Daily Cardiology Research Analysis

Accurate evaluation of coronary intermediate lesions (50-70% stenosis) is essential for stent decision-making, yet conventional angiography remains subjective and adjunctive tests like FFR are often invasive or costly. In this retrospective multicenter study of 1298 patients, we developed an attention-enhanced deep learning model using Improved_EfficientNet with a Convolutional Block Attention Module to predict stent necessity directly from coronary angiography images. The model utilized multimodal labels from FFR, IVUS, and OCT as reference standards during training. In internal validation, the model achieved an accuracy of 0.976 and an F1-score of 0.971. External validation across independent institutions demonstrated robust performance with an accuracy of 0.807 and an AUC of 0.897. Grad-CAM visualization confirmed that the model focuses on clinically relevant stenotic regions, showing high alignment with expert interpretations. These results suggest that the proposed model can effectively integrate anatomical and functional information to provide real-time decision support, potentially reducing the need for invasive adjunctive testing and enhancing precision in interventional cardiology.

BACKGROUND: Evidence supporting the discontinuation of antiplatelet therapy in patients with stable coronary artery disease who require anticoagulation remains limited and continues to evolve. This study aimed to assess the efficacy and safety of antithrombotic therapy in this population. METHODS: We reviewed randomized controlled trials comparing the efficacy and safety of oral anticoagulant monotherapy versus oral anticoagulant plus single antiplatelet therapy in patients beyond six months after coronary revascularization requiring anticoagulation. The outcomes included major adverse cardiovascular events (MACE) and major bleeding. MACE was defined as a composite of all-cause death, myocardial infarction, stroke, systemic embolism, and revascularization. A pairwise meta-analysis using a random-effects model was conducted. RESULTS: A total of 5924 patients from 6 randomized controlled trials were included: 2970 received oral anticoagulant alone, and 2954 received oral anticoagulant plus single antiplatelet therapy. Anticoagulant monotherapy was associated with a comparable risk of MACE [hazard ratio (HR), 0.80; 95% confidence interval (CI), 0.62-1.04] and a significantly lower major bleeding risk (HR, 0.46; 95% CI, 0.32-0.66) than the combined therapy. CONCLUSION: Oral anticoagulant alone may be a reasonable strategy to mitigate bleeding risk while preserving an ischemic risk comparable to combined anticoagulant and antiplatelet therapy.

BACKGROUND: Cardiovascular risk prediction models use single blood pressure measurements. Cumulative blood pressure exposure over time may better predict cardiovascular events. METHODS: We used data from a large community database to examine the incremental value of 10-year cumulative blood pressure exposure over standard risk based on a single value using the Pooled Cohort Equations (PCE). The index date was set to January 1, 2018, with a 5-year prediction horizon and 10 years of prior exposure. Individuals included were 45 years of age or older, had no known cardiovascular disease and had at least 3 prior blood pressure values. The primary exposure was cumulative blood pressure over the previous 10 years, expressed as the area under the systolic blood pressure curve over 140 mmHg. We assessed the model's ability to improve prediction of "Hard cardiovascular disease" (cardiac mortality, myocardial infarction or stroke), stroke and all cause mortality beyond that achieved by the PCE. RESULTS: Our cohort of 614,084 individuals was divided into a derivation set of 428,826 and a validation set of 184,222 individuals. The C statistic improved by 0.8% (95% CI: 0, 0.8%), 1.3% (1.0, 1.7%), and 0% (0, 0.1%), and continuous net reclassification improvement was 0.492, 0.656 and 0.539 for the "Hard cardiovascular disease", stroke, and all-cause mortality outcomes, respectively. CONCLUSIONS: Cumulative blood pressure exposure over 10 years significantly improves the prediction of incident cardiovascular events and mortality above that derived from a single value. Introduction of cumulative blood pressure exposure into electronic health records might facilitate personalized risk prediction.