Explore the vast range of titles available.

Artificial intelligence (AI) represents a rapidly developing field. Its use can improve diagnosis and therapy in many areas of medicine. Despite this enormous progress, many physicians perceive it as a black box and are skeptical about it. This review will present the basics of machine learning. Different classifications of artificial intelligence, such as supervised versus unsupervised and discriminative versus generative AI, are given. Analogies to human intelligence are discussed as far as algorithms are oriented toward it. In the second step, the most common models like random forest, k‐means clustering, convolutional neural network, and transformers will be presented in a way that the underlying idea can be understood. Corresponding medical applications in cardiovascular medicine will be named for all models, respectively. The overview is intended to show that the term artificial intelligence covers a wide range of different concepts. It should help physicians understand the principles of AI to make up one's minds about its application in cardiology. It should also enable them to evaluate results obtained with AI's help critically. Artificial intelligence (AI) represents a rapidly developing field. This review will present the basics of AI. Different classifications of AI, like supervised versus unsupervised and discriminative versus generative AI, are given. Analogies to human intelligence are discussed as far as algorithms are oriented toward it. The second step will present the most common models like random forest, k‐means clustering, convolutional neural networks, and transformers to understand the underlying ideas. Corresponding medical applications in cardiovascular medicine will be named for all models.

Background Pulmonary vein isolation (PVI) is recommended to treat paroxysmal and persistent atrial fibrillation (AF). This analysis aimed to assess the hospital efficiency of single-shot cryoballoon ablation (CBA) and point-by-point radiofrequency ablation (RFA). Methods The discrete event simulation used PVI procedure times from the FREEZE Cohort study to establish the electrophysiology (EP) lab occupancy time. 1000 EP lab days were simulated according to an illustrative German hospital, including 3 PVI cases per day using CBA at one site and RFA at the other. Results The analysis included 1560 CBA patients and 1344 RFA patients from the FREEZE Cohort. Some baseline patients’ characteristics were different between groups (age, AF type, and some concomitant diseases), without being statistically associated to ablation procedure time. Mean procedure time was 122.2 ± 39.4 min for CBA and 160.3 ± 53.5 min for RFA ( p  < 0.0001). RFA was associated with a more than five-fold increase of cumulative overtime compared to CBA over the simulated period (1285 h with RFA and 253 h with CBA). 70.7% of RFA lab days included overtime versus 25.7% for CBA. CBA was associated with more days with an additional hour at the end of the EP lab shift compared to RFA (47.8% vs 11.5% days with one hour left, respectively). Conclusion CBA is faster and more predictable than point-by-point RFA, and enables improvements in EP lab efficiency, including: fewer cumulative overtime hours, more days where overtime is avoided and more days with remaining time for the staff or for any EP lab usage. Clinical trial registration NCT01360008 (first registration 25/05/2011).

IntroductionCatheter ablation of focal atrial tachycardia (FAT) can be a challenging procedure and results have been rarely described. The purpose of this study was to determine the characteristics and results of FAT ablation in the large cohort of the German Ablation Registry.MethodsThe German Ablation Registry is a nationwide prospective multicenter database including 12566 patients who underwent an ablation procedure between 2007 and 2010. Among them 431 (3.4%) underwent an FAT ablation and 413 patients with documented locations were analyzed. Patients were divided into three groups according to the FAT location: biatrial (BiA, n = 31, 7.5%), left atrial (LA, n = 110, 26.5%), and right atrial (RA, n = 272, 66%).ResultsAcute success rate was 84% (68 vs. 85 vs. 85% in biA, LA, and RA, respectively, p = 0.038). 4.8% of patients had an early recurrence during hospitalization, most in biatrial location (p < 0.001). No major acute complication occurred. At 12 months, 81% were asymptomatic or improved. The incidence of major adverse cardiovascular and cerebrovascular events (MACCE) was 3.7%. Arrhythmia freedom without antiarrhythmic drugs was 58% and was lower in biA (34 vs. 56% in LA vs. 62% in RA, p = 0.019). Early recurrence during hospitalization was an outstanding predictive factor for recurrence during follow-up.ConclusionIn this large patient population, FAT ablation had a relatively high acute success rate with a low complication rate. During follow-up, the recurrence rate was high, particularly in biatrial location. This was frequently predicted by an early recurrence during hospitalization.

In patients with atrial fibrillation, catheter ablation is suggested to reduce the mortality rate and is thus frequently performed. However, peri- and postprocedural thromboembolic complications as well as high recurrence rates of atrial fibrillation limit its advantages and require concomitant anticoagulation. With the advent of novel oral anticoagulants (NOACs), fixed dosing without routine laboratory monitoring became feasible. Nevertheless, several factors are associated with either an overdose or an insufficient drug activity of NOACs. We report on a patient with atrial fibrillation undergoing catheter ablation and cardioversion suffering from ischemic stroke despite being under oral anticoagulation. It turned out that the drug activity of the NOACs used was repeatedly insufficient in spite of regular intake and adequate dosing. In sum, drug activity controls should be taken into consideration in patients with thrombotic events despite oral anticoagulation with NOACs.

