Aims The objective of the EuroHeart Failure Survey II (EHFS II) was to assess patient characteristics, aetiology, treatment, and outcome of acute heart failure (AHF) in Europe in relation to the guidelines on the diagnosis and treatment of AHF published by the European Society of Cardiology. Methods and results Patients hospitalized for AHF were recruited by 133 centres in 30 European countries. Three thousand five hundred and eighty patients were entered into the database by the end of August 2005. Mean age was 70 years, and 61% of patients were male. New-onset AHF (de novo AHF) was diagnosed in 37%, of which 42% was due to acute coronary syndromes (ACS). Clinical classification according to the guidelines divided AHF patients into (i) decompensated HF (65%), (ii) pulmonary oedema (16%), (iii) HF and hypertension (11%), (iv) cardiogenic shock (4%), and (v) right HF (3%). Coronary heart disease, hypertension, and atrial fibrillation were the most common underlying conditions. Arrhythmias, valvular dysfunction, and ACS were each present as precipitating factor in one-third of cases. Preserved left ventricular ejection fraction (≥45%) was observed in 34%. Valvular disorders were common, especially mitral regurgitation (MR) which was reported on echocardiography in 80% of patients. Median length of stay was 9 days, and in-hospital mortality 6.7%. At discharge, 80% of patients were on angiotensin-converting enzyme-inhibitors or angiotensin receptor blockers, whereas 61% were taking beta-blocker medication. Conclusion Decompensated HF is the most common clinical presentation of AHF patients. More than one-third of AHF patients do not have a previous history of HF, and new-onset HF is often caused by ACS. Preserved systolic function is found in a substantial proportion of the patients. The prevalence of valvular dysfunction is strikingly high and contributes to the clinical presentation. The EHFS II on AHF verified that the use of evidence-based HF medication was well adopted to clinical practice.

GLORIA-AF (Global Registry on Long-Term Oral Antithrombotic Treatment in Patients with Atrial Fibrillation) is a prospective, global registry program describing antithrombotic treatment patterns in patients with newly diagnosed nonvalvular atrial fibrillation at risk of stroke. Phase 2 began when dabigatran, the first non-vitamin K antagonist oral anticoagulant (NOAC), became available. This study sought to describe phase 2 baseline data and compare these with the pre-NOAC era collected during phase 1. During phase 2, 15,641 consenting patients were enrolled (November 2011 to December 2014); 15,092 were eligible. This pre-specified cross-sectional analysis describes eligible patients' baseline characteristics. Atrial fibrillation disease characteristics, medical outcomes, and concomitant diseases and medications were collected. Data were analyzed using descriptive statistics. Of the total patients, 45.5% were female; median age was 71 (interquartile range: 64, 78) years. Patients were from Europe (47.1%), North America (22.5%), Asia (20.3%), Latin America (6.0%), and the Middle East/Africa (4.0%). Most had high stroke risk (CHA2DS2-VASc [Congestive heart failure, Hypertension, Age ≥75 years, Diabetes mellitus, previous Stroke, Vascular disease, Age 65 to 74 years, Sex category] score ≥2; 86.1%); 13.9% had moderate risk (CHA2DS2-VASc = 1). Overall, 79.9% received oral anticoagulants, of whom 47.6% received NOAC and 32.3% vitamin K antagonists (VKA); 12.1% received antiplatelet agents; 7.8% received no antithrombotic treatment. For comparison, the proportion of phase 1 patients (of N = 1,063 all eligible) prescribed VKA was 32.8%, acetylsalicylic acid 41.7%, and no therapy 20.2%. In Europe in phase 2, treatment with NOAC was more common than VKA (52.3% and 37.8%, respectively); 6.0% of patients received antiplatelet treatment; and 3.8% received no antithrombotic treatment. In North America, 52.1%, 26.2%, and 14.0% of patients received NOAC, VKA, and antiplatelet drugs, respectively; 7.5% received no antithrombotic treatment. NOAC use was less common in Asia (27.7%), where 27.5% of patients received VKA, 25.0% antiplatelet drugs, and 19.8% no antithrombotic treatment. The baseline data from GLORIA-AF phase 2 demonstrate that in newly diagnosed nonvalvular atrial fibrillation patients, NOAC have been highly adopted into practice, becoming more frequently prescribed than VKA in Europe and North America. Worldwide, however, a large proportion of patients remain undertreated, particularly in Asia and North America. (Global Registry on Long-Term Oral Antithrombotic Treatment in Patients With Atrial Fibrillation [GLORIA-AF]; NCT01468701).

