Aspect-Based Sentiment Analysis with Semi-Supervised Approach on Taiwan Social Distancing App User Reviews

Sentiment analysis has a critical role to reveal an opinion in a text-based form. Therefore, we exploit this analysis to discover the sentiment polarity of Taiwan Social Distancing mobile application. This paper proposes a semi-supervised scheme for annotating this mobile application's reviews. The semi-supervised scheme utilized a combination of numeric rating and lexicon-based sentiment. In addition, we also perform the sentiment analysis on an aspect-based level. Based on the experiment, we decide to select three aspects to be analyzed. This paper also evaluates the proposed scheme by implementing bidirectional encoder representations from transformers (BERT) and multilayer perceptron (MLP) as the classification model using the sentiment label of the proposed scheme. The result shows that the annotation of the proposed scheme outperforms the data annotation using counterpart models. © 2023 IEEE.

Image Recognition Based on Deep Learning with Thermal Camera Sensing

As the COVID-19 epidemic spread across the globe, people around the world were advised or mandated to wear masks in public places to prevent its spreading further. In some cases, not wearing a mask could result in a fine. To monitor mask wearing, and to prevent the spread of future epidemics, this study proposes an image recognition system consisting of a camera, an infrared thermal array sensor, and a convolutional neural network trained in mask recognition. The infrared sensor monitors body temperature and displays the results in real-time on a liquid crystal display screen. The proposed system reduces the inefficiency of traditional object detection by providing training data according to the specific needs of the user and by applying You Only Look Once Version 4 (YOLOv4) object detection technology, which experiments show has more efficient training parameters and a higher level of accuracy in object recognition. All datasets are uploaded to the cloud for storage using Google Colaboratory, saving human resources and achieving a high level of efficiency at a low cost. © 2023 CRL Publishing. All rights reserved.

Are there racial disparities in the incidence of venous thromboembolism (VTE) in hospitalized cancer patients with COVID-19?

Background: Both cancer and COVID-19 have been reported to be associated with an increased risk of VTE. Severe disease needing hospitalization is also associated with an increased risk of VTE. There is a paucity of data evaluating the effects of race on this risk, with the limited available data suggesting that such a correlation exists. Given the increased prevalence of comorbidities and risk factors for VTE in African Americans (AA), we sought to evaluate if there are racial disparities in the incidence of VTE in the hospitalized subset of COVID-19 patients with cancer. Method(s): This was a retrospective chart review of unvaccinated cancer patients hospitalized with COVID-19 at a major tertiary health facility. Only cancer patients who were on active systemic chemotherapy were included. The primary study outcomes were development of DVT or PE (VTE) within 30 days of COVID-19 diagnosis. Secondary outcomes included mortality, hospital length of stay, mechanical ventilation, ICU admission, and need for vasopressors. Mean and standard deviation were reported for continuous variables;proportions were reported for categorical variables. To compare between races, the Chi-square test was used for categorical variables and the t-test was used for continuous variables. Multivariable logistic regression was then conducted to assess the relationship between race and selected factors. All statistical tests were 2-sided with an alpha (significance) level of 0.05. Result(s): A total of 73 patients were included in our analysis. The median age of the cohort was 70 years (interquartile range [IQR] 64-79). Gender breakdown: 58.9% males, 41.1 females. 31.5% were Caucasian, 64.4% African American, 1.4% Hispanic, and 2.7% other races/ethnicities. There were 8 DVT/PE patients in the cohort. Of 23 Caucasians in our cohort, 3 (13.0%) had VTE. Of 47 African Americans, 5 (10.6%) had DVT/PE. There was no significant difference between the incidence of VTE and race (p > 0.05). Multivariable logistic regression did not show a significant relationship between race and VTE, controlling for age, ICU stay, intubation, vasopressor use, serum ferritin and serum IL-6 levels. Notably, all patients included in this study were on enoxaparin prophylaxis for VTE. The only variable associated with DVT/PE was age and the presence of hemoglobinopathy. Incidence of VTE was significantly associated with increasing age (p < 0.03) and the presence of hemoglobinopathy (p < 0.01). Hemoglobinopathy was only seen in AA cancer patients with VTE (n = 4), and none in Caucasian patients. Conclusion(s): Contrary to what has been reported in the literature, we did not detect racial disparity in the incidence of VTE in hospitalized cancer patients with COVID 19. Prophylactic anticoagulation likely had a protective effect. However, racial disparity was observed in AA cancer patients with hemoglobinopathy with increased VTE risk despite prophylactic anticoagulation. This warrants further evaluation in future studies.

