Detect Depression from Social Networks with Sentiment Knowledge Sharing (preprint)

Social network plays an important role in propagating people's viewpoints, emotions, thoughts, and fears. Notably, following lockdown periods during the COVID-19 pandemic, the issue of depression has garnered increasing attention, with a significant portion of individuals resorting to social networks as an outlet for expressing emotions. Using deep learning techniques to discern potential signs of depression from social network messages facilitates the early identification of mental health conditions. Current efforts in detecting depression through social networks typically rely solely on analyzing the textual content, overlooking other potential information. In this work, we conduct a thorough investigation that unveils a strong correlation between depression and negative emotional states. The integration of such associations as external knowledge can provide valuable insights for detecting depression. Accordingly, we propose a multi-task training framework, DeSK, which utilizes shared sentiment knowledge to enhance the efficacy of depression detection. Experiments conducted on both Chinese and English datasets demonstrate the cross-lingual effectiveness of DeSK.

[Exploration and example interpretation of real-world herbal prescription classification based on similarity matching algorithm].

In observational studies, herbal prescriptions are usually studied in the form of "similar prescriptions". At present, the classification of prescriptions is mainly based on clinical experience judgment, but there are some problems in manual judgment, such as lack of unified criteria, labor consumption, and difficulty in verification. In the construction of a database of integrated traditional Chinese and western medicine for the treatment of coronavirus disease 2019(COVID-19), our research group tried to classify real-world herbal prescriptions using a similarity matching algorithm. The main steps include 78 target prescriptions are determined in advance; four levels of importance labeling shall be carried out for the drugs of each target prescription; the combination, format conversion, and standardization of drug names of the prescriptions to be identified in the herbal medicine database; calculate the similarity between the prescriptions to be identified and each target prescription one by one; prescription discrimination is performed based on the preset criteria; remove the name of the prescriptions with "large prescriptions cover the small". Through the similarity matching algorithm, 87.49% of the real prescriptions in the herbal medicine database of this study can be identified, which preliminarily proves that this method can complete the classification of herbal prescriptions. However, this method does not consider the influence of herbal dosage on the results, and there is no recognized standard for the weight of drug importance and criteria, so there are some limitations, which need to be further explored and improved in future research.

E-learners' satisfaction as predictors of online classroom community

Purpose: This study investigates Chinese college students' satisfaction with using e-learning systems and its influences on their sense of online classroom community in synchronous, asynchronous, or a blend of both synchronous and asynchronous online course format during the COVID-19 pandemic. Methods: A total number of 307 college students were recruited with 270 usable responses from a southeastern university in China. E-learner satisfaction measurement and Classroom Community Scale (both with a 5-point Likert-type scale) were used as the instruments to investigate the research questions. Descriptive statistical analysis and multiple regression analysis were conducted in SPSS. Results: Results of the analysis show that Chinese college students' satisfaction of using the e-learning system regarding the learner interface, learning community, content, and personalization positively impacts their sense of online classroom community no matter in synchronous, asynchronous, or a blend of both synchronous and asynchronous online course format. Implications: A well-developed e-learning system would enhance students' sense of online classroom community. Specifically, the user interface, interaction, content arrangement, and personalization should be focused on when developing the e-learning system.

Wildlife-borne microorganisms and strategies to prevent and control emerging infectious diseases

China is one of the countries with the richest wildlife population. The large variety of widely distributed species act as natural or susceptible hosts for numerous infectious diseases. It is estimated that there are more than 1.2 million unknown virus species in China, and there might be 10,000–30,000 unknown bacteria in wild mammals on the Qinghai-Tibet Plateau alone. There are no less than 600,000 species of animal-borne parasites and approximately 2 million species of fungi worldwide. With rapid economic growth and globalization, humans and wildlife interact more frequently, which enhances the probability of wildlife-borne pathogens infecting humans. The occurrence of animal-borne infectious diseases will become the “new normal” we have to face in the future. Therefore, research should be carried out on wildlife-borne microorganisms and the prevention and control of emerging infectious diseases to establish an analytical framework and an evaluation technology system for risk assessment and early warning of potential animal-borne emerging infectious diseases. This will not only improve our understanding of wildlife-borne microbial communities but also enable in-depth analysis, discovery, early warning, and even prediction of major animal-borne emerging infectious diseases that might occur in the future. Furthermore, this research will reduce response times, minimize the social and economic impact and losses, enable interventions related to the emergence or spread of the disease as early as possible, and comprehensively improve our management of infectious disease outbreaks.

