Daily Cardiology Research Analysis

AIMS: Hybrid intravascular ultrasound-optical coherence tomography (IVUS-OCT) can enable more accurate plaque characterization than single-modality intravascular imaging, enhancing treatment planning and vulnerable plaque detection. However, image interpretation in IVUS-OCT is challenging and time-consuming. To overcome this limitation, we introduce a novel histology-trained deep learning (DL)-classifier for plaque component classification in IVUS-OCT images and compare its performance against single-modality DL and expert analysts. METHODS AND RESULTS: IVUS-OCT frames and matched histological sections from 10 cadaveric human hearts were included in this analysis. The histological data were used to define fibrotic, calcific, and necrotic core tissue regions of interest (ROIs) in IVUS-OCT and used to train three DL-classifiers for IVUS, OCT, or hybrid IVUS-OCT image analysis (992 frames) and test their performance (264 frames). The test set was additionally annotated by experts from three different core labs, and their estimations and those of the DL-classifiers were compared with histology.The IVUS-OCT DL-classifier had a superior performance to the IVUS-DL, OCT-DL, and the expert analysts in detecting plaque phenotypes (Kappa 0.60 vs. 0.19, 0.35, and 0.53, respectively) and accurately classified 68% of histologically defined fibroatheromas. The hybrid IVUS-OCT DL-classifier also had a better performance than single-modality DL-classifiers and the experts in assessing tissue types in ROIs annotated by histology (overall accuracy 86.7% compared with 73.2% for IVUS-DL, 66.6% for OCT-DL, and 70.6% for the experts). CONCLUSION: Plaque characterization using a histology-trained hybrid IVUS-OCT DL-classifier is feasible and enables more accurate detection of plaque components and phenotype classification than single-modality DL-classifiers and expert analysts.

BACKGROUND AND AIMS: Atrial fibrillation (AF) disease burden is increasing. Pharmacotherapy of cardio-renal-metabolic diseases may prevent incident AF. This meta-analysis estimates the effect of different pharmacotherapies on risk of incident AF across cardio-renal-metabolic diseases. METHODS: The Medline, Embase, and Cochrane Central databases were searched to 7 October 2025 for randomized clinical trials (RCTs) comparing the effect of a non-antiarrhythmic cardio-renal-metabolic medication with control or another agent for incident AF. Random-effects meta-analysis using the Mantel-Haenszel method, with between-study variance estimated using the DerSimonian-Laird method, was performed to synthesize risk ratios (RR) with 95% confidence intervals (CI). RESULTS: Two hundred and forty-nine RCTs involving 745 041 patients were included, of which 207 identified AF through adverse event reports, 161 were placebo-controlled, and 15 had AF as a pre-specified endpoint. In placebo-controlled trials, significant differences in incident AF were observed with treatment of heart failure with reduced ejection fraction with angiotensin-converting enzyme inhibitors and angiotensin receptor blockers (RR 0.69, 95% CI 0.60-0.80), mineralocorticoid receptor antagonists (RR 0.62, 95% CI 0.43-0.90), and sodium-glucose co-transporter 2 (SGLT2) inhibitors (RR 0.62, 95% CI 0.44-0.87); treatment of chronic kidney disease with SGLT2 inhibitors (RR 0.53, 95% CI 0.33-0.85); and treatment of obesity with glucagon-like peptide-1 receptor agonists (RR 0.79, 95% CI 0.63-0.99). However, the number of AF events per trial was low and none were adequately powered for incident AF. CONCLUSIONS: Prospective RCTs with AF as a pre-specified outcome should be integrated into the design of future trials of cardio-renal-metabolic medications to determine whether they reduce incident AF.

AIMS: Current recommendations for echocardiography-based classification of left ventricular filling pressure (LVFP) as normal or elevated, are based on an algorithm and parameter selection determined by human experts. We tested whether machine learning (ML) can improve classification of LVFP and investigated which parameters were deemed most important by different ML models. METHODS: In a multicentre study, echocardiography was performed simultaneously with, or within 24 hours of, heart catheterization in 250 patients. Eight different ML models were trained and tested using a nested cross-validation procedure to classify LVFP as normal or elevated. The training included a search and selection of the most useful parameters. Performance was assessed from the test sets not seen during training. RESULTS: The eight ML models could classify all patients regardless of missing parameter values with accuracy ranging from 82% to 86%. The 2016 ASE/EACVI guidelines algorithm left 13% unclassified due to missing values and had an accuracy of 81% in the remaining patients. On average the eight ML models selected 13 parameters, and left atrial strain was included in three of these. The five highest ranked parameters by the ML models were: mitral E/left atrial reservoir strain, log(NT-proBNP), tricuspid regurgitation velocity, septal E/e' and E/A. CONCLUSIONS: ML can improve classification of LVFP, particularly with a higher feasibility. The study unveiled less used parameters as some of the most valuable for evaluating LVFP.