Supplement of iron abrogates SARS-CoV-2 pseudovirus infection in a 3D model of vascularized organoids

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cause severe outbreak of coronavirus disease 2019 (COVID-19). Even though vaccination, the spread of SARS-CoV-2 is still continue. It is urgent to have a model that can efficiently evaluate potential therapeutic agents to counteract SARS-CoV-2 infection. Iron is an essential molecule for maintaining homeostasis. Supplement of iron significantly to affect virus infection. But the detailed mechanisms of iron on regulating SARS-CoV-2 infection are still unveiled. The three-dimensional (3D) model is a promising system for drug screening and disease progression analysis. Organoid is a typical 3D culture system that recapitulates genetic characteristics and phenotypic features of organs within body. Vasculature is prevalent for all various organs or tumors in the body which transport nutrients, oxygen and metabolites to maintain cellular homeostasis. Thus, we have established a 3D model of vascularized organoid to evaluate the effects of iron on infectivity of SARS-CoV-2 pseudovirus to provide the novel therapeutic strategy in coping SARS-CoV-2 infection. © 2022 IEEE.

Building Capacity for Congenital Heart Patient- Centered Outcomes Research in Under-Represented Minorities

Background: In congenital heart disease, racial and ethnic disparities impact mortality, especially among Blacks and Hispanics in Texas and surrounding regions, however meaningful engagement in ACHD, especially interventional patient-centered outcomes research (PCOR) and comparative effectiveness research (CER) has been limited by socioeconomic, cultural, and geographic factors. We employed a patient-driven peer-to-peer approach to recruit and engage racial minority ACHD patients and family members with the capacity to act as equal research partners to identify, participate in, develop, lead, and disseminate transcatheter intervention PCOR and CER. Method(s): In addition to the study team, four expert PCORI funded-consultants provided strategies and training on stakeholder recruitment and engagement for targeting minorities and underserved communities. The following strategies were employed: 1) engaging through faithbased organizations like churches, synagogues, and mosques 2) working with Houston Methodist Primary Care Providers (PCP) group to identify ACHD patients 3) recruiting through the project's Online Portal and participants' Video Blogs to appeal to stakeholders 4) using social media for mainstream outreach. Result(s): Eighteen total ACHD collaborative members were successfully recruited. Six ACHD patient advocates were recruited as Steering Committee Members (SCM) of the stakeholder collaborative (STK), however, two SCMs resigned from their positions due to family reasons and time commitments. One member was replaced by previously interviewed candidates and another was promoted from our lay STKs. Other applicants remain involved in a non-decision maker capacity as in-waiting STK members. Social media outreach and our online portal proved to be the most efficient recruitment and engagement strategies. On average, we received three new candidate applications after every social media post. Eleven stakeholders were recruited through social media. One stakeholder was recruited through the PCP network. Two churches promoted our flier in their newsletter but we did not receive any applications. Onsite recruiting from faith-based organizations was not feasible due to the ongoing global health crisis from COVID- 19. Discussion(s): Addressing racial disparities in congenital heart and interventional cardiology is challenging and requires a patient-centered approach to research. Despite the COVID-19 pandemic, we successfully built an 18-member ACHD patient collaborative of underrepresented minorities, employing a peer-to-peer strategy through a multi-faceted approach. Social media was the most successful approach especially in the absence of in-person gatherings, however, despite financial compensation for involvement, attrition due to personal reasons occurred. Current efforts are directed toward training the ACHD patient collaborative in basic research methods to serve as equal partners in patient-centered outcomes and comparative effectiveness research.

