Prediction of clinical outcomes after percutaneous coronary intervention: Machine-learning analysis of the National Inpatient Sample.

BACKGROUND: This study aimed to develop a multiclass machine-learning (ML) model to predict all-cause mortality, ischemic and hemorrhagic events in unselected hospitalized patients undergoing percutaneous coronary intervention (PCI). METHODS: This retrospective study included 1,815,595 unselected weighted hospitalizations undergoing PCI from the National Inpatient Sample (2016-2019). Five most common ML algorithms (logistic regression, support vector machine (SVM), naive Bayes, random forest (RF), and extreme gradient boosting (XGBoost)) were trained and tested with 101 input features. The study endpoints were different combinations of all-cause mortality, ischemic cerebrovascular events (CVE) and major bleeding. An area under the curve (AUC) with 95% confidence interval (95% CI) was selected as a performance metric. RESULTS: The study population was split to a training cohort of 1,186,880 PCI discharges, validation cohort (for calibration) of 296,725 hospitalizations and a test cohort of 331,990 PCI discharges. A total of 98,180 (5.4%) hospital entries included study outcomes. Logistic regression, SVM, naive Bayes, and RF model demonstrated AUCs of 0.83 (95% CI 0.82-0.84), 0.84 (95% CI 0.83-0.86), 0.81 (95% CI 0.80-0.82), and 0.83 (95% CI 0.81-0.84), retrospectively. The XGBoost classifier performed the best with an AUC of 0.86 (95% CI 0.85-0.87) with excellent calibration. We then built a web-based application that provides predictions based on the XGBoost model. CONCLUSION: We derived the multi-task XGBoost classifier based on 101 features to predict different combinations of all-cause death, ischemic CVE and major bleeding. Such models may be useful in benchmarking and risk prediction using routinely collected administrative data.

Cardiovascular outcomes in breast cancer survivors: a systematic review and meta-analysis.

AIMS: It is unclear whether the future risk of cardiovascular events in breast cancer (Bc) survivors is greater than in the general population. This meta-analysis quantifies the risk of cardiovascular disease development in Bc patients, compared to the risk in a general matched cancer-free population, and reports the incidence of cardiovascular events in patients with Bc. METHODS AND RESULTS: We searched PubMed, Scopus, and Web of Science databases (up to 23 March 2022) for observational studies and post hoc analyses of randomized controlled trials. Cardiovascular death, heart failure (HF), atrial fibrillation (AF), coronary artery disease (CAD), myocardial infarction (MI), and stroke were the individual endpoints for our meta-analysis. We pooled incidence rates (IRs) and risk in hazard ratios (HRs), using random-effects meta-analyses. Heterogeneity was reported through the I2 statistic, and publication bias was examined using funnel plots and Egger's test in the meta-analysis of risk. One hundred and forty-two studies were identified in total, 26 (836 301 patients) relevant to the relative risk and 116 (2 111 882 patients) relevant to IRs. Compared to matched cancer-free controls, Bc patients had higher risk for cardiovascular death within 5 years of cancer diagnosis [HR = 1.09; 95% confidence interval (CI): 1.07, 1.11], HF within 10 years (HR = 1.21; 95% CI: 1.1, 1.33), and AF within 3 years (HR = 1.13; 95% CI: 1.05, 1.21). The pooled IR for cardiovascular death was 1.73 (95% CI 1.18, 2.53), 4.44 (95% CI 3.33, 5.92) for HF, 4.29 (95% CI 3.09, 5.94) for CAD, 1.98 (95% CI 1.24, 3.16) for MI, 4.33 (95% CI 2.97, 6.30) for stroke of any type, and 2.64 (95% CI 2.97, 6.30) for ischaemic stroke. CONCLUSION: Breast cancer exposure was associated with the increased risk for cardiovascular death, HF, and AF. The pooled incidence for cardiovascular endpoints varied depending on population characteristics and endpoint studied. REGISTRATION: CRD42022298741.

This work investigated the absolute and relative risk of cardiovascular outcomes in breast cancer survivors. Breast cancer was associated with a higher risk of cardiovascular death, heart failure (HF), and atrial fibrillation when compared to the general population.The incidence for cardiovascular death, HF, and coronary artery disease were 1.73, 4.44, and 4.29 per 1000 person-years, respectively.Clinicians should carefully assess breast cancer survivors for their cardiovascular risk factor profile and monitor their cardiovascular function.

Phenotyping for percutaneous coronary intervention and long-term recurrent weighted outcomes.

