The Impact of Power Distance Beliefs on Resistance Toward AI (vs Human Service): An Abstract

With the rapid advances of technology enabled healthcare services in the last few decades, Artificial intelligence (AI) can provide cost-effective healthcare services with equal precision to human expert-delivered health services (Chatterjee, 2019). AI can diagnose various diseases and provides medical suggestions which may help to enhance patients' well-being. For example, AI can readily track Covid-19 patients and assists with infection management by providing real-time data (Vaishya et al., 2020). However, many customers have shown their apathy to adopt AI-enabled patient care services. This research investigates why customers resist to adopt AI delivered patient services. Using identity process theory, this study demonstrates that power distance belief (PDB) dimension influences customers to resist AI delivered health services. We reason that people with high PDB demonstrate resistance toward AI delivered health services because they believe that AI may fail to consider their unique problems. Consequently, their uniqueness motives get activated and create anxiety among them, resulting in resistance toward AI delivered medical services. Further, this study proposes a boundary condition for this effect. We argue that when high (vs low) PDB people perceive threat, they demonstrate lower need for uniqueness. However, when they don't perceive threat, they show higher need for uniqueness. To examine our assertions above, we used 2 (PDB: High vs Low) × 2 (Perceived threat: present vs control) between subject experimental design. Findings demonstrate that people with high PDB show less need for uniqueness when they perceive threat, which impact their adoption of AI delivered health services. However, they demonstrate higher need for uniqueness in the control condition. Results show the importance of threat in consumer decisions as well as the need to emphasize on the tailored and individualized care in the AI delivered health services to enhance customers' preference. These results have important implications for healthcare marketers, as customers with high PDB resist AI delivered health services for their preference toward equality. Therefore, hospitals can design AI delivered health services in a way that attenuates customers' concerns for their uniqueness. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Evaluating the generalisability of neural rumour verification models

Research on automated social media rumour verification, the task of identifying the veracity of questionable information circulating on social media, has yielded neural models achieving high performance, with accuracy scores that often exceed 90%. However, none of these studies focus on the real-world generalisability of the proposed approaches, that is whether the models perform well on datasets other than those on which they were initially trained and tested. In this work we aim to fill this gap by assessing the generalisability of top performing neural rumour verification models covering a range of different architectures from the perspectives of both topic and temporal robustness. For a more complete evaluation of generalisability, we collect and release COVID-RV, a novel dataset of Twitter conversations revolving around COVID-19 rumours. Unlike other existing COVID-19 datasets, our COVID-RV contains conversations around rumours that follow the format of prominent rumour verification benchmarks, while being different from them in terms of topic and time scale, thus allowing better assessment of the temporal robustness of the models. We evaluate model performance on COVID-RV and three popular rumour verification datasets to understand limitations and advantages of different model architectures, training datasets and evaluation scenarios. We find a dramatic drop in performance when testing models on a different dataset from that used for training. Further, we evaluate the ability of models to generalise in a few-shot learning setup, as well as when word embeddings are updated with the vocabulary of a new, unseen rumour. Drawing upon our experiments we discuss challenges and make recommendations for future research directions in addressing this important problem. © 2022 The Author(s)

A Cross-sectional Study to Evaluate People's Knowledge, Attitude and Practice Towards Using Disinfectants and Sanitizers During COVID-19 Pandemic in Bangladesh

The devastating novel coronavirus (COVID-19) pandemic worldwide has become a global health crisis. This disease is highly contagious and caused by the transmission of severe acute respiratory syndrome, coronavirus 2 (SARS-CoV-2). To prevent the transmission of SARS-CoV-2, disinfectants and sanitizers are very effective and readily available preventive agents. In this study, knowledge, attitude and practice (KAP) levels of Bangladeshi people's were assessed regarding the use of disinfectants and sanitizers during the pandemic. An online questionnaire-based survey was conducted among the respondents from July 2021 to December 2021. A total number of 428 respondents participated in this survey. Data were analysed by the Statistical Package for the Social Sciences (SPSS) V26 software and interpreted. Results revealed that most of the respondents were knowledgeable, had a positive attitude and engaged in beneficial practice. Among the respondents, a significantly higher knowledge and practice score were observed among females (54.1% and 54.4%, respectively) than their counterpart. Moreover, people living in urban areas (71.7%) had a better attitude than the rural people (28.3%). In addition, a medium positive correlation between knowledge and attitude (r = + 0.482), a weak positive association between attitude and practice (r = +0.199), and a weak positive association between knowledge and practice (r = + 0.282) were found. Overall, majority of the respondents had better KAP scores in knowledge and attitude with relatively low scores in practice which indicates some space for betterment. Copyright © 2022, University of Dhaka. All rights reserved.

