Organic food and obesity: factors influencing actual purchase of organic food in COVID-19 pandemic with moderating role of organic food availability

Purpose: Organic food consumption decreases the risk of becoming obese or overweight. This study intends to see the influence of customer perceived value, COVID-19 fear, food neophobia, effort and natural content on the intention to purchase organic food (IPOF) that leads to the actual purchase of organic food (APOF). Moreover, organic food availability is a moderator between IPOF and APOF. Design/methodology/approach: PLS-SEM is used for hypothesis testing. A purposive sampling technique was followed to gather data from organic food consumers in Lahore, Gujranwala and Islamabad and a total of 479 questionnaires were part of the analysis. Findings The outcomes show that customer perceived value, effort and natural content is positively related to IPOF. Despite this, COVID-19 fear and food neophobia are negatively associated with IPOF. IPOF and organic food availability are positively related to APOF. Finally, organic food availability significantly moderated between IPOF and APOF. Practical implications: This study outcome reveals that companies of organic food can recognize customer perceived value, COVID-19 fear, food neophobia, effort, natural content and organic food availability in their decision-making if they determine the actual purchase of organic food. This study offers a valuable policy to companies of organic food to enhance customer's behavior in purchasing organic food in Pakistan. Besides, practitioners and academicians can benefit from this study finding. Originality/value: This initial research integrates customer perceived value, COVID-19 fear, food neophobia, effort, natural content, IPOF and organic food availability to determine APOF in the COVID-19 pandemic. Moreover, consumption value theory is followed to develop the framework.

Impact of e-service quality on e-loyalty of online banking customers in Pakistan during the Covid-19 pandemic: mediating role of e-satisfaction

This study explores the mediating role of e-satisfaction during the pandemic on the relationship between e-service quality and e-loyalty of banking customers in Pakistan. The data were collected from 442 customers of online banking services in Pakistan during the Covid-19 pandemic, following a survey-based study. Baron and Kenny (J Personal Soc Psychol, 51(6):1173, 1986) and Preacher and Hayes (Behav Res Methods, 40(3):879-891, 2008) mediation technique which utilizes the bootstrapping method has been used to explore mediation. The findings show that e-service quality has a significant positive effect on the e-loyalty of the customers of online banking services. Relationships between e-service quality and e-loyalty of online banking customers in Pakistan are significantly and fully mediated by their online satisfaction in unusual situations. This study would help the bankers to implement more effective marketing strategies to retain their customers and attract potential customers, particularly during non-normal situations like the Covid-19 pandemic. It will help them identify the areas of e-services that need improvement to enhance the satisfaction and loyalty of the customers. The bootstrap method for mediation along with Baron and Kenny (J Personal Soc Psychol, 51(6):1173, 1986) leads to using a more sophisticated methodological technique to explore the mediation. The Oliver Expectancy-Disconfirmation Paradigm (EDP) in electronic banking setup during non-normal situations like the Covid-19 pandemic also served as a unique contribution to this study. Application of Baron and Kenny (J Personal Soc Psychol, 51(6):1173, 1986) mediation along with Preacher and Hayes (Behav Res Methods, 40(3):879-891, 2008) leads to more robust findings for the study in non-normal situations like the Covid-19 pandemic. The study findings add scientific value as they are applicable to the banking sector in particular in non-normal situations like the Covid-19 pandemic and the overall service sector in general. Further, as two different methods of mediation have been employed and this makes the study more rigorous and scientific.

