percutaneous coronary intervention.

OBJECTIVE: In this study, we aimed to determine whether admission hemoglobin versus post-percutaneous coronary intervention (PCI) hemoglobin level at 24 hours is a predictor of in-hospital mortality for patients with ST elevation myocardial infarction (STEMI) without evidence of clinical hemorrhage who underwent primary PCI. METHODS: In this study, we included 1,444 consecutive patients with STEMI who underwent primary PCI at a tertiary heart hospital. The primary outcome of the study was the in-hospital all-cause mortality. We used the penalized maximum likelihood estimation (PMLE) logistic regression method to examine the relationship between primary outcome and candidate predictors. RESULTS: In total, 172 (11.9%) patients died during the in-hospital course. According to a PMLE logistic regression analysis, age, KILLIP class ≥2, pre-PCI thrombolysis in myocardial infarction (TIMI) flow <3, systolic blood pressure, creatinine, glycoprotein IIb/IIIa inhibitor use, and post-PCI hemoglobin levels at 24 hours were predictors of in-hospital mortality. The relative importance of post-PCI hemoglobin at 24 hours (contributing 6% of the explainable outcome in the model) was significantly higher than admission hemoglobin (contributing only 0.1% of the explainable outcome in the model). CONCLUSION: This study demonstrated that post-PCI hemoglobin levels were independently associated with in-hospital survival in patients with STEMI without evidence of bleeding following primary PCI. In addition, post-PCI hemoglobin was a better predictor of in-hospital mortality than admission hemoglobin for patients with STEMI who underwent primary PCI.

The association of preprocedural C-reactive protein/albumin ratio with in-stent restenosis in patients undergoing iliac artery stenting.

Introduction: In-stent restenosis (ISR) still constitutes a major problem after percutaneous vascular interventions and the inflammation has a pivotal role in the pathogenesis of such event. The C-reactive protein/albumin ratio (CAR) is a newly identified inflammatory biomarker, and it may be used as an indicator to predict ISR in subjects with coronary artery stenting. In light of these data, our main objective was to investigate the relationship between the preprocedural CAR and ISR in patients undergoing successful iliac artery stent implantation. Methods: In total, 138 consecutive patients who had successful iliac artery stent implantation in a tertiary heart center between 2015 and 2018 were enrolled in the study. The study population was categorized into two groups; patients with ISR and those without ISR during follow-up. The CAR was determined by dividing CRP by serum albumin. Results: In the multivariable regression analysis; the CAR (HR: 2.66, 95% CI: 1.66-4.25, P < 0.01), stent length (HR: 1.01, 95% CI: 0.99-1.02, P = 0.04), and HbA1c levels (HR: 1.22, 95% CI: 0.99-1.51, P = 0.04) were independently related with ISR. A receiver operating curve analysis displayed that the CAR value of >0.29 predicted ISR with sensitivity of 97.5% and specificity of 88.8% (AUC 0.94, P < 0.01). Conclusion: Our findings provide evidence that the CAR may be an applicable inflammatory biomarker in predicting ISR in subjects undergoing iliac artery stenting for the treatment of peripheral artery disease (PAD). Also, the stent length and poor glycemic control were found to be associated with ISR.

Interatrial block as a predictor of atrial fibrillation in patients with ST-segment elevation myocardial infarction.

INTRODUCTION: Interatrial block (IAB) is strongly associated with recurrence of atrial fibrillation (AF) in different clinical scenarios. Atrial fibrosis is considered the responsible mechanism underlying the pathogenesis of IAB. The aim of this study was to investigate whether IAB predicted AF at 12 months follow-up in a population of patients with ST segment elevation myocardial infarction (STEMI). HYPOTHESIS: We aimed to investigate whether IAB predicted AF at 12 months follow up in a population of patients with STEMI. METHODS: Prospective, single center, observational study of patients presenting with ST-segment elevation myocardial infarction (STEMI) and referred to primary percutaneous coronary intervention (P-PCI). Surface electrocardiograms (ECG) were recorded on admission and at 6th hour post P-PCI. Patients were screened for the occurrence of AF at a 12-months visit. RESULTS: A total of 198 patients were included between September 2015 and September 2016. IAB (partial and advanced) was detected in 102 (51.5%) patients on admission. Remodeling of the P-wave and subsequent normalization reduced the prevalence of IAB to 47 (23.7%) patients at 6th hour. AF was detected in 17.7% of study patients at 12 months. Partial IAB (p-IAB) on admission (OR 5.10; 95% CI, 1.46-17.8; P = 0.011) and on 6th hour (OR 4.15; 95% CI, 1.29-13.4; P = 0.017), presence of a lesion in more than one coronary artery (OR 3.29; 95% CI, 1.32-8.16; P = 0.010) found to be independent predictors of AF at 12 months. CONCLUSION: IAB is common in patients with STEMI and along with the presence of diffuse coronary artery disease is associated with new onset of AF.