COVID-19 Detection Through Deep Learning Algorithms using Chest X-ray Images

COVID-19 became a pandemic affecting the lives of every human globally by the end of 2019. The disease impaired the lungs of infected patients. Precise prediction and diagnosis of COVID-19 disease are challenging due to its resemblance to viral pneumonia. Using multiple deep learning approaches, the researchers used chest X-ray (CXR) imaging to diagnose COVID-19. The X-ray image dataset from Kaggle is used for the study by selecting the COVID-19 and normal class. InceptionV3, MobileNetV2, VGG19,VGG16 and ResNet50 are the five neural networks used for binary classification of COVID-19. The accuracy of MobileNetV2 surpasses that of the remainder of the model by 93.02%. However, it has a compilation time of 1836 seconds per epoch. Besides, VGG16 has an accuracy of 92.37%, with a compilation time of 603 seconds per epoch. Compared to these models, Inceptonv3, Resnet50 and VGG19 perform with an accuracy score of 86.42%, 68.34% and 91.79%. Applying deep learning techniques to COVID-19 radiological imaging holds great promise for enhancing the accuracy of diagnosis when in comparison to the gold standard RT-PCR test and assisting healthcare professionals in making decisions quickly © 2022 IEEE.

The effect of the pandemic on the number of examined lymph nodes following major oesophophagogastric resection

Background: Lymph node yield following oesophagogastric (OG) cancer resection remains a valuable prognosticator of overall patient survival. It is also a quality indicator of histopathological assessment and a surrogate marker of surgical technique. The Royal College of Pathologists' state a minimum lymph node yield of 15 per specimen should obtained in 100% of cases where a radical OG resection has been undertaken. It is well known that the COVID-19 pandemic placed immense strain on NHS services. This study aimed to evaluate its effect on lymph node yield reporting following major OG resection in a large volume tertiary unit. Method(s): Retrospective National OG Cancer Audit (NOGCA) metrics were collected. Histological data including total lymph node yield and positive node status were extracted from patient records. Patient data was categorised into two study periods;pre-pandemic (March 2018-Feb 2020) and pandemic (March 2020- Feb 2022) following the first UK national lockdown. Comparative analysis between the two study periods was performed and for lymph node yield >15 per specimen a X2 statistic calculated. Result(s): In the pre COVID period a total of 280 (excluding GIST) resections were performed, 75% (210) oesophagectomies v. 25% (70) gastrectomies. The median age was 69 (range 25-90, males= 189 v. females =91). In the post pandemic period a total of 188 resections were performed, 72% (135) oesophagectomies v. 28% (53) gastrectomies. The median age was 69 (38-87, males = 142 v. female= 46). Lymph node yield was available for 275 resections in pre-pandemic study period, with a median nodal yield of 20 (5-61). In the pandemic study period lymph node yield data was available for 180 patients, median 19.5 (0-69). The minimum nodal yield (>15) was obtained in 80.7% of resection specimens pre-pandemic v. 68.9% in the pandemic study period (p= 0.00382). Conclusion(s): Our study demonstrates a higher rate of inadequate nodes examined in the post pandemic study period. Despite staffing pressures, efforts should be made to improve number of nodes examined to provide robust prognostic data.