Considering the significant burden to patients and healthcare systems globally related to atrial fibrillation (AF) complications, the early AF diagnosis is of crucial importance. In the view of prominent perspectives for fast and accurate point-of-care arrhythmia detection, our study optimizes an artificial neural network (NN) classifier and ranks the importance of enhanced 137 diagnostic ECG features computed from time and frequency ECG signal representations of short single-lead strips available in 2017 Physionet/CinC Challenge database. Based on hyperparameters’ grid search of densely connected NN layers, we derive the optimal topology with three layers and 128, 32, 4 neurons per layer (DenseNet-3@128-32-4), which presents maximal F1-scores for classification of Normal rhythms (0.883, 5076 strips), AF (0.825, 758 strips), Other rhythms (0.705, 2415 strips), Noise (0.618, 279 strips) and total F1 relevant to the CinC Challenge of 0.804, derived by five-fold cross-validation. DenseNet-3@128-32-4 performs equally well with 137 to 32 features and presents tolerable reduction by about 0.03 to 0.06 points for limited input sets, including 8 and 16 features, respectively. The feature reduction is linked to effective application of a comprehensive method for computation of the feature map importance based on the weights of the activated neurons through the total path from input to specific output in DenseNet. The detailed analysis of 20 top-ranked ECG features with greatest importance to the detection of each rhythm and overall of all rhythms reveals DenseNet decision-making process, noticeably corresponding to the cardiologists’ diagnostic point of view.

The QT interval and the QT dispersion are currently a subject of considerable interest. Cardiac repolarization delay is known to favor the development of arrhythmias. The QT dispersion, defined as the difference between the longest and the shortest QT intervals or as the standard deviation of the QT duration in the 12-lead ECG is assumed to be reliable predictor of cardiovascular mortality. The seventh annual PhysioNet/Computers in Cardiology Challenge, 2006 addresses a question of high clinical interest: Can the QT interval be measured by fully automated methods with accuracy acceptable for clinical evaluations? The PTB Diagnostic ECG Database was given to 4 cardiologists and 1 biomedical engineer for manual marking of QRS onsets and T-wave ends in 458 recordings. Each recording consisted of one selected beat in lead II, chosen visually to have minimum baseline shift, noise, and artifact.In cases where no T wave could be observed or its amplitude was very small, the referees were instructed to mark a 'group-T-wave end' taking into consideration leads with better manifested T wave.A modified Delphi approach was used, which included up to three rounds of measurements to obtain results closer to the median. A total amount of 2*5*548 Q-onsets and T-wave ends were manually marked during round 1. To obtain closer to the median results, 8.58 % of Q-onsets and 3.21 % of the T-wave ends had to be reviewed during round 2, and 1.50 % Q-onsets and 1.17 % T-wave ends in round 3. The mean and standard deviation of the differences between the values of the referees and the median after round 3 were 2.43 +/- 0.96 ms for the Q-onset, and 7.43 +/- 3.44 ms for the T-wave end. A fully accessible, on the Internet, dataset of manually measured Q-onsets and T-wave ends was created and presented in additional file: 1 (Table 4) with this article. Thus, an available standard can be used for the development of automated methods for the detection of Q-onsets, T-wave ends and for QT interval measurements.