A Social Network Analysis of COVID-19 Transmission Models in Taiwan: Two Epidemic Waves in 2020-2021

The COVID-19 pandemic has made a profound global impact. As it rages on around the globe, social network researchers have been involved in exploring key factors of rapid infection and transmission. For Taiwan, it is thus worthy of exploring the differences between the transmission models of the two epidemic waves in 2020-2021 for any insight that may have been overlooked. In this study, the social network analysis is adopted for revealing any unforeseen threats of infection. In the first wave, 652 confirmed cases were reported from January 21, 2020, to November 30, 2020. In the second wave, 880 confirmed cases were reported from May 03, 2021, to May 17, 2021. The infection source attribute, i.e., local vs. imported, made the transmission models to be structured differently between the first and the second wave. In the first wave, it was found that a community outbreak could easily happen when one node got infected without knowing when and where the transmission occurred. In contrast, in the second wave, it was found that the gender attribute was more effective than the age attribute in quickly identifying the differences in the transmission models among all the confirmed cases. © 2022 Taiwan Academic Network Management Committee. All rights reserved.

Development of Ultrapure and Potent Tannic Acids as a Pan-coronal Antiviral Therapeutic

The rampageous transmission of SARS-CoV-2 has been devastatingly impacting human life and public health since late 2019. The waves of pandemic events caused by distinct coronaviruses at present and over the past decades have prompted the need to develop broad-spectrum antiviral drugs against them. In this study, our Pentarlandir ultrapure and potent tannic acids (UPPTA) showed activities against two coronaviral strains, SARSCoV-2 and HCoV-OC43, the earliest-known coronaviruses. The mode of inhibition of Pentarlandir UPPTA is likely to act on 3-chymotrypsin-like protease (3CLpro) to prevent viral replication, as supported by results of biochemical analysis, a 3CLpro assay, and a "gain-of-function" 3CLpro overexpressed cell-based method. Even in the 3CLpro overexpressed environment, Pentarlandir UPPTA remained its antiviral characteristic. Utilizing cell-based virucidal and cytotoxicity assays, the 50% effective concentrations (EC50) and 50% cytotoxicity concentration (CC50) of Pentarlandir UPPTA were determined to be similar to 0.5 and 52.5 mu M against SARS-CoV-2, while they were 1.3 and 205.9 mu M against HCoV-OC43, respectively. In the pharmacokinetic studies, Pentarlandir UPPTA was distributable at a high level to the lung tissue with no accumulation in the body, although the distribution was affected by the food effect. With further investigation in toxicology, Pentarlandir UPPTA demonstrated an overall safe toxicology profile. Taking these findings together, Pentarlandir UPPTA is considered to be a safe and efficacious pancoronal antiviral drug candidate that has been advanced to clinical development.

Using an Online Learning Platform to Show Students’ Achievements and Attention in the Video Lecture and Online Practice Learning Environments

During the worldwide pandemic of coronavirus disease 2019 (COVID-19 pandemic), online learning is increasingly vital for students to learn at home, and online learning platforms provide learning opportunities to students. The Junyi Academy online platform is an online learning platform that both helps lower-achieving students review lessons and helps teachers in Taiwan do differentiated instruction. Several studies have shown the relationships between students’ attention and their academic achievements for students’ self-learning, but how to best use these platforms to help students learn by themselves is unclear. Therefore, this study investigates the relationships between students’ attention and their academic achievements with two online learning environments. A total of 38 upper secondary students in Taiwan to participate in this study, and these students were divided between a Khan-style video lecture (VL) group and an online practice (OP) group. This study adopted an experimental design with data collected by an electroencephalogram (EEG). The results show that students’ attention in the VL group was higher than in the OP group. Furthermore, their attention in three stages differed between the two groups. Student attention was similar in the two groups for the first stage, but the VL group had higher attention for the second and third stages was than did the OP group. In addition, there was no relationship between students’ attention and their academic achievements in the VL and OP groups. Finally, this study raised some suggestions the future research. © 2022, Educational Technology and Society. All rights reserved.