Effects of Critical Incident Stress Management on Nurses During COVID-19 Pandemic

Objective: To analyze the effect of Critical Incident Stress Management on the mental health of nurses during COVID-19. Study Design: Quasi-experimental study. Place and Duration of Study: Combined Military Hospital, Jhelum Pakistan from Mar to Jun 2020. Methodology: Forty-six nurses were consecutively recruited and evaluated regarding Knowledge about COVID-19, thoughts regarding its origin, emotional reactions, and coping mechanisms. The evaluation was followed by the provision of Critical Incident Stress Management sessions in March. Finally, in the second phase conducted in June, the participants were evaluated again to assess the effect of intervention regarding the above parameters. Results: Results indicated a statistically significant shift in Knowledge from Social Media to Academic Resources (p<0.001). Thoughts regarding the origin of COVID-19 showed that ‘Religious Causes' and belief in ‘Religious and Biological Causes both” significantly reduced (p=0.001 and p=0.003, respectively), while opinions regarding ‘Biological Causes' increased in frequency (p< 0.001). Emotionally a significant reduction was seen in Confusion (p<0.001). A significant reduction was observed in Religious Rituals (p=0.002) for Coping Mechanisms. However, observing Safety Precautions and Distraction Strategies were insignificantly affected (p=0.668 and p=1, respectively). Conclusion: Critical Incident Stress Management helped healthcare workers sublimate their emotional reactions and helped them cope with a productive mindset for better management of the pandemic.

Dock-able linear and homodetic di, tri, tetra and pentapeptide library from canonical amino acids: SARS-CoV-2 Mpro as a case study

Peptide-based therapeutics are increasingly pushing to the forefront of biomedicine with their promise of high specificity and low toxicity. Although noncanonical residues can always be used, employing only the natural 20 residues restricts the chemical space to a finite dimension allowing for comprehensive in silico screening. Towards this goal, the dataset comprising all possible di-, tri-, and tetrapeptide combinations of the canonical residues has been previously reported. However, with increasing computational power, the comprehensive set of pentapeptides is now also feasible for screening as are the comprehensive set of cyclic peptides comprising four or five residues. Here, we provide both the complete and prefiltered libraries of all di-, tri-, tetra-, and penta-peptide sequences from 20 canonical amino acids and their homodetic (N-to-C-terminal) cyclic homologues. The FASTA, SMILES, and SDF-3D libraries can be readily used for screening against protein targets. We also provide a simple method and tool for conducting identity-based filtering. Access to this dataset will accelerate small peptide screening workflows and encourage their use in drug discovery campaigns. As a case study, the developed library was screened against SARS-CoV-2 main protease to identify potential small peptide inhibitors. Graphical Image 1

Development of Carbon-Nanodot-Loaded PLA Nanofibers and Study of Their Barrier Performance for Medical Applications.

The COVID-19 pandemic has increased the usage of personal protective equipment (PPE) all round the world and, in turn, it has also increased the waste caused by disposable PPE. This has exerted a severe environmental impact, so in our work, we propose the utilization of a sustainable electrospun nanofiber based on poly lactic acid (PLA), as it is biobased and conditionally degradable. We optimized the weight percentage of the PLA-precursor solution and found that 19% PLA produces fine nanofibers with good morphology. We also introduced carbon nanodots (CNDs) in the nanofibers and evaluated their antibacterial efficiency. We used 1, 2, 3, and 4% CNDs with 19% PLA and found increased antibacterial activity with increased concentrations of CNDs. Additionally, we also applied a spunbond-nanofiber layered assembly for the medical face masks and found that with the addition of only 0.45 mg/cm2 on the nonwoven sheet, excellent particle filtration efficiency of 96.5% and a differential pressure of 39 Pa/cm2 were achieved, meeting the basic requirements for Type I medical face masks (ASTM-F2100).

A lightweight CORONA-NET for COVID-19 detection in X-ray images.