Maintaining high volume oesophagagogastric resections during the COVID-19 pandemic: A single centres experience utilising the independent sector

Background: With many resources redirected to care for the those affected by the COVID-19 pandemic, the NHS faced unprecedented pressure to maintain oesophagogastric (OG) cancer resectional services. Our institution along with many tertiary units across the country were faced with limited access to essential critical care beds. The implementation of emergency contracts between the NHS and the independent sector (IS) allowed our unit to maintain a high volume resectional service by utilising the resources of a local private hospital with HDU/ ITU provision. We began operating within the IS shortly after the first UK lockdown in March 2020, and continued through till February 2022. During this period, we continued operating at our tertiary unit (TU) albeit at a reduced capacity. This study aimed to evaluate the surgical outcomes of patients undergoing major OG resectional surgery between the two sites. Method(s): This retrospective study included all patients who underwent major OG resectional surgery (including GIST) from March 2020-February 2022. Operation type and site were identified using OPCS-4 clinical codes and combined with National OG Cancer Audit (NOGCA) data to compare basic patient demographics, length of stay, complication rates, COVID infection rates and 90-day mortality. Descriptive and statistical analysis between the two operating sites was performed. Result(s): A total of 204 major OG resections were undertaken, 44% (89) at our TU;57 oesophagectomies and 32 gastrectomies, with 56% (115) at a local IS hospital;86 oesophagectomies and 29 gastrectomies. Additionally, 13 (6.4%) open and close procedures were performed across both sites. Median patient age was similar, 69 (45-86) years at our TU v. 68 (38-85) years at the IS site. A higher proportion of ASA 3 patients (46%) were operated on at our TU. No difference in median length of stay was observed;TU= 8 (1-93) days v. IS =9 (3-69) days, this included all patients who were repatriated to the TU. Higher complication rates seemed to occur in patients operated at the IS site v. the TU though these did not reach statistical significance;18 (15.7%) patients suffered an anastomotic leak v. 9 (10.1%) respectively (p= 0.246). 21 (18.3%) v. 13 (14.6%) patients suffered a major respiratory (p=0.487) and 4 (3.5%) v. 1 (1.1%) a major cardiac (p=0.281) complication. There were no cases of COVID infection within 30 days of primary procedure at the IS site, with 2 cases within the TU cohort. Our 90-day mortality rates were similar (IS= 4.54% v. TU=5.32%), p=0.661. Conclusion(s): Our study demonstrates that resection of patients with OG cancer is feasible in an independent sector hospital if supported by critical care. It allowed a high-volume tertiary unit to continue offering potentially curative surgery to patients whose treatment options would have otherwise been limited to oncological therapy only. Long term survival data compared to non-resecting trusts is required to determine whether this approach was superior. When considering future pandemic planning, we have demonstrated the value of this model in maintaining major OG resectional services.

An Empirical Model of Classifying Lung Affected Diseases to Detect COVID-19 Using Chest X-ray Employing Convolutional Neural Architecture

The earlier detection and accurate diagnosis of COVID seem to be a global problem. It is difficult to make a large number of testing equipment, but then again, their reliability is relatively poor. Recent research indicates the usefulness of chest x-ray pictures in identifying COVID. This study presents a deep learning algorithm developed from the ground up to categorize as well as confirm the existence of COVID in a set of X-ray imaging data. We designed a CNN architecture from the ground up to retrieve elements from provided X-ray data to categorize them and identify the individual contaminated with COVID. Our strategy may aid in mitigating the consistency issues while working with medical data. In contrast to some other classifying activities with a large enough image database, obtaining large X-ray datasets for this classification job is challenging. So, we applied multiple data enhancement techniques to maximize the accurateness, achieving a significant accuracy of 97.75 percent. © 2022 IEEE.