Pulmonary edema and its association with low flow times has been observed in postcardiac arrest patients. However, diagnosis of distinct types of lung pathology is difficult.The aim of this study was to investigate pulmonary edema by transpulmonary thermodilution (TPTD) after out-of-hospital cardiac arrest (OHCA), and the correlation to downtimes. In this retrospective single-center study consecutive patients with return of spontaneous circulation (ROSC) following OHCA, age ≥ 18, and applied TPTD were enrolled. According to downtimes, patients were divided into a short and a long no-flow-time group, and data of TPTD were analysed. We identified 45 patients (n = 25 short no-flow time; n = 20 long no-flow time) who met the inclusion criteria. 24 h after ROSC, the extra vascular lung water index (EVLWI) was found to be lower in the group with short no-flow time compared to the group with long no-flow time (10.7 ± 3.5 ml/kg vs. 12.8 ± 3.9 ml/kg; p = 0.08) and remained at a similar level 48 h (10.9 ± 4.3 ml/kg vs. 12.9 ± 4.9 ml/kg; p = 0.25) and 72 h (11.1 ± 5.0 ml/kg vs. 13.9 ± 7.7 ml/kg; p = 0.27) post-ROSC. We found a statistically significant and moderate correlation between no-flow duration and EVLWI 48 h (r = 0.51; p = 0.002) and 72 h (r = 0.54; p = 0.004) post-ROSC. Pulmonary vascular permeability index (PVPI) was not correlated with downtimes. Our observation underlines the presence of cardiac arrest-related lung edema by determination of EVLWI. The duration of no-flow times is a relevant factor for increased extravascular lung water index.

Background Although aortic stenosis (AS) is the most common valvular heart disease in the western world, many affected patients remain undiagnosed. Auscultation is a readily available screening tool for AS. However, it requires a high level of professional expertise. Hypothesis An AI algorithm can detect AS using audio files with the same accuracy as experienced cardiologists. Methods A deep neural network (DNN) was trained by preprocessed audio files of 100 patients with AS and 100 controls. The DNN's performance was evaluated with a test data set of 40 patients. The primary outcome measures were sensitivity, specificity, and F1‐score. Results of the DNN were compared with the performance of cardiologists, residents, and medical students. Results Eighteen percent of patients without AS and 22% of patients with AS showed an additional moderate or severe mitral regurgitation. The DNN showed a sensitivity of 0.90 (0.81–0.99), a specificity of 1, and an F1‐score of 0.95 (0.89–1.0) for the detection of AS. In comparison, we calculated an F1‐score of 0.94 (0.86–1.0) for cardiologists, 0.88 (0.78–0.98) for residents, and 0.88 (0.78–0.98) for students. Conclusions The present study shows that deep learning‐guided auscultation predicts significant AS with similar accuracy as cardiologists. The results of this pilot study suggest that AI‐assisted auscultation may help general practitioners without special cardiology training in daily practice.

Background The incidence of recognized cardiopulmonary cement embolism in the context of percutaneous vertebroplasty varies between 0% and 23%. In most cases, only small fragments embolize in the pulmonary arteries or the right heart cavities. The latter can cause potential harm by right ventricular perforation. Case summary A 57-year-old patient was admitted to our department of cardiology due to exertional dyspnoea and chest pain. In the course of further diagnostic tests, a huge cement embolus was accidentally discovered in the right ventricle. The unusual size and length and the threat of ventricular perforation make this case so unique. Discussion Large cement embolisms in kyphoplasty settings are possible and associated with the risk of fulminant complications.

Since its introduction in clinical cardiology, several studies have shown the superiority of coronary stent implantation as compared to conventional angioplasty. However, restenosis still remains a major drawback of this new technique. Basic research in animal models could identify stent-related factors like stent-material and stent-design as major determinants of intima proliferation. Since materials with good biocompatibility often have unsuitable mechanical properties and vice versa, the concept of stent coating has been developed to allow the combination of favorable characteristics from different materials. In general, passive coatings, which only serve as a barrier between the stainless steel and the tissue, and active coatings, which directly interfere with the process of intima proliferation have been identified. Currently there are several passive coatings commercially available with good results in animal models and preliminary reports from clinical studies. As any surface induces some kind of tissue reaction promoting restenosis, an active stent coating with antiproliferative drugs has been proposed. However, while animal studies revealed convincing results, preliminary clinical studies not only showed active stent coating effective in preventing restenosis, but also demonstrated the potential risks of this new approach. Although this technique may harbor some specific risks, with the introduction of stent coating a new chapter of interventional cardiology has been flipped open.