Since December 2019, COVID-19 has posed the most serious threat to living beings. With the advancement of vaccination programs around the globe, the need to quickly diagnose COVID-19 in general with little logistics is fore important. As a consequence, the fastest diagnostic option to stop COVID-19 from spreading, especially among senior patients, should be the development of an automated detection system. This study aims to provide a lightweight deep learning method that incorporates a convolutional neural network (CNN), discrete wavelet transform (DWT), and a long short-term memory (LSTM), called CORONA-NET for diagnosing COVID-19 from chest X-ray images. In this system, deep feature extraction is performed by CNN, the feature vector is reduced yet strengthened by DWT, and the extracted feature is detected by LSTM for prediction. The dataset included 3000 X-rays, 1000 of which were COVID-19 obtained locally. Within minutes of the test, the proposed test platform's prototype can accurately detect COVID-19 patients. The proposed method achieves state-of-the-art performance in comparison with the existing deep learning methods. We hope that the suggested method will hasten clinical diagnosis and may be used for patients in remote areas where clinical labs are not easily accessible due to a lack of resources, location, or other factors.

Vaccine Adjuvants: Selection Criteria, Mechanism of Action Associated with Immune Responses and Future Directions.

The most effective method to minimize the prevalence of infectious diseases is vaccination. Vaccines enhance immunity and provide protection against different kinds of infections. Subunit vaccines are safe and less toxic, but due to their lower immunogenicity, they need adjuvants to boost the immune system. Adjuvants are small particles/molecules integrated into a vaccine to enhance the immunogenic feedback of antigens. They play a significant role to enhance the potency and efficiency of vaccines. There are several types of adjuvants with different mechanisms of action; therefore, improved knowledge of their immunogenicity will help develop a new generation of adjuvants. Many trials have been designed using different kinds of vaccine adjuvants to examine their safety and efficacy, but in practice, only a few have entered in animal and human clinical trials. However, for the development of safe and effective vaccines, it is important to have adequate knowledge of the side effects and toxicity of different adjuvants. The current review discussed the adjuvants which are available for producing modern vaccines as well as some new classes of adjuvants in clinical trials.

Advanced and Smart Textiles during and after the COVID-19 Pandemic: Issues, Challenges, and Innovations.

The COVID-19 pandemic has hugely affected the textile and apparel industry. Besides the negative impact due to supply chain disruptions, drop in demand, liquidity problems, and overstocking, this pandemic was found to be a window of opportunity since it accelerated the ongoing digitalization trends and the use of functional materials in the textile industry. This review paper covers the development of smart and advanced textiles that emerged as a response to the outbreak of SARS-CoV-2. We extensively cover the advancements in developing smart textiles that enable monitoring and sensing through electrospun nanofibers and nanogenerators. Additionally, we focus on improving medical textiles mainly through enhanced antiviral capabilities, which play a crucial role in pandemic prevention, protection, and control. We summarize the challenges that arise from personal protective equipment (PPE) disposal and finally give an overview of new smart textile-based products that emerged in the markets related to the control and spread reduction of SARS-CoV-2.

Performance of saliva compared with nasopharyngeal swab for diagnosis of COVID-19 by NAAT in cross-sectional studies: Systematic review and meta-analysis.

Nucleic acid amplification testing (NAAT) is the preferred method to diagnose coronavirus disease 2019 (COVID-19). Saliva has been suggested as an alternative to nasopharyngeal swabs (NPS), but previous systematic reviews were limited by the number and types of studies available. The objective of this systematic review and meta-analysis was to assess the diagnostic performance of saliva compared with NPS for COVID-19. We searched Ovid MEDLINE, Embase, Cochrane, and Scopus databases up to 24 April 2021 for studies that directly compared paired NPS and saliva specimens taken at the time of diagnosis. Meta-analysis was performed using an exact binomial rendition of the bivariate mixed-effects regression model. Risk of bias was assessed using the QUADAS-2 tool. Of 2683 records, we included 23 studies with 25 cohorts, comprising 11,582 paired specimens. A wide variety of NAAT assays and collection methods were used. Meta-analysis gave a pooled sensitivity of 87 % (95 % CI = 83-90 %) and specificity of 99 % (95 % CI = 98-99 %). Subgroup analyses showed the highest sensitivity when the suspected individual is tested in an outpatient setting and is symptomatic. Our results support the use of saliva NAAT as an alternative to NPS NAAT for the diagnosis of COVID-19.