INTRODUCTION: Percutaneous coronary interventions (PCI) are often performed in multimorbid patients with heterogeneous characteristics and variable clinical outcomes. We aimed to identify distinct clinical phenotypes utilizing machine learning and explore their relationship with long-term recurrent and weighted outcomes. METHODS: This prospective observational cohort study enrolled all-comer PCI patients in 2020-2021. Multiple imputation k-means clustering was utilized to detect specific phenotypes. The study endpoints were patient-oriented and device oriented composite endpoints (POCE, DOCE), its individual components, and major bleeding. We applied semiparametric regression models for recurrent and weighted endpoints. RESULTS: The study included a total of 643 patients. We unveiled three phenotype clusters: 1) inflammatory (n = 44, with high white blood cell counts, high values of C-reactive protein (CRP) and neutrophil-to-lymphocyte ratio), 2) high erythrocyte sedimentation rate (ESR) (n = 204), and 3) non-inflammatory (n = 395). For ACS-only population, we four distinct phenotypes (high-CRP, high-ESR, high aspartate-aminotransferase, and normal). For all-comer PCI patients, identified phenotypes had a higher risk of POCE (mean ratio (MR) 1.42 (95% confidence interval (CI) 1.11-1.81) and MR 2.01 (95% CI 1.58-2.56), respectively), DOCE (MR 1.61 (95% CI 1.20-2.16), MR 2.60 (95%CI 1.94-3.48), respectively), and stroke (hazard ratio (HR) 2.86 (95% CI 1.10-7.4), 6.83 (95% CI 2.01-23.2)). Similarly, high-ESR and high-CRP phenotypes of ACS patients were significantly associated with the development of clinical composite outcomes. CONCLUSION: Machine learning unveiled three distinct phenotype clusters in patients after PCI that were linked with the risk of recurrent and weighted clinical endpoints. German Clinical Trial Registry number: DRKS00020892.

Baseline platelet count in percutaneous coronary intervention: a dose-response meta-analysis.

OBJECTIVES: The nature of the relationship between baseline platelet count and clinical outcomes following percutaneous coronary intervention (PCI) is unclear. We undertook dose-response and pairwise meta-analyses to better describe the prognostic value of the initial platelet count and clinical endpoints in patients after PCI. METHODS: A search of PubMed, Scopus and Web of Science (up to 9 October 2021) was performed to identify studies that evaluated the association between platelet count and clinical outcomes following PCI. The primary outcomes of interest were all-cause mortality, major adverse cardiovascular events (MACE) and major bleeding. We performed random-effects pairwise and one-stage dose-response meta-analyses by calculating HRs and 95% CIs. RESULTS: The meta-analysis included 19 studies with 217 459 patients. We report a J-shaped relationship between baseline thrombocyte counts and all-cause death, MACE and major bleeding at follow-up. The risk of haemorrhagic events exceeded the risk of thrombotic events at low platelet counts (<175×109/L), while a predominant ischaemic risk was observed at high platelet counts (>250×109/L). Pairwise meta-analyses revealed a robust link between initial platelet counts and the risk of postdischarge all-cause mortality, major bleeding (for thrombocytopenia: HR 1.39, 95% CI 1.30 to 1.49; HR 1.51, 95% CI 1.15 to 2.00, respectively) and future death from any cause and MACE (thrombocytosis: HR 1.60, 95% CI 1.29 to 1.98; HR 1.47, 95% CI 1.22 to 1.78, respectively). CONCLUSION: Low platelet counts were associated with the predominant bleeding risk, while high platelet counts were only associated with the ischaemic events. PROSPERO REGISTRATION NUMBER: CRD42021283270.

The Prognostic Utility of Mean Platelet Volume in Patients With Acute Coronary Syndrome: A Systematic Review With Meta-Analyses.

Mean platelet volume (MPV) is a hematological index that is routinely measured in clinical settings. Although many studies have been conducted to investigate the prognostic significance of MPV in acute coronary syndromes (ACS), the findings have been inconsistent. The goal of this study was to systematically review all current evidence on the association between admission MPV and clinical outcomes after ACS. PubMed, Scopus, Web of Science, and other databases were searched. The primary endpoints were major adverse cardiovascular events (MACE) and mortality. We applied a Knapp and Hartung adjustment, prediction interval calculations and permutation tests during pairwise meta-analyses. A one-stage dose-response meta-analysis was also conducted. The meta-analysis consisted of 41 studies with 33443 participants. Mean platelet volume, as a continuous variable, was associated with the risk of long-term mortality (hazard ratio 1.33, 95% CI 1.19-1.48). After conducting permutation tests and calculation of prediction intervals, this association remained significant. The results for MACE were nonsignificant. Linear models were the best fitted models during dose-response meta-analyses, trends for nonlinearity were significant for long-term endpoints. Admission MPV was associated with long-term mortality in ACS patients, with nonlinear associations between MPV levels and long-term clinical outcomes.

