Background: Population‐based studies suggest that genetic factors contribute to sudden cardiac death ( SCD ). Methods and Results: In the first part of the present study (Diagnostic Data Influence on Disease Management and Relation of Genetic Polymorphisms to Ventricular Tachy‐arrhythmia in ICD Patients [DISCOVERY] trial) Cox regression was done to determine if 7 single‐nucleotide polymorphisms ( SNP s) in 3 genes coding G‐protein subunits ( GNB 3, GNAQ , GNAS ) were associated with ventricular tachyarrhythmia ( VT ) in 1145 patients receiving an implantable cardioverter‐defibrillator ( ICD ). In the second part of the study, SNP s significantly associated with VT were further investigated in 1335 subjects from the Oregon SUDS , a community‐based study analyzing causes of SCD . In the DISCOVERY trial, genotypes of 2 SNP s in the GNAS gene were nominally significant in the prospective screening and significantly associated with VT when viewed as recessive traits in post hoc analyses ( TT vs CC / CT in c.393C>T: HR 1.42 [ CI 1.11‐1.80], P =0.005; TT vs CC / CT in c.2273C>T: HR 1.57 [ CI 1.18‐2.09], P =0.002). TT genotype in either SNP was associated with a HR of 1.58 ( CI 1.26‐1.99) ( P =0.0001). In the Oregon SUDS cohort significant evidence for association with SCD was observed for GNAS c.393C>T under the additive ( P =0.039, OR =1.21 [ CI 1.05‐1.45]) and recessive ( P =0.01, OR =1.52 [ CI 1.10‐2.13]) genetic models. Conclusions: GNAS harbors 2 SNP s that were associated with an increased risk for VT in ICD patients, of which 1 was successfully replicated in a community‐based population of SCD cases. To the best of our knowledge, this is the first example of a gene variant identified by ICD VT monitoring as a surrogate parameter for SCD and also confirmed in the general population. Clinical Trial Registration: URL : http://www.clinicaltrials.gov . Unique identifier: NCT 00478933.
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.
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.
Leadless pacing can be done by transmitting energy by an alternating magnetic field from a subcutaneous transmitter unit (TU) to an endocardial receiver unit (RU). Safety and energy consumption are key issues that determine the clinical feasibility of this new technique. The aims of the study were (i) to evaluate the stimulation characteristics of the non-rectangular pacing pulses induced by the alternating magnetic field, (ii) to determine the extent and impact of RU movement caused by the beating heart, and (iii) to evaluate the influence of the relative position between TU and RU on pacing efficiency and energy consumption. In the first step pacing efficiency and energy consumption for predefined positions were determined by bench testing. Subsequently, in a goat at five different ventricular sites (three in the right ventricle, two in the left ventricle) pacing thresholds using non-rectangular induction pulses were compared with conventional pulses. Relative position, defined by parallel distance, radial distance, and angulation between TU and RU, were determined in vivo by X-ray and an inclination angle measurement system. Bench testing showed that by magnetic induction for every alignment between TU and RU appropriate pulses can be produced up to a distance of 100 mm. In the animal experiment pacing thresholds were similar for non-rectangular pulses as compared with conventional pulse shapes. In all five positions with distances between 62 and 102 mm effective pacing was obtained in vivo. Variations in distance, displacement and angle caused by the beating heart did not cause loss of capture. At pacing threshold energy consumptions between 0.28 and 5.36 mJ were measured. Major determinants of energy consumption were distance and pacing threshold. For any given RU position up to a distance of 100 mm reliable pacing using induction can be obtained. In anatomically crucial distances, up to 60 mm energy consumption is within a reasonable range.
1 September 2005 in Herzschrittmachertherapie + Elektrophysiologie