Background: Myocardial infarction can lead to malignant arrhythmia, heart failure, and sudden death. Clinical studies have shown that early identification of and timely intervention for acute MI can significantly reduce mortality. The traditional MI risk assessment models are subjective, and the data that go into them are difficult to obtain. Generally, the assessment is only conducted among high-risk patient groups.Objective: To construct an artificial intelligence–based risk prediction model of myocardial infarction (MI) for continuous and active monitoring of inpatients, especially those in noncardiovascular departments, and early warning of MI.Methods: The imbalanced data contain 59 features, which were constructed into a specific dataset through proportional division, upsampling, downsampling, easy ensemble, and w-easy ensemble. Then, the dataset was traversed using supervised machine learning, with recursive feature elimination as the top-layer algorithm and random forest, gradient boosting decision tree (GBDT), logistic regression, and support vector machine as the bottom-layer algorithms, to select the best model out of many through a variety of evaluation indices.Results: GBDT was the best bottom-layer algorithm, and downsampling was the best dataset construction method. In the validation set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.84. In the test set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.83, and the area under the curve was 0.91.Conclusion: Compared with traditional models, artificial intelligence–based machine learning models have better accuracy and real-time performance and can reduce the occurrence of in-hospital MI from a data-driven perspective, thereby increasing the cure rate of patients and improving their prognosis.
Objective. We aim to conduct a comparison of the safety and effectiveness performance between left bundle branch area pacing (LBBAP) and right ventricular pacing (RVP) regimens for patients with atrioventricular block (AVB). Methods. This observational cohort study included patients who underwent pacemaker implantations with LBBAP or RVP for AVB indications from the 1st of January 2018 to the 18th of November 2021 at West China Hospital. The primary composite outcome included all-cause mortality, lead failure, or heart failure hospitalization (HFH). The secondary outcome included periprocedure complication, cardiac death, or recurrent unexplained syncope. A 1 : 1 propensity score–matched cohort was conducted for left ventricular (LV) function analysis. Results. A total of 903 patients met the inclusion criteria and completed clinical follow-up. After adjusting for the possible confounders, LBBAP was independently associated with a lower risk of the primary outcome (OR 0.48, 95% CI 0.28 to 0.83, ), including a lower risk of all-cause mortality and HFH. No significant difference in the secondary outcome was detected between the groups except that LBBAP was independently associated with a lower risk of recurrent unexplained syncope. In the propensity-score matching cohort of echocardiographic analysis, the LV systolic dyssynchrony index was lower in LBBAP compared with that in RVP ( vs. %, ). Conclusions. Compared to conventional RVP, LBBAP is a feasible novel pacing model associated with a significant reduction in the primary composite outcome. Moreover, LBBAP significantly reduces the risk of recurrent unexplained syncope and improves LV systolic synchrony. This study is registered with ClinicalTrials.gov NCT05722379.
Background. Thrombocytopenia was intuitively considered to be associated with higher risk of bleeding and multiple comorbidities after percutaneous coronary intervention (PCI). However, controversial results exist, and the real-world clinical impact of thrombocytopenia in patients undergoing PCI is largely unknown. The aim of this study was to evaluate the influence of baseline thrombocytopenia on the prognosis of patients undergoing PCI. Methods. Using the West China Hospital Inpatient Sample database, patients who underwent PCI were identified from August 2012 to January 2019. Baseline thrombocytopenia was defined as a preprocedural platelet count of or less obtained from a routine blood sample taken within 48 hours before coronary PCI. The clinical effect of the advanced thrombocytopenia group ( ), according to the median value of platelet count in the thrombocytopenia cohort, was further assessed. The primary outcome was a composite of in-hospital death, bleeding events, and post-PCI transfusion. Results. Of 9531 patients enrolled in our study, 936 had baseline thrombocytopenia and 8595 patients did not have. There were no significant differences in the primary outcome between the two groups. However, advanced thrombocytopenia was independently associated with higher risk of primary outcome (OR 1.67, 95% CI 1.06 to 2.65, ). Acute coronary syndrome (ACS) patients with thrombocytopenia were associated with higher odds of major bleeding ( ) (OR 2.56, 95% CI 1.24 to 5.44, ). Compared with the nonthrombocytopenia group, the thrombocytopenia group with ticagrelor use had higher odds of major bleeding (OR 9.7, 95% CI 1.57 to 60.4 versus OR 0.22, 95% CI 0.03 to 1.69, interaction ). Conclusions. It seems feasible for patients with thrombocytopenia to receive PCI, but close attention should be paid to advanced thrombocytopenia, the risk of postprocedure bleeding in ACS patients, and the use of more potent P2Y12 inhibitor.
Primary percutaneous coronary intervention (PPCI), the preferred reperfusion strategy for all acute ST‐segment elevation myocardial infarction (STEMI) patients, is not universally available in clinical practice. Pharmacoinvasive strategy has been proposed as a therapeutic option in patients with STEMI when timely PPCI is not feasible. However, pharmacoinvasive strategy has potential delay between clinical patency and complete myocardial perfusion. The optimal reperfusion strategy for STEMI patients with anticipated PPCI delay according to current practice is uncertain. OPTIMAL‐REPERFUSION is an investigator‐initiated, prospective, multicenter, randomized, open‐label, superiority trial with blinded evaluation of outcomes. A total of 632 STEMI patients presenting within 6 hours after symptom onset and with an expected time of first medical contact to percutaneous coronary intervention (PCI) ≥120 minute will be randomized to a reduced‐dose facilitated PCI strategy (reduced‐dose fibrinolysis combined with simultaneous transfer for immediate invasive therapy with a time interval between fibrinolysis to PCI < 3 hours) or to standard pharmacoinvasive treatment. The primary endpoint is the composite of death, reinfarction, refractory ischemia, congestive heart failure, or cardiogenic shock at 30‐days. Enrollment of the first patient is planned in March 2021. The recruitment is anticipated to last for 12 to 18 months and to complete in September 2023 with 1 year follow‐up. The OPTIMAL‐REPERFUSION trial will help determine whether reduced‐dose facilitated PCI strategy improves clinical outcomes in patients with STEMI and anticipated PPCI delay. This study is registered with the ClinicalTrials.gov (NCT04752345).