Explore the vast range of titles available.

Machine learning (ML) is a powerful tool for identifying and structuring several informative variables for predictive tasks. Here, we investigated how ML algorithms may assist in echocardiographic pulmonary hypertension (PH) prediction, where current guidelines recommend integrating several echocardiographic parameters. In our database of 90 patients with invasively determined pulmonary artery pressure (PAP) with corresponding echocardiographic estimations of PAP obtained within 24 hours, we trained and applied five ML algorithms (random forest of classification trees, random forest of regression trees, lasso penalized logistic regression, boosted classification trees, support vector machines) using a 10 times 3-fold cross-validation (CV) scheme. ML algorithms achieved high prediction accuracies: support vector machines (AUC 0.83; 95% CI 0.73-0.93), boosted classification trees (AUC 0.80; 95% CI 0.68-0.92), lasso penalized logistic regression (AUC 0.78; 95% CI 0.67-0.89), random forest of classification trees (AUC 0.85; 95% CI 0.75-0.95), random forest of regression trees (AUC 0.87; 95% CI 0.78-0.96). In contrast to the best of several conventional formulae (by Aduen et al.), this ML algorithm is based on several echocardiographic signs and feature selection, with estimated right atrial pressure (RAP) being of minor importance. Using ML, we were able to predict pulmonary hypertension based on a broader set of echocardiographic data with little reliance on estimated RAP compared to an existing formula with non-inferior performance. With the conceptual advantages of a broader and unbiased selection and weighting of data our ML approach is suited for high level assistance in PH prediction.

Transcatheter aortic valve replacement (TAVR) has become the standard treatment for aortic stenosis in older patients. It increasingly relies on accurate pre-procedural planning using multidetector computed tomography (MDCT). Since little is known about the required competence levels for MDCT analyses, we comprehensively assessed MDCT TAVR planning reproducibility and accuracy with regard to valve selection in various healthcare workers. 20 randomly selected MDCT of TAVR patients were analyzed using dedicated software by healthcare professionals with varying backgrounds and experience (two structural interventionalists, one imaging specialist, one cardiac surgeon, one general physician, and one medical student). Following the analysis, the most appropriate Edwards SAPIEN 3™ and Medtronic CoreValve valve size was selected. Intra- and inter-observer variability were assessed. The first structural interventionalist was considered as reference standard for inter-observer comparison. Excellent intra- and inter-observer variability was found for the entire group in regard to the MDCT measurements. The best intra-observer agreement and reproducibility were found for the structural interventionalist, while the medical student had the lowest reproducibility. The highest inter-observer agreement was between both structural interventionalists, followed by the imaging specialist. As to valve size selection, the structural interventionalist showed the highest intra-observer reproducibility, independent of the brand of valve used. Compared to the reference structural interventionalist, the second structural interventionalist showed the highest inter-observer agreement for valve size selection [ICC 0.984, 95% CI 0.969–0.991] followed by the cardiac surgeon [ICC 0.947, 95%CI 0.900–0.972]. The lowest inter-observer agreement was found for the medical student [ICC 0.507, 95%CI 0.067–0.739]. While current state-of-the-art MDCT analysis software provides excellent reproducibility for anatomical measurements, the highest levels of confidence in terms of valve size selection were achieved by the performing interventional physicians. This was most likely attributable to observer experience.