Role of Methylprednisolone for COVID-19 Patients Admitted to a Tertiary Care Hospital

Objective: To determine the role of Methylprednisolone in managing COVID-19 patients. Study Design: Cross-sectional study. Place and Duration of Study: Pakistan Emirates Military Hospital (PEMH), Rawalpindi Pakistan, from Jan to Feb 2021. Methodology: This study was carried out at the Department of Medicine. Medical records of all moderate, severe and critical COVID-19 patients admitted and receiving Methylprednisolone were reviewed. Methylprednisolone was used in all patients at doses 0.-2 mg per kg. Results: A total of 200 cases were included. The most common presenting symptoms were cough (77.5%), fever (67.5%) and shortness of breath (63.5%). Most patients (85%) presented within the first week of their illness. One or more comorbidities were present in 75% of patients. Most common being hypertension in 70(35%) and diabetes mellitus in 63(31.5%). Complications seen in the study were Cytokine release storm 92(46%) and acute respiratory distress syndrome 44(22%). The median time for initiation of corticosteroid therapy was 4 hours (range 1-96 hours). Overall survival (OS) in the study was 83.5%. OS for patients with moderate, severe and critical diseases was 97.8%, 86.2% and 62%, respectively (p<0.001). Conclusion: Corticosteroids are useful in COVID-19-admitted patients and provide excellent survival outcomes.

Multi-head deep learning framework for pulmonary disease detection and severity scoring with modified progressive learning.

Chest X-rays (CXR) are the most commonly used imaging methodology in radiology to diagnose pulmonary diseases with close to 2 billion CXRs taken every year. The recent upsurge of COVID-19 and its variants accompanied by pneumonia and tuberculosis can be fatal in some cases and lives could be saved through early detection and appropriate intervention for the advanced cases. Thus CXRs can be used for an automated severity grading of pulmonary diseases that can aid radiologists in making better and informed diagnoses. In this article, we propose a single framework for disease classification and severity scoring produced by segmenting the lungs into six regions. We present a modified progressive learning technique in which the amount of augmentations at each step is capped. Our base network in the framework is first trained using modified progressive learning and can then be tweaked for new data sets. Furthermore, the segmentation task makes use of an attention map generated within and by the network itself. This attention mechanism allows to achieve segmentation results that are on par with networks having an order of magnitude or more parameters. We also propose severity score grading for 4 thoracic diseases that can provide a single-digit score corresponding to the spread of opacity in different lung segments with the help of radiologists. The proposed framework is evaluated using the BRAX data set for segmentation and classification into six classes with severity grading for a subset of the classes. On the BRAX validation data set, we achieve F1 scores of 0.924 and 0.939 without and with fine-tuning, respectively. A mean matching score of 80.8% is obtained for severity score grading while an average area under receiver operating characteristic curve of 0.88 is achieved for classification.

Identification of RdRp inhibitors against SARS-CoV-2 through E-pharmacophore-based virtual screening, molecular docking and MD simulations approaches.