The implications of blood pressure targets from the 2018 European Society of Cardiology hypertension guidelines in Asian patients: a systematic review and meta-analysis.

BACKGROUND: The evidence for optimal blood pressure (BP) targets in Asian patients with hypertension is insufficient and controversial. Western guidelines should be used with caution in clinical practice until there is supporting evidence. OBJECTIVE: Systematically synthesize the evidence on the efficacy of achieving the strict 2018 European Society of Cardiology (ESC) guideline BP targets versus standard BP targets in Asian patients. DATA SOURCES: We searched PubMed, Web of Science, Scopus, the Cochrane Central Register of controlled trials, and additional databases to retrieve relevant Asian studies. STUDY SELECTION: Randomized controlled trials (RCTs) and observational studies that reported clinical endpoints, had a minimal follow-up period of one year and included Asian patients older than 18 years with essential hypertension. DATA EXTRACTION: Two investigators independently conducted the study selection with any discrepancies resolved between team members. DATA SYNTHESIS: We selected 15 studies for analysis (4 RCTs, 7 observational studies, and 4 post-hoc analyses). The evidence for the strict BP targets in elderly patients was insufficient. In middle-aged patients, the meta-analysis of observational studies revealed a significant reduction in major adverse cardiac events (MACCE) (hazard ratio (HR)=0.78; 95% confidence interval (CI: 0.74-0.81). For studies that reported results for patients of any age, the tight systolic BP-lowering therapy was associated with a decrease in MACCE (HR=0.80; 95% CI: 0.69-0.92), stroke (HR=0.82; 95% CI: 0.71-0.94), but not in cardiac events (HR=0.91; 95% CI: 0.72-1.14, P=.41), all-cause (HR=0.80; 95% CI: 0.57-1.13) and cardiovascular mortality (HR=0.73; 95% CI: 0.40-1.33, P=.30). Similar findings were obtained for the strict diastolic BP targets. CONCLUSION: Our findings provide evidence for Asian patients that support the efficacy of the strict antihypertensive treatment with BP targets proposed by the 2018 ESC hypertension guidelines for the prevention of cardiovascular events. However, these data were obtained from only observational studies and the results were not confirmed by RCTs, probably due to insufficient power. Therefore, further high-quality RCTs are crucial. LIMITATIONS: Use of aggregated data, the subgroup and meta-regression analyses are inconclusive, limited to English language, unable to estimate summary measures for some outcomes, publication bias difficult to assess, and unclear that results could be extrapolated. REGISTRATION: The protocol registered in PROSPERO (CRD42018115570). CONFLICT OF INTEREST: None.

Ticagrelor for Asian patients with acute coronary syndrome in real-world practice: A systematic review and meta-analysis of observational studies.

OBJECTIVE: We aimed to assess the efficacy and safety of ticagrelor compared to clopidogrel in Asian patients with acute coronary syndrome (ACS) in real-world practice. METHODS: PubMed, Web of Science and Scopus databases were searched systematically to obtain relevant Asian observational studies. RESULTS: The meta-analysis included six studies with 27959 participants. Compared with clopidogrel, ticagrelor was significantly beneficial in prevention of major adverse cardiac events (MACCEs) (OR=0.62; 95% CI: 0.46-0.83, I2=69%, p=0.001) mainly driven by reducing stroke (OR=0.62; 95% CI: 0.49-0.78, I2=0%, p<0.001). No differences were found between ticagrelor and clopidogrel in the risk of cardiovascular mortality (OR=0.66; 95% CI: 0.41-1.06, I2=0%, p=0.09), target vessel revascularization (OR=0.53; 95% CI: 0.21-1.35, I2=82%, p=0.18), major bleeding (OR=1.11; 95% CI: 0.62-2.00, I2=75%, p=0.73), and net adverse clinical and cerebral events (OR=0.76; 95% CI: 0.55-1.04, I2=78%, p=0.09). However, ticagrelor significantly increased the incidence of major/minor (OR=1.73; 95% CI: 1.36-2.21, I2=0%, p<0.001) and minor bleeding (OR=1.73; 95% CI: 1.29-2.32, I2=0%, p<0.001). Sensitivity analyses did not find consistent effect of ticagrelor on prevention of all-cause death and myocardial infarction. CONCLUSION: This meta-analysis suggested that ticagrelor might reduce the risk of MACCEs mainly by reducing stroke in Asian patients with ACS without increasing the rates of major bleeding. Ticagrelor did not show a significant effect on other parts of MACCEs. Considerable increase in the risk of major/minor and minor bleeding was observed in ticagrelor compared with clopidogrel users. Further high-quality studies are required to support these findings.