Background Since cardiovascular magnetic resonance (CMR) imaging allows comprehensive quantification of both myocardial function and structure we aimed to assess myocardial remodeling processes in patients with severe aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). Methods CMR imaging was performed in 40 patients with severe AS before and 1 year after TAVR. Image analyses comprised assessments of myocardial volumes, CMR-feature-tracking based atrial and ventricular strain, myocardial T1 mapping, extracellular volume fraction-based calculation of left ventricular (LV) cellular and matrix volumes, as well as ischemic and non-ischemic late gadolinium enhancement analyses. Moreover, biomarkers including NT-proBNP as well as functional and clinical status were documented. Results Myocardial function improved 1 year after TAVR: LV ejection fraction (57.9 ± 16.9% to 65.4 ± 14.5%, p = 0.002); LV global longitudinal (− 21.4 ± 8.0% to -25.0 ± 6.4%, p < 0.001) and circumferential strain (− 36.9 ± 14.3% to − 42.6 ± 11.8%, p = 0.001); left atrial reservoir (13.3 ± 6.3% to 17.8 ± 6.7%, p = 0.001), conduit (5.5 ± 3.2% to 8.4 ± 4.6%, p = 0.001) and boosterpump strain (8.2 ± 4.6% to 9.9 ± 4.2%, p = 0.027). This was paralleled by regression of total myocardial volume (90.3 ± 21.0 ml/m 2 to 73.5 ± 17.0 ml/m 2 , p < 0.001) including cellular (55.2 ± 13.2 ml/m 2 to 45.3 ± 11.1 ml/m 2 , p < 0.001) and matrix volumes (20.7 ± 6.1 ml/m 2 to 18.8 ± 5.3 ml/m 2 , p = 0.036). These changes were paralleled by recovery from heart failure (decrease of NYHA class: p < 0.001; declining NT-proBNP levels: 2456 ± 3002 ng/L to 988 ± 1222 ng/L, p = 0.001). Conclusion CMR imaging enables comprehensive detection of myocardial remodeling in patients undergoing TAVR. Regression of LV matrix volume as a surrogate for reversible diffuse myocardial fibrosis is accompanied by increase of myocardial function and recovery from heart failure. Further data are required to define the value of these parameters as therapeutic targets for optimized management of TAVR patients. Trial registration DRKS, DRKS00024479. Registered 10 December 2021—Retrospectively registered, https://www.drks.de/drks_web/navigate.do?navigationId=trial.HTML&TRIAL_ID=DRKS00024479

Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. Leveraging these could enhance transformer architectures’ ability in regimes with small and diversely annotated sets. We conduct the largest federated cardiac CT analysis to date ( n = 8, 104) in a real-world setting across eight hospitals. Our two-step semi-supervised strategy distills knowledge from task-specific CNNs into a transformer. First, CNNs predict on unlabeled data per label type and then the transformer learns from these predictions with label-specific heads. This improves predictive accuracy and enables simultaneous learning of all partial labels across the federation, and outperforms UNet-based models in generalizability on downstream tasks. Code and model weights are made openly available for leveraging future cardiac CT analysis.

Background Myocardial fibrosis is a major determinant of outcome in aortic stenosis (AS). Novel fast real-time (RT) cardiovascular magnetic resonance (CMR) mapping techniques allow comprehensive quantification of fibrosis but have not yet been compared against standard techniques and histology. Methods Patients with severe AS underwent CMR before ( n  = 110) and left ventricular (LV) endomyocardial biopsy ( n  = 46) at transcatheter aortic valve replacement (TAVR). Midventricular short axis (SAX) native, post-contrast T1 and extracellular volume fraction (ECV) maps were generated using commercially available modified Look-Locker Inversion recovery (MOLLI) (native: 5(3)3, post-contrast: 4(1)3(1)2) and RT single-shot inversion recovery Fast Low-Angle Shot (FLASH) with radial undersampling. Focal late gadolinium enhancement was excluded from T1 and ECV regions of interest. ECV and LV mass were used to calculate LV matrix volumes. Variability and agreements were assessed between RT, MOLLI and histology using intraclass correlation coefficients, coefficients of variation and Bland Altman analyses. Results RT and MOLLI derived ECV were similar for midventricular SAX slice coverage (26.2 vs. 26.5, p  = 0.073) and septal region of interest (26.2 vs. 26.5, p  = 0.216). MOLLI native T1 time was in median 20 ms longer compared to RT ( p  < 0.001). Agreement between RT and MOLLI was best for ECV (ICC > 0.91), excellent for post-contrast T1 times (ICC > 0.81) and good for native T1 times (ICC > 0.62). Diffuse collagen volume fraction by biopsies was in median 7.8%. ECV (RT r  = 0.345, p  = 0.039; MOLLI r  = 0.40, p  = 0.010) and LV matrix volumes (RT r  = 0.45, p  = 0.005; MOLLI r  = 0.43, p  = 0.007) were the only parameters associated with histology. Conclusions RT mapping offers fast and sufficient ECV and LV matrix volume calculation in AS patients. ECV and LV matrix volume represent robust and universally comparable parameters with associations to histologically assessed fibrosis and may emerge as potential targets for clinical decision making.