Molecular PET/CT Profiling of ACE2 Expression In Vivo: Implications for Infection and Outcome from SARS-CoV-2.

Rapid progress has been made to identify and study the causative agent leading to coronavirus disease 2019 (COVID-19) but many questions including who is most susceptible and what determines severity remain unanswered. Angiotensin-converting enzyme 2 (ACE2) is a key factor in the infection process of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). In this study, molecularly specific positron emission tomography imaging agents for targeting ACE2 are first developed, and these novel agents are evaluated in vitro, in preclinical model systems, and in a first-in-human translational ACE2 imaging of healthy volunteers and a SARS-CoV-2 recovered patient (NCT04422457). ACE2 expression levels in different organs in live subjects are quantitatively delineated and observable differences are measured in the patient recovered from COVID-19. Surprising sites of uptake in the breast, reproductive system and very low uptake in pulmonary tissues are reported. This novel method can add a unique tool to facilitate SARS-CoV-2 related research and improve understanding of this enigmatic disease. Molecular imaging provides quantitative annotation of ACE2, the SARS-CoV-2 entry receptor, to noninvasively monitor organs impacted by the COVID-19.

Innocence in the shadow of COVID-19: Plea decision making during a pandemic.

Over 95% of criminal convictions in the United States are the result of guilty pleas. Consequently, it is critical that we ensure the process of pleading guilty is as free of coercion as possible. Yet, research has indicated that incarcerating defendants to await trial could have an undue influence on their decision to plead guilty. The current research employed a novel computer simulation to examine the impact of the COVID-19 pandemic on plea decision making among the innocent and the guilty when faced with potential pretrial detention. While presenting COVID-related information to participants increased both true and false guilty pleas, further analyses indicated that concerns about COVID-19 weighed more heavily on the innocent than the guilty. These findings illustrate the negative impact a pandemic could have in combination with a system of pleas that often allows prosecutors to provide defendants with just one guaranteed respite from jail-a guilty plea. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

AI-assisted quantitative lung CT evaluation following umbilical cord mesenchymal stem cell treatment in severe COVID-19 patients (preprint)

Background: The COVID-19 has high transmission and mortality. Previous studies support the efficacy and safety of mesenchymal stem cells (MSCs) in the treatment of lung injury. In this study, We aimed to evaluate the CT changes of lung lesions in severe COVID-19 patients treated with umbilical cord mesenchymal stem cells (UC-MSCs) by using AI-assisted quantification method.Methods46 patients with severe COVID-19 from March 5 to April 1, 2020 were selected by single-blind, non-randomized controlled clinical study and divided into three groups: 11 cases in UC-MSCs treatment group 1 (MSC-1, with cells infusion once), 26 cases in UC-MSCs treatment group 2 (MSC-2, with cells infusion twice or three times), and 9 cases in control group with routine treatment. Repeated measure ANOVA was used to compare the effects of treatment factors on chest CT parameters of COVID-19 patients between control and experimental groups, and pairwise comparison using LSD test.FindingsThe differences between the percentage of GGO in total lung or the percentage of total lung infection volume on day 0 and that in day 60 as well as in day 90 were statistically significant among the three groups. The P values were 0.034 and 0.018 respectively. Pairwise comparison results showed that the percentage difference of the whole lung GGO and total lung infection volume in MSC-1 group was smaller than that in control group and MSC-2 group respectively, but there was no statistical difference between control group and MSC-2 group. The distribution characteristics and other CT parameters post-proceeded by AI software were not significantly different among the three groups. There were no serious adverse events related to stem cell infusion in all treated patients.InterpretationUC-MSC infusion is safe for the treatment of severe COVID-19 patients. The absorption of lung lesions at 60 days and 90 days after UC-MSC infusion once was more obvious than that in the control group. AI quantification of lung lesions is more suitable for comparative studies before and after treatment.