Search

Abstract The increasing prevalence of heart failure (HF) in ageing populations drives demand for echocardiography (echo). There is a worldwide shortage of trained sonographers and long waiting times for expert echo. We hypothesised that artificial intelligence (AI)-enhanced point-of-care echo can enable HF screening by novices. The primary endpoint was the accuracy of AI-enhanced novice pathway in detecting reduced LV ejection fraction (LVEF)

Abstract Background Heart failure (HF) is a type of cardiovascular disease caused by abnormal cardiac structure and function. Early screening of HF has important implication for treatment in a timely manner. Heart sound (HS) conveys relevant information related to HF; this study is therefore based on the analysis of HS signals. The objective is to develop an efficient tool to identify subjects of normal, HF with preserved ejection fraction and HF with reduced ejection fraction automatically. Methods We proposed a novel HF screening framework based on gated recurrent unit (GRU) model in this study. The logistic regression-based hidden semi-Markov model was adopted to segment HS frames. Normalized frames were taken as the input of the proposed model which can automatically learn the deep features and complete the HF screening without de-nosing and hand-crafted feature extraction. Results To evaluate the performance of proposed model, three methods are used for comparison. The results show that the GRU model gives a satisfactory performance with average accuracy of 98.82%, which is better than other comparison models. Conclusion The proposed GRU model can learn features from HS directly, which means it can be independent of expert knowledge. In addition, the good performance demonstrates the effectiveness of HS analysis for HF early screening.

Background: Heart failure (HF) is a type of cardiovascular disease caused by abnormal cardiac structure and function. Early screening of HF has important implication for treatment in a timely manner. Heart sound (HS) conveys relevant information related to HF; this study is therefore based on the analysis of HS signals. The objective is to develop an efficient tool to identify subjects of normal, HF with preserved ejection fraction and HF with reduced ejection fraction automatically.Methods: We proposed a novel HF screening framework based on gated recurrent unit (GRU) model in this study. The logistic regression-based hidden semi-Markov model was adopted to segment HS frames. Normalized frames were taken as the input of the proposed model which can automatically learn the deep features and complete the HF screening without de-nosing and hand-crafted feature extraction.Results: To evaluate the performance of proposed model, three methods are used for comparison. The results show that the GRU model gives a satisfactory performance with average accuracy of 98.82%, which is better than other comparison models.Conclusion: The proposed GRU model can learn features from HS directly, which means it can be independent of expert knowledge. In addition, the good performance demonstrates the effectiveness of HS analysis for HF early screening. [ABSTRACT FROM AUTHOR]

Aims To evaluate the accuracy and cost-effectiveness of different screening strategies to identify systolic and/or diastolic asymptomatic LV dysfunction (ALVD), as well as pre-clinical (stage B) heart failure (HF), in a community of elderly subjects in Italy. Methods and results A sample of 1452 subjects aged 65–84 years were chosen from the original cohort of 2001 randomly selected residents of the Lazio Region (Italy), as a part of the PREDICTOR survey. All subjects underwent physical examination, biochemistry/NT-proBNP assessment, 12-lead ECG, and Doppler transthoracic echocardiography (TE). Five strategies were evaluated including ECG, NT-proBNP, TE, and their combinations. Subjects older than 75 years, and with at least two additional risk factors, were defined as being high-risk for HF (435), whereas the remaining 1017 were defined at low risk. Screening characteristics and cost-effectiveness (cost per case) of the five strategies to predict systolic (EF <50% ) or diastolic ALVD and pre-clinical HF (stage B) were compared. NT-proBNP was the most accurate and cost-effective screening strategy to identify systolic and moderate to severe diastolic LV dysfunction without a difference between the high-risk and low-risk groups. Adding ECG to the NT-proBNP assessment did not improve the detection of pre-clinical LV dysfunction. TE-based screening was the least cost-effective strategy. In fact, all screening strategies were inadequate to identify stage B HF. Conclusions In a community of elderly people, NT-proBNP is the most accurate and cost- effective pre-screening strategy to identify systolic and moderate to severe diastolic LV dysfunction. [ABSTRACT FROM AUTHOR]

Left ventricular dilatation (LVD) and left ventricular hypertrophy (LVH) are risk factors for heart failure, and their detection improves heart failure screening. This study aimed to investigate the ability of deep learning to detect LVD and LVH from a 12-lead electrocardiogram (ECG). Using ECG and echocardiographic data, we developed deep learning and machine learning models to detect LVD and LVH. We also examined conventional ECG criteria for the diagnosis of LVH. We calculated the area under the receiver operating characteristic (AUROC) curve, sensitivity, specificity, and accuracy of each model and compared the performance of the models. We analyzed data for 18,954 patients (mean age (standard deviation): 64.2 (16.5) years, men: 56.7%). For the detection of LVD, the value (95% confidence interval) of the AUROC was 0.810 (0.801-0.819) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods (P < 0.001). The AUROCs for the logistic regression and random forest methods (machine learning models) were 0.770 (0.761-0.779) and 0.757 (0.747-0.767), respectively. For the detection of LVH, the AUROC was 0.784 (0.777-0.791) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods and conventional ECG criteria (P < 0.001). The AUROCs for the logistic regression and random forest methods were 0.758 (0.751-0.765) and 0.716 (0.708-0.724), respectively. This study suggests that deep learning is a useful method to detect LVD and LVH from 12-lead ECGs.