The outbreak of novel Coronavirus, an enduring pandemic declared by WHO, has consequences to an alarming ongoing public health menace which has already claimed several million human lives. In addition to numerous vaccinations and medications for mild to moderate COVID-19 infection, lack of promising medication or therapeutic pharmaceuticals remains a serious concern to counter the ongoing coronavirus infections and to hinder its dreadful spread. Global health emergencies have called for urgency for potential drug discovery and time is the biggest constraint apart from the financial and human resources required for the high throughput drug screening. However, computational screening or in-silico approaches appeared to be an effective and faster approach to discover potential molecules without sacrificing the model animals. Accumulated shreds of evidence on computational studies against viral diseases have revealed significance of in-silico drug discovery approaches especially in the time of urgency. The central role of RdRp in SARS-CoV-2 replication makes it promising drug target to curtain on going infection and its spread. The present study aimed to employ E-pharmacophore-based virtual screening to reveal potent inhibitors of RdRp as potential leads to block the viral replication. An energy-optimised pharmacophore model was generated to screen the Enamine REAL DataBase (RDB). Then, ADME/T profiles were determined to validate the pharmacokinetics and pharmacodynamics properties of the hit compounds. Moreover, High Throughput Virtual Screening (HTVS) and molecular docking (SP & XP) were employed to screen the top hits from pharmacophore-based virtual screening and ADME/T screen. The binding free energies of the top hits were calculated by conducting MM-GBSA analysis followed by MD simulations to determine the stability of molecular interactions between top hits and RdRp protein. These virtual investigations revealed six compounds having binding free energies of -57.498, -45.776, -46.248, -35.67, -25.15 and -24.90 kcal/mol respectively as calculated by the MM-GBSA method. The MD simulation studies confirmed the stability of protein ligand complexes, hence, indicating as potent RdRp inhibitors and are promising candidate drugs to be further validated and translated into clinics in future.

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks.

Artificial Intelligence (AI) techniques of deep learning have revolutionized the disease diagnosis with their outstanding image classification performance. In spite of the outstanding results, the widespread adoption of these techniques in clinical practice is still taking place at a moderate pace. One of the major hindrance is that a trained Deep Neural Networks (DNN) model provides a prediction, but questions about why and how that prediction was made remain unanswered. This linkage is of utmost importance for the regulated healthcare domain to increase the trust in the automated diagnosis system by the practitioners, patients and other stakeholders. The application of deep learning for medical imaging has to be interpreted with caution due to the health and safety concerns similar to blame attribution in the case of an accident involving autonomous cars. The consequences of both a false positive and false negative cases are far reaching for patients' welfare and cannot be ignored. This is exacerbated by the fact that the state-of-the-art deep learning algorithms comprise of complex interconnected structures, millions of parameters, and a 'black box' nature, offering little understanding of their inner working unlike the traditional machine learning algorithms. Explainable AI (XAI) techniques help to understand model predictions which help develop trust in the system, accelerate the disease diagnosis, and meet adherence to regulatory requirements. This survey provides a comprehensive review of the promising field of XAI for biomedical imaging diagnostics. We also provide a categorization of the XAI techniques, discuss the open challenges, and provide future directions for XAI which would be of interest to clinicians, regulators and model developers.

Genetic analysis of ACE2 peptidase domain in SARS-CoV-2-positive and SARS-CoV-2-negative individuals from Pakistan.

BACKGROUND: The outbreak of coronavirus disease 2019 (COVID-19) has emerged as a serious public health emergency of global concern. Angiotensin converting enzyme 2 (ACE2) peptidase domain is important for the cellular entry of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Germline variants in ACE2 peptidase domain may influence the susceptibility for SARS-CoV-2 infection and disease severity in the host population. ACE2 genetic analysis among Caucasians showed inconclusive results. This is the first Asian study investigating the contribution of ACE2 germline variants to SARS-CoV-2 infection in Pakistani population. METHODS: In total, 442 individuals, including SARS-CoV-2-positive (n = 225) and SARS-CoV-2-negative (n = 217) were screened for germline variants in ACE2 peptidase domain (exons 2, 3, 9, and 10) using high resolution melting and denaturing high-performance liquid chromatography analyses followed by DNA sequencing of variant fragments. The identified variant was analyzed by in silico tools for potential effect on ACE2 protein. RESULTS: A missense variant, p.Lys26Arg, was identified in one SARS-CoV-2-positive (1/225; 0.4%) and three SARS-CoV-2-negative (3/217; 1.4%) individuals. No significant difference in the minor allele frequency of this variant was found among SARS-CoV-2-positive and SARS-CoV-2-negative individuals (1/313; 0.3% versus 3/328; 0.9%; P = 0.624), respectively. The SARS-CoV-2-positive patient carrying p.Lys26Arg showed mild COVID-19 disease symptoms. It was predicted as benign variant by in silico tool. No variant was detected in ACE2 residues important for binding of SARS-CoV-2 spike protein. CONCLUSION: The p.Lys26Arg variant may have no association with SARS-CoV-2 susceptibility in Pakistani population. Whole ACE2 gene screening is warranted to clarify its role in SARS-CoV-2 infection.