Background: The diagnostic performance of preprocedural CT angiography in detecting coronary artery disease (CAD) in patients scheduled for transcatheter aortic valve implantation (TAVI) has been reported. However, data on predictors of diagnostic inaccuracy are sparse. We sought to investigate clinical characteristics and imaging criteria that predict the inaccurate assessment of coronary artery stenosis based on pre-TAVI-CT. Methods: The patient- and vessel-level analysis of all CT datasets from 192 patients (mean age 82.1 ± 4.8 years; 63.5% female) without known CAD or severe renal dysfunction was performed retrospectively in a blinded fashion. Significant CAD was defined as a CAD-RADS™ 2.0 category ≥ 4 by CT. Invasive coronary angiography (ICA) served as the reference standard for relevant CAD (≥70% luminal diameter stenosis or fractional flow reserve ≤ 0.80). Pertinent clinical characteristics and imaging criteria of all true-positive (n = 71), false-positive (n = 30), false-negative (n = 4), and true-negative patient-level CT diagnoses (n = 87) for relevant stenosis according to ICA were assessed. Results: In the univariate per-patient analysis, the following parameters yielded discriminative power (p < 0.10) regarding inaccurate CAD assessment by pre-TAVI-CT: age, atrial fibrillation, scanner generation, and image quality. Factors independently associated with CT diagnostic inaccuracy were determined using multivariable logistic regression analysis: a younger age (odds ratio [OR] 0.87; 95% confidence interval [CI] 0.80 to 0.94; p < 0.01) and insufficient CT image quality (OR 0.6; CI 0.41 to 0.89; p < 0.01). Conclusions: Our results demonstrate younger age and poor CT image quality to predict less accurate CAD assessments by pre-TAVI-CT in comparison with ICA. Knowledge of these predictors may aid in more efficient coronary artery interpretations based on pre-TAVI-CT.

Aims There is evidence to suggest that the subtype of aortic stenosis (AS), the degree of myocardial fibrosis (MF), and level of aortic valve calcification (AVC) are associated with adverse cardiac outcome in AS. Because little is known about their respective contribution, we sought to investigate their relative importance and interplay as well as their association with adverse cardiac events following transcatheter aortic valve replacement (TAVR). Methods and results One hundred consecutive patients with severe AS and indication for TAVR were prospectively enrolled between January 2017 and October 2018. Patients underwent transthoracic echocardiography, multidetector computed tomography, and left ventricular endomyocardial biopsies at the time of TAVR. The final study cohort consisted of 92 patients with a completed study protocol, 39 (42.4%) of whom showed a normal ejection fraction (EF) high‐gradient (NEFHG) AS, 13 (14.1%) a low EF high‐gradient (LEFHG) AS, 25 (27.2%) a low EF low‐gradient (LEFLG) AS, and 15 (16.3%) a paradoxical low‐flow, low‐gradient (PLFLG) AS. The high‐gradient phenotypes (NEFHG and LEFHG) showed the largest amount of AVC (807 ± 421 and 813 ± 281 mm3, respectively) as compared with the low‐gradient phenotypes (LEFLG and PLFLG; 503 ± 326 and 555 ± 594 mm3, respectively, P < 0.05). Conversely, MF was most prevalent in low‐output phenotypes (LEFLG > LEFHG > PLFLG > NEFHG, P < 0.05). This was paralleled by a greater cardiovascular (CV) mortality within 600 days after TAVR (LEFLG 28% > PLFLG 26.7% > LEFHG 15.4% > NEFHG 2.5%; P = 0.023). In patients with a high MF burden, a higher AVC was associated with a lower mortality following TAVR (P = 0.045, hazard ratio 0.261, 95% confidence interval 0.07–0.97). Conclusions MF is associated with adverse CV outcome following TAVR, which is most prevalent in low EF situations. In the presence of large MF burden, patients with large AVC have better outcome following TAVR. Conversely, worse outcome in large MF and relatively little AVC may be explained by a relative prominence of an underlying cardiomyopathy. The better survival rates in large AVC patients following TAVR indicate TAVR induced relief of severe AS‐associated pressure overload with subsequently improved outcome.

