Search

Early detection is critical to achieving improved treatment outcomes for child patients with congenital heart diseases (CHDs). Therefore, developing effective CHD detection techniques using low-cost and non-invasive pediatric electrocardiogram are highly desirable. We propose a deep learning approach for CHD detection, CHDdECG, which automatically extracts features from pediatric electrocardiogram and wavelet transformation characteristics, and integrates them with key human-concept features. Developed on 65,869 cases, CHDdECG achieved ROC-AUC of 0.915 and specificity of 0.881 on a real-world test set covering 12,000 cases. Additionally, on two external test sets with 7137 and 8121 cases, the overall ROC-AUC were 0.917 and 0.907 while specificities were 0.937 and 0.907. Notably, CHDdECG surpassed cardiologists in CHD detection performance comparison, and feature importance scores suggested greater influence of automatically extracted electrocardiogram features on CHD detection compared with human-concept features, implying that CHDdECG may grasp some knowledge beyond human cognition. Our study directly impacts CHD detection with pediatric electrocardiogram and demonstrates the potential of pediatric electrocardiogram for broader benefits. Congenital heart disease is life threatening, and its screening is complex and costly. Here, authors use AI to detect the disease based on pediatric electrocardiogram, suggesting superior performance over cardiologists. [ABSTRACT FROM AUTHOR]

The hydrogen energy generated by the electrocatalytic water splitting reaction has been established as a renewable and clean energy carrier with ultra‐high energy density, which can well make up for shortcomings of conventional renewable energy sources, such as geographical limitations, climatic dependence, and energy wastage. Notably, the introduction of electrocatalysts can enhance the efficiency of the water splitting process to generate hydrogen. Particularly, the heterostructure electrocatalysts constructed by coupling multiple components (or phases) have emerged as the most promising option for water splitting due to the well‐known electronic and synergistic effects. The existing reviews on interface engineering for electrocatalyst design mostly focus on the relationship between the heterostructures and specific electrocatalytic reactions. However, a comprehensive overview of the integration of model building, directional synthesis, and electrocatalytic mechanism has been rarely reported. To this end, in this review, the development of heterostructure catalysts is systematically introduced from the perspective of interface classification, interface growth and synthesis, and regulation of electrocatalytic performance based on the interfacial microenvironment (bonding, electronic configuration, lattice strain, etc.), thereby offering useful insights on the design and construction of interfacial models. Besides, combined with the current development and applications of interface engineering strategies, the challenges of future heterostructure catalysts are discussed and relevant solutions are proposed. Overall, this review can serve as a useful theoretical reference for the integration of interfacial model building, directional synthesis, and electrocatalytic mechanism, which can further promote the development of hydrogen production technologies with low energy consumption and high yield. [ABSTRACT FROM AUTHOR]