Data Mining for Predicting and Finding Factors of Bankruptcy

The financial crisis, since the pandemic outbreak due to COVID-19, the dissemination and invasive systemic risk in the global financial environment have drawn the attention to organizations' solvency monitoring methods. Inevitably, in this paper we have looked at the both bankruptcy prediction and the factors that lead to bankruptcy. The dataset for this study was acquired from Kaggle, which was based on the Taiwan Economic Journal, from 1999 to 2009. The corporate statutes of the Taiwan Stock Exchange were utilized to determine a company's bankruptcy. It was a highly imbalanced dataset having 220 Non-bankrupt and 6,599 bankrupt data. We have used Random Forest, Support Vector Machine, Artificial Neural Network, XGBoost, and LightGBM classifiers regarding bankruptcy prediction. On the other hand, to find the factors that lead to bankruptcy, we did an empiric analysis for which we calculated fourteen statistical values of both bankrupted and non-bankrupted features and saw their cosine similarities. These factors will help any financial company to plan its financial ratios for preventing bankruptcy. Here we got the best performance from the Artificial Neural Network with 98.64% accuracy. And we found four factors that were responsible for the bankruptcy in our dataset. Here, the factors determining bankruptcy are crucial because by finding these factors and the likelihood of bankruptcy, companies can take the necessary steps to plan their financial ratios and ensure the solvency of their businesses. © 2022 IEEE.

THE COMPUTATIONAL INVESTIGATION OF SIXTEEN ANTIVIRAL DRUGS AGAINST MAIN PROTEASE (MPRO) AND SPIKE PROTEASE (SPRO) OF SARS-CoV-2

In this research, the fourteen commonly used antiviral drugs were investigated through the computational tools against CoV-19 or SARS-2, as well as two small bioactive molecules from the cannabis plant, Tetrahydrocannabinol (THC) and Cannabinol (CBN). Thus, these were selelcted for molecular docking against main protein (5r7y) and spike protein (6xs6) of coronavirus. It was illustrated that the binding energies of Mpro for Pimodivir, Baloxavir Marboxil, Lopinavir, Baricitinib, Remdesivir, THC, Darunavir, Galidesivir, Nitazoxanide, CBN, Ritonavir, Penciclovir, Ribavirin, Favipiravir, Umifenovir, and Chloroquine were -8.6, -7.7, -7.6, -7.5, -7.3, -6.8, -6.6, -6.6, -6.6, -6.5, -6.5, -6.3, -6.2, -6.0, -5.7 and -5.4 kcal/mol, respectively, which could be supported for good binding molecules against micropathogens, where it was -9.8, -6.9, -6.9, -7.1, -7.1, -7.1, -7.5, -6.0, -6.2, -7.4, -5.8, -5.9, -5.7, -5.6 and -5.4 kcal/mol, respectively, for Spro. Among these, Pimodivir is a best-bonded molecule with Mpro and Spro in view of molecular docking score. Secondly, the ligand interaction was accounted for this protein against required corona virus protein consisting of weak H bonding, hydrophobic bond and Van dar Waal interaction. For justification of molecular docking, the molecular dynamics was calculated for top six scored drugs where the root mean square deviation (RMSD) and root mean square fluctuation (RMSF) were showed that the six drugs for both main protein and spike protein. Additionally, the chemical hardness and softness have calculated, and the lowest value of softness has found in sample 06 and 13 around 0.24. The HOMO-LUMO gap has calculated with a different value for all, but the lowest value has obtained for 01. Finally, the pharmacokinetics and Lipisinki rule were calculated, and all of these molecules had satisfied the Lipisinki rule. Finally, using the admetsar online data base, absorption, distribution, metabolism, excretion and toxicity have calculated. © 2021 Sociedad Chilena de Quimica. All rights reserved.

Design and Implementation of Automatic Line Follower Robot for Assistance of COVID-19 Patients

Coronavirus disease (COVID-19) has caused unprecedented global health problems, and the disease’s spread rate is extremely high. It spreads from infected people (COVID-19 positive) to others via droplets from the mouth or nose when they cough, sneeze, speak, sing, or take deep breaths. Frontline fighters of healthcare organizations such as doctors, nurses, and other medical staff cannot have direct contact with COVID-19 patients in isolation room without personal protective equipment (PPE). Hence, hospital workers have to face different types of problems in distributing foods, medicines, and disposal of waste. An Automatic Line Follower Robot (ALFR) is designed and implemented for COVID-19 patients which is capable of serving infected patients in an isolation room. The main contribution of this paper is to serve essential medicines and foods from the hospital staff and serve it to the patients following the black line. The ALFR also proposes a system which maintains an emergency wireless communication protocol between doctors and patients. It also collects waste from a specified basket and damps it to a proper place. Finally, it can sanitize the isolated room with the help of a disinfectant machine which is assembled in ALFR. ALFR’s performance has significantly improved, and it can successfully complete all tasks. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Comparative Study of CNN Transfer Learning Classification Algorithms with Segmentation for COVID-19 Detection from CT Scan Images

