Artificial intelligence has been able to automatically learn and judge large-scale data to some extent. Based on database of a large amount of burn data and in-depth learning, artificial intelligence can assist burn surgeons to evaluate burn surface, diagnose burn depth, guide fluid supply during shock stage, and predict prognosis, with high accuracy. With the development of technology, artificial intelligence can provide more accurate information for burn surgeons to make clinical diagnosis and treatment strategies.

The paraventricular thalamic nucleus (PVT) is a key nucleus involved in wakefulness. PVT plays an important role in normal sleep-wake regulation, but its role may vary during anesthesia depending on the stage of anesthesia. This article will review the role of PVT in sleep and anesthesia based on its wakefulness function neural pathways.

【Objective】 To analyze the basic characteristics of whole blood donors from blood stations before and after the outbreak of COVID-19. 【Methods】 After excluding invalid data, data related to the basic characteristics of whole blood donors collected from 26 blood stations in China during 2018 to 2021 were statistically analyzed, including the trend of total whole blood donors, the number of repeated blood donors, the frequency of blood donation, the average age of donors and the recruitment of first-time blood donors. 【Results】 Affected by the epidemic, 8 out of 14 indicators were with large variations, accounting for 57%. The overall growth rate of total whole blood donors during the epidemic was higher than before the epidemic (P<0.05).The number of repeated blood donors has shown an increased trend, with a higher number during the epidemic than before (P<0.05). The frequency of blood donation was lower during the epidemic than before(P<0.05).Average ages of blood donors and female blood donors fluctuated widely during the epidemic, both higher than those before the epidemic(P<0.05).The donation rate of first-time blood donors <25 years old and ≥25 years old varied widely and irregularly during the epidemic (both P<0.05). The percentage of first-time blood donors fluctuated irregularly during the epidemic, with overall percentage lower than that before the epidemic(P<0.05). 【Conclusion】 Whole blood donors from 26 blood stations increased after the outbreak of COVID-19, and some indicators in certain areas showed significant fluctuations during the epidemic.

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

【Objective】 To learn the production efficient of platelet components among prefecture-level blood stations in China, to provide supporting data for those blood stations to optimize the production mode of platelet components and continuously improve production efficiency and supply capacity. 【Methods】 The data from 2017 to 2020 was obtained from 24 prefecture-level blood stations who were the members of the practice comparison network for blood institutes in China. The collection units of apheresis platelets, the number of dual-collections of apheresis platelets and plasma, the average apheresis units of one platelet apheresis procedure, the discarded rate of apheresis platelets, the amount of expired apheresis platelets and the amount of apheresis platelets issued were collected. For concentrated platelets, the prepared amount of platelet concentrates and the amount of expired platelet concentrates were collected; both the quantity of qualified and issued concentrated platelets were submitted for statistical analysis.The total output and efficiency of platelet components were calculated based on the collected data. 【Results】 The average annual growth rate of apheresis platelets collection in 24 prefecture-level blood stations was 12.23%, accounting for 99.80% of the total platelet output; the average collection unit of one platelets apheresis procedure was 1.75; from 2019 to 2020, only 5 blood stations performed dual-collection of platelet and plasma during one apheresis procedure; the discarded rate of apheresis platelets was 0.28%, of which 0.007% was due to expiration. A total of 1 621.2 therapeutic units of concentrated platelets were prepared, and 13.03% of them was discarded due to the expiration. The production efficiency of platelet components was 97.56%, of which the production efficiency of apheresis platelets was 97.61% and the production efficiency of concentrated platelets was 74.43%. 【Conclusion】 There are large regional differences in the supply capacity of platelet components in prefecture-level blood stations. Apheresis platelets are the main resource of platelet components product, and the collection capacity is increasing over the years with the characteristics of high production efficiency and low expiration scrapping rate. However, the preparation of concentrated platelets are still limited with relatively low production and high expiration discarded rate.

【Objective】 To understand the current situation of blood components distribution in domestic prefecture-level blood stations through analyzing the components distribution data of 24 prefecture-level blood stations in China. 【Methods】 The data of components distribution of 24 blood stations from 2017 to 2020 as well as the data of blood deployment of 24 blood stations from 2019 to 2020 were collected and analyzed. 【Results】 From 2017 to 2020, positive annual growth in red blood cells, plasma and cryoprecipitate was observed in 22, 19 and 15 out of the 24 blood stations, and the annual growth median rate of above three components was 5.24%, 3.80% and 3.25%, respectively. Among the 24 prefecture-level blood stations, 23 carried out the preparation of cryoprecipitate. 【Conclusion】 The distribution of red blood cells, cryoprecipitate and plasma in prefecture-level blood stations is increasing year by year. However, there is a overstock of plasma, and most blood stations need blood employment.