Extracorporeal life support (ECLS) is increasingly used in the treatment of infarct-related cardiogenic shock despite a lack of evidence regarding its effect on mortality. In this multicenter trial, patients with acute myocardial infarction complicated by cardiogenic shock for whom early revascularization was planned were randomly assigned to receive early ECLS plus usual medical treatment (ECLS group) or usual medical treatment alone (control group). The primary outcome was death from any cause at 30 days. Safety outcomes included bleeding, stroke, and peripheral vascular complications warranting interventional or surgical therapy. A total of 420 patients underwent randomization, and 417 patients were included in final analyses. At 30 days, death from any cause had occurred in 100 of 209 patients (47.8%) in the ECLS group and in 102 of 208 patients (49.0%) in the control group (relative risk, 0.98; 95% confidence interval [CI], 0.80 to 1.19; P = 0.81). The median duration of mechanical ventilation was 7 days (interquartile range, 4 to 12) in the ECLS group and 5 days (interquartile range, 3 to 9) in the control group (median difference, 1 day; 95% CI, 0 to 2). The safety outcome consisting of moderate or severe bleeding occurred in 23.4% of the patients in the ECLS group and in 9.6% of those in the control group (relative risk, 2.44; 95% CI, 1.50 to 3.95); peripheral vascular complications warranting intervention occurred in 11.0% and 3.8%, respectively (relative risk, 2.86; 95% CI, 1.31 to 6.25). In patients with acute myocardial infarction complicated by cardiogenic shock with planned early revascularization, the risk of death from any cause at the 30-day follow-up was not lower among the patients who received ECLS therapy than among those who received medical therapy alone. (Funded by the Else Kröner Fresenius Foundation and others; ECLS-SHOCK ClinicalTrials.gov number, NCT03637205.).

In heart failure, intracellular Ca 2+ leak from cardiac ryanodine receptors (RyR2s) leads to a loss of Ca 2+ from the sarcoplasmic reticulum (SR) potentially contributing to decreased function. Experimental data suggest that the 1,4-benzothiazepine K201 (JTV-519) may stabilise RyR2s and thereby reduce detrimental intracellular Ca 2+ leak. Whether K201 exerts beneficial effects in human failing myocardium is unknown. Therefore, we have studied the effects of K201 on muscle preparations from failing human hearts. K201 (0.3 μM; extracellular [Ca 2+ ] e 1.25 mM) showed no effects on contractile function and micromolar concentrations resulted in negative inotropic effects (K201 1 μM; developed tension −9.8 ± 2.5% compared to control group; P  < 0.05). Interestingly, K201 (0.3 μM) increased the post-rest potentiation (PRP) of failing myocardium after 120 s, indicating an increased SR Ca 2+ load. At high [Ca 2+ ] e concentrations (5 mmol/L), K201 increased PRP already at shorter rest intervals (30 s). Strikingly, treatment with K201 (0.3 μM) prevented diastolic dysfunction (diastolic tension at 5 mmol/L [Ca 2+ ] e normalised to 1 mmol/L [Ca 2+ ] e : control 1.26 ± 0.06, K201 1.01 ± 0.03, P  < 0.01). In addition at high [Ca 2+ ] e, K201 (0.3 μM) treatment significantly improved systolic function [developed tension +27 ± 8% (K201 vs. control); P  < 0.05]. The beneficial effects on diastolic and systolic functions occurred throughout the physiological frequency range of the human heart rate from 1 to 3 Hz. Upon elevated intracellular Ca 2+ concentration, systolic and diastolic contractile functions of terminally failing human myocardium are improved by K201.