After it's inception, COVID-19 has spread rapidly all across the globe. Considering this outbreak, by far, it is the most decisive task to detect early and isolate the patients quickly to contain the spread of this virus. In such cases, artificial intelligence and machine learning or deep learning methods can come to aid. For that purpose, we have conducted a qualitative investigation to inspect 12 off-the-shelf Convolution Neural Network (CNN) architectures in classifying COVID-19 from CT scan images. Furthermore, a segmentation algorithm for biomedical images - U-Net, is analyzed to evaluate the performance of the CNN models. A publicly available dataset (SARS-COV-2 CT-Scan) containing a total of 2481 CT scan images is employed for the performance evaluation. In terms of feature extraction by excluding the segmentation technique, a performance of 88.60% as the F1 Score and 89.31% as accuracy is achieved by training DenseNet169 architecture. Adopting the U-Net segmentation method, we accomplished the most optimal accuracy and F1 Scores as 89.92% and 89.67% respectively on DenseNet201 model. Furthermore, evaluating the performances, we can affirm that a combination of a Transfer Learning architecture with a segmentation technique (U-Net) enhances the performance of the classification model.

INTRINSIC CULTURAL FACTORS THAT HELPED VIETNAM OVERCOME the COVID-19 PANDEMIC COMPARED with OTHER COUNTRIES

The Coronavirus Disease 2019 (COVID-19) pandemic emerged in Wuhan, China, spread nationwide and then onto many other countries between December 2019 and early 2020. The implementation of strict quarantine measures in Vietnam has kept a large number of people in isolation and has eventually put the disease under control. Social and physical distancing turned to be an efficient way of slowing the spread of disease and stopping chains of transmission of COVID-19 as well as preventing new ones from appearing (World Health Organization, 2020). Analyzing the World Health Organization (WHO) data, we could see a clear difference in the reported numbers between Vietnam, a developing country, and the USA, one of the leading developed countries in the western hemisphere. We tried to address the question if there are factors that helped local governments to implement helpful rules. We argue that Eastern Asian cultural traits played a role in reducing the spread of COVID-19. We recommend to take this commentary paper, and further research those cultural factors that positively affected the slowdown of the spread of the COVID-19 pandemic in Vietnam. © 2020 Australasian College of Health Service Management. All rights reserved.

Understanding mental health services and help-seeking behaviours among college students in Vietnam

OBJECTIVE Mental health is a significant topic, especially in the context of the COVID-19 pandemic. While there is higher prevalence, there is less attention, to mental health problems among Asian college students, so the authors decided to investigate the effectiveness and efficiency of mental health services and help-seeking behaviors in Vietnamese universities. By conducting this study, the authors hoped to contribute to current literature on the factors that contribute to professional mental health help-seeking behavior of college students in Vietnam and to suggest strategies to reduce possible barriers that prevent them from looking for professional medical help. DESIGN For this cross-sectional research, we first conducted a pilot study to test the reliability and validity of our measurements. We then made necessary adjustments and distributed the final questionnaires to a university in Ho Chi Minh City, Vietnam. Collected data was analyzed through exploratory factor analysis RESULTS Results indicate that between psychological openness and help-seeking propensity, in our model, help-seeking propensity more significantly explains students' help-seeking behavioral intentions than the other two. CONCLUSIONS Using the Theory of Planned Behavior, this study examined predictors of professional mental health-seeking behavior among college students in Vietnam. Our findings indicated that help-seeking propensity significantly influences Vietnamese students' intention to obtain professional healthcare. Through this study, we suggested some guidance to the school administrators on the factors that encourage students to seek professional mental care. © Asia Pacific Journal of Health Management 2020. All rights reserved.