Optimization of Nucleic Acid Detection Method under the New Epidemic Situation in Macao based on Experimental and Mathematical Statistics Analysis

A large number of COVID-19 nucleic acid tests are performed every day in the world. If the testing is performed individually, the testing workload and testing cost would be high. In this paper, we proposed a simulated model to check the efficiency of group testing methods given four typical situations and find the best grouping number for different predicted infection rates. Maximum likelihood Estimation (MLE) is applied for model estimation and Inversion Method is used to generate pseudo random variables for simulation. The simulation results point to the conclusions: (1) Given a high infection rate (p>0.1), both the false-positive and the false-negative possibilities have a poor relation with the grouping number. (2) However, given a low infection rate (p<0.1), the false-positive and false-negative possibilities will become important factors to reduce the grouping number. Especially, if p is close to 0.01, the grouping number is significantly affected. (3) With a 10% infection rate, it is recommended to group 5 participants in one test given no false-positive or false-negative situations. (4) If p<0.3, the group testing approach has the potential to improve overall testing efficiency. © 2021 ACM.

Risk Stratification for Acute Arterial and Venous Thromboembolism using CHA 2DS 2-VASc Score in Hospitalized COVID-19 Patients: A Multicenter Study

Introduction: Arterial and venous thromboembolism are common complications in COVID-19. Micro-macro thrombosis-related organ dysfunction can confer an increased risk for mortality. The optimal dosage of anticoagulation (AC) in COVID-19 patients remains unclear. Interim data from adaptive randomized control trials (ATTACC, REMAP-CAP, and ACTIV-4a) showed divergent results of therapeutic AC (TAC) versus usual care AC for the primary outcome of organ support free days in hospitalized COVID-19 patients. Components of CHA 2DS 2-VASc, a model originally built for predicting ischemic stroke in atrial fibrillation, are consistent with independent risk factors for COVID-19 severity and mortality. Herein, we analyzed the performance of the CHA 2DS 2-VASc model in hospitalized COVID-19 patients for predicting arterial and venous thromboembolic events, which could potentially aid in risk stratification of hospitalized patients and guide AC dosing. Methods: This is a large, retrospective, multicenter cohort study that included all adult patients from one tertiary care and five community hospitals with PCR-proven SARS-CoV-2 infection between 3/1/2020 and 12/1/2020. The primary composite outcome was acute arterial thromboembolism (ATE) and venous thromboembolism (VTE). We identified patients with ATE [cerebrovascular accident (CVA), myocardial infarction (MI) including both ST-segment elevation MI and non-ST-segment elevation MI], and VTE [deep vein thrombosis (DVT) and pulmonary embolism (PE)] using ICD -10 codes. Mean and standard deviation were reported for continuous variables;proportions were reported for categorical variables. To compare the groups, the Chi-square test was used for categorical variables, and the t-test was used for continuous variables. CHA 2DS 2-VASc scores were calculated on admission and were used as a measure of the predictive accuracy of the scoring system. Sensitivity and specificity with different cut-offs of CHA 2DS 2-VASc scores were calculated. All statistical tests were 2-sided with an α (significance) level of 0.05. All data were analyzed using R version 4.0.5. Results: Among 3526 patients, a total of 619 patients had thromboembolic events: 383 had ATE and 236 had VTE. Of 383 patients who had ATE, 350 patients were found to have acute MI, 48 had CVA, and 15 had both MI and CVA. In patients with VTE, 134 had DVT, 168 had PE, and 66 had both DVT and PE (Figure 1). We analyzed the primary composite outcome of ATE and VTE (group 1) vs no ATE and VTE (group 2). Baseline characteristics are included in Table 1. The in-patient all-cause mortality rate was 28.4% in group 1 vs 12.6% in group 2 (p<0.001). The mean hospital length of stay was 12.3 days in group 1 vs 8.8 days in group 2 (p<0.001). Group 1 had a mean CHA 2DS 2-VASc score of 3.3 ±1.6. vs 2.7±1.7 in group 2 (p<0.001) (Figure 2). At CHA 2DS 2-VASc scores of 3 and 4, the model had a specificity of 46% and 67% and sensitivity of 68% and 42% respectively for predicting ATE/VTE. The CHA 2DS 2-VASc score of 5 had a specificity of 86% and sensitivity of 25%. The score of 7 had 98% specificity but 3% sensitivity (Table 2). Conclusion: Our results suggest that the CHA 2DS 2-VASc model for arterial and venous thromboembolism has a moderate performance. The CHA 2DS 2-VASc score of 5 has a high specificity, though low sensitivity, for predicting thromboembolism. The CHA 2DS 2-VASc score can be used as an adjunct risk stratification tool to initiate TAC. [Formula presented] Disclosures: No relevant conflicts of interest to declare.

