OBJECTIVES Our objectives were to identify the risk factors for postoperative complications after paediatric cardiac surgery, develop a tool for predicting postoperative complications and compare it with other risk adjustment tools of congenital heart disease. METHODS A total of 2308 paediatric patients who had undergone cardiac surgeries with cardiopulmonary bypass support in a single centre were included in this study. A univariate analysis was performed to determine the association between perioperative variables and postoperative complications. Statistically significant variables were integrated into a synthetic minority oversampling technique-based XGBoost model which is an implementation of gradient boosted decision trees designed for speed and performance. The 7 traditional risk assessment tools used to generate the logistic regression model as the benchmark in the evaluation included the Aristotle Basic score and category, Risk Adjustment for Congenital Heart Surgery (RACHS-1), Society of Thoracic Surgeons–European Association for Cardio-Thoracic Surgery (STS-EACTS) mortality score and category and STS morbidity score and category. RESULTS Our XGBoost prediction model showed the best prediction performance (area under the receiver operating characteristic curve = 0.82) when compared with these risk adjustment models. However, all of these models exhibited a relatively lower sensitivity due to imbalanced classes. The sensitivity of our optimization approach (synthetic minority oversampling technique-based XGBoost) was 0.74, which was significantly higher than the average sensitivity of the traditional models of 0.26. Furthermore, the postoperative length of hospital stay, length of cardiac intensive care unit stay and length of mechanical ventilation duration were significantly increased for patients who experienced postoperative complications. CONCLUSIONS Postoperative complications of paediatric cardiac surgery can be predicted based on perioperative data using our synthetic minority oversampling technique-based XGBoost model before deleterious outcomes ensue.

Background In the past decades, birdwatching as a hobby developed rapidly and produced ample scientific records that have aided conservation efforts. Therefore, it is increasingly attractive to promote avian research by providing data from birdwatching. Methods We compared records from 16 years of community birdwatching and a 1-year formalized bird monitoring in Suzhou, China to study the similarities and differences between the two monitoring methods. Results We showed that within the 325 bird species recorded by the two methods, an annual average of 108 species were documented by community science and 223 bird species were recorded by 1-year formalized monitoring. Measured by the number of bird species recorded per survey trip, the bird monitoring activity of community birdwatchers was significantly lower. Furthermore, the monitoring intensity of community birdwatching measured as the average survey trips per site each survey year was also lower than that of formalized bird monitoring. In addition, community birdwatchers preferred urban landscapes to rural areas. Conclusions Community birdwatching could record the majority of local birds and complements the professional surveys in avian research. Well designed and coordinated community science can be used to expand the knowledge about avian distribution and population dynamics. These findings are critical for the development of conservation science with regard to community involvement.

No abstract

Contexts The invasion of fast growing Phyllostachys edulis (Moso bamboo) into forest is likely further favored by climate change, creating more transitional regions within forests. Such forest-bamboo transitional zones provide windows to look at ecological processes driving bamboo’s interaction with competing species across space. Objectives We tested the hypothesis that spatial patterns at scales of ecotone and individual stems can inform bamboo’s invasive spread and its competitive engulfing strategy, with the allocation of biomass and resources within a bamboo colony being a key life-history strategy to facilitate its spatial spread. Methods We used remote sensing imagery and field survey data to analyze the dynamics of bamboo-tree transitional boundaries in Tianmu Mountain Nature Reserve (TMNR) of southeastern China. We evaluated bamboo’s invasive spread and its allocation of resources along the transitional gradient. Results Both remote sensing and field data showed bamboo recovery and advancement into tree territories after the extensive logging of bamboo but with a slower spread compared to historical records. The spatial distributions of bamboo and tree stems were not random at their transitional interfaces and were affected by competition. Successful invasion of bamboo required close coordination between stems and rhizomes within a colony, as they served different functions in clonal integration. Conclusions Our study initiates a mechanistic, scale-dependent analysis of bamboo invasion strategies, which provides insights on how to accurately predict future bamboo distributions under climate change accounting for interspecific competition and bamboo’s clonal integration of resources.

Although Generative Adversarial Network(GAN) has obtained remarkable achievements in the image analysis and generation, its exploration in GAN-based curve clustering is still limited. The latent space of curve data is often used for clustering. However, the distance geometry in the latent space does not reflect the inherent clusters. In this paper, we propose CPGAN(Curve Clustering Architecture based on Projected Latent Vector of Generative Adversarial Network) for the clustering of curve dataset. Firstly, a novel GAN network structure, which utilizes a projector P(composed of the transposed convolutional network) to reconstruct the latent space of curve data, is proposed. CPGAN utilizes the concatenation of discrete code and Gaussian noise as a latent vector to preserve the implicit signal and structure of the cluster. Secondly, the loss function with two regularizations for CPGAN is proposed to guarantee the robustness and effectiveness of the model. Based on these, the jointly trained projector P is used to participate in the clustering process, while the generator can be used in the generating process. Finally, the spectral dataset from the LAMOST survey, the UCI dataset, and the UCR dataset are used as experimental data to evaluate clustering performance, the robustness of CPGAN, and further application on anomalous detection. CPGAN presents higher results than other methods.