Background/Objectives: The timely and accurate detection of atrial fibrillation (AF) is critical from a clinical perspective. Detecting short or transient AF events is challenging in 24–72 h Holter ECG recordings, especially when symptoms are infrequent. This study aims to explore the potential of deep transfer learning with ImageNet deep neural networks (DNNs) to improve the interpretation of short-term ECHOView images for the presence of AF. Methods: Thirty-second ECHOView images, composed of stacked heartbeat amplitudes, were rescaled to fit the input of 18 pretrained ImageNet DNNs with the top layers modified for binary classification (AF, non-AF). Transfer learning provided both retrained DNNs by training only the top layers (513–2048 trainable parameters) and fine-tuned DNNs by slowly training retrained DNNs (0.38–23.48 M parameters). Results: Transfer learning used 13,536 training and 6624 validation samples from the two leads in the IRIDIA-AF Holter ECG database, evenly split between AF and non-AF cases. The top-ranked DNNs evaluated on 11,400 test samples from independent records are the retrained EfficientNetV2B1 (96.3% accuracy with minimal inter-patient (1%) and inter-lead (0.3%) drops), and fine-tuned EfficientNetV2B1 and DenseNet-121, -169, -201 (97.2–97.6% accuracy with inter-patient (1.4–1.6%) and inter-lead (0.5–1.2%) drops). These models can process shorter ECG episodes with a tolerable accuracy drop of up to 0.6% for 20 s and 4–15% for 10 s. Case studies present the GradCAM heatmaps of retrained EfficientNetV2B1 overlaid on raw ECG and ECHOView images to illustrate model interpretability. Conclusions: In an extended deep transfer learning study, we validate that ImageNet DNNs applied to short-term ECHOView images through retraining and fine-tuning can significantly enhance automated AF diagnoses. GradCAM heatmaps provide meaningful model interpretability, highlighting ECG regions of interest aligned with cardiologist focus.

OBJECTIVE: To evaluate the effects of aliskiren on blood pressure and myocardial functionassessed by global longitudinal strain in patients with uncontrolled arterial hypertension. PATIENTS AND METHODS: Forty-fi ve patients were included in the study (29 males, 16 females, mean age 58.7 ± 12.4 years) with BP > 140/90 mmHg despite treatment with combined antihypertensive therapy and echocardiographic data for diastolic dysfunction: Е/Е’ratio ≤ 8, Е/А ratio < 0.8, deceleration time (DT) > 200 msec. Aliskiren (2 х 150 mg per day) was added to the previous therapy. The follow-up period was 1 year, including monthly clinical visits. Echocardiographic assessment of the left ventricular function by longitudinal strain and Doppler analysis of the trans-mitral blood flow was performed at months 1, 6, 12. RESULTS: The baseline systolic and diastolic blood pressures scores were 153.4 ± 14.4/99.2 ± 6.7 mmHg and 157.6 ± 12.5/97.3 ± 8.2 mmHg for males and females, respectively. The systolic and diastolic values at 1 month were 131.7 ± 7.4/83.6 ± 5.2 mmHg for males and 132.4 ± 5.3/81.8 ± 6.9 mmHg for females (р < 0.05 vs. baseline). The baseline Е/Е’ was 6.5 ± 0.9, Е/А - 0.6 ± 001, DT - 258 ± 32.7 msec. These indicators at month 12 were as follows: Е/Е’ - 7.0 ± 0.64, Е/А - 0.7 ± 0.05, DT - 239 ± 16.5 msec, р = NS. Baseline global longitudinal strain in males was -10.4 ± 0.7% and -11.0 ± 0.9% in females and at month 12 - 16.3 ± 0.9% and -17.5 ± 0.7% for males and females, respectively, р < 0.05. For the period of follow-up no adverse effects due to aliskiren treatment were registered. CONCLUSIONS: Adding aliskiren to combined antihypertensive therapy leads to significant improvement of hypertension control and myocardial function assessed by global longitudinal strain.