Pandemic Response and Crisis Informatics: An Imperative for Public Health Messaging

The focus of this research is to examine the usage patterns exhibited by users of online search engines in the midst of COVID-19. We aim to understand how the queries are structured and their timing on the various platforms that citizens are using to check the availability of Personal Protective Equipment (PPE) since the outbreak of the COVID-19 public health crisis. Understanding and analyzing peak volume for information platforms is critical, especially for public health policy, with a mind toward crisis informatics. In this study, we collect all the data of users querying data from Face Mask Map (FMM), a real-time application which displays the inventory status for all stores selling PPE. This data is from the point at which the public health crisis became widely known to the time at which PPE availability saturated the market. As COVID-19 continues to proliferate and affect people around the globe, official organizations such as Department of Health and World Health Organization (WHO) utilize Web or Social Media (Facebook or Twitter) to announce up-to-date news, e.g. daily confirmed cases or in order to update policy regarding resource management. We then correlate the significant announcements from public health officials, specifically published by Ministry of Health and Welfare (MoHW) in Taiwan, that are concerning usage and distribution of PPE. We find that the temporal dynamics of aggregated users behavior are consistent with the events. For the practitioner of disaster management, it is critical to be able to identify when the public will consistently react to public health announcements for the purpose of ensuring proper supply distribution and avoid misallocation. It is our hope that the study can help to build an effective online disaster preparedness information system, in the consideration of computing and public psychology, to better respond to disaster with a greater corpus of data. © 2020 IEEE.

A proposal of exercise and performance learning assistant system for self-practice at home

Due to pandemic spreads of COVID-19 and increasing populations of seniors, exercises or performance practices at home have become important to maintain healthy lives around the world. World Health Organization (WHO) has announced the physical health determines the Quality of Life (QoL) of a human. Unfortunately, a lot of people have no exercise and may be in unhealthy conditions. In this paper, we propose an Exercise and Performance Learning Assistant System (EPLAS) to assist people practicing exercises or learning performances by themselves at home. EPLAS adopts inexpensive devices and free software for low-cost implementation. It offers a video content of model actions by an instructor to be followed by the user, where the reaction is rated by comparing the feature points of the human bodies extracted by an open-source software OpenPose. For evaluations, we conduct experiments of applying EPLAS with five Yoga poses to 41 persons in Indonesia, Japan, and Taiwan, and confirm the effectiveness of the proposal. © 2020 ASTES Publishers. All rights reserved.