Serum level estimation of some biomarkers in diabetic and non-diabetic COVID-19 infected patients.

Diabetes, hypertension, and cardiovascular disease all raise the risk of hospitalization and mortality in individuals infected with coronavirus disease 2019 (COVID-19). Higher levels of flogosis mediators such as TNF, C-reactive protein (CRP), IL-1, IL-6, leptin, and resistin, as well as increased levels of TNF, C-reactive protein (CRP), IL-1, IL-6, leptin, and resistin, define diabetes. The goal of this study is to evaluate the levels of D-dimer, total serum bilirubin (TSB), glutamic-oxaloacetic transaminase (GOT), glutamic pyruvic transaminase (GPT), and CRP in diabetic patients with COVID-19 infection to COVID-19 patients without diabetes. Blood samples were collected from individuals with diabetes who had COVID-19 and non-diabetic COVID patients as control. Moreover, D-dimer and CRP were evaluated by using Min Vidus and Latx, respectively, whereas AccEnT 200 system was used to measure the serum level of TSB, GPT, and GOT in the hematology lab. Also demonstrated that the average serum concentration of D-dimer, GOT and CRP was high in diabetic COVID-19-infected patients (980.66 ng/mL, 67.71 U/L, and 27.06 mg/L, respectively) compared with non-diabetic COVID-19-infected patients (791.17 ng/mL, 54.023 U/L and 20.11 mg/L, respectively) (p < 0.05), while the situation was inverse for the average concentration of TSB and GTP when their average concentrations were low in diabetic COVID-19-infected patients (12.89 Mmol/L and 59.79 U/L, respectively) (p > 0.05). Moreover, the cut-off values for serum D-dimer, TSB, GPT, GOT, and CRP of COVID-19-infected diabetic patients were ≥ 6500 ng/mL, ≥ 350 Mmol/L, ≥ 133 U/L mg/L, ≥ 150 U/L, and ≥ 15.22 mg/L, respectively, represented a perfect test for predicting COVID-19-infected diabetic patients with 100% sensitivity and specificity. In conclusion, serum D-dimer, TSB, GPT, GOT and CRP increased in diabetic COVID-19-infected patients compared to non-diabetic COVID-19 patients and the D-dimer concentration also increases. TSB and CRP were more pronounced among diabetic patients with corona, while liver enzyme concentrations were decreased.

Integrating real-world data from Brazil and Pakistan into the OMOP common data model and standardized health analytics framework to characterize COVID-19 in the Global South.

OBJECTIVES: The aim of this work is to demonstrate the use of a standardized health informatics framework to generate reliable and reproducible real-world evidence from Latin America and South Asia towards characterizing coronavirus disease 2019 (COVID-19) in the Global South. MATERIALS AND METHODS: Patient-level COVID-19 records collected in a patient self-reported notification system, hospital in-patient and out-patient records, and community diagnostic labs were harmonized to the Observational Medical Outcomes Partnership common data model and analyzed using a federated network analytics framework. Clinical characteristics of individuals tested for, diagnosed with or tested positive for, hospitalized with, admitted to intensive care unit with, or dying with COVID-19 were estimated. RESULTS: Two COVID-19 databases covering 8.3 million people from Pakistan and 2.6 million people from Bahia, Brazil were analyzed. 109 504 (Pakistan) and 921 (Brazil) medical concepts were harmonized to Observational Medical Outcomes Partnership common data model. In total, 341 505 (4.1%) people in the Pakistan dataset and 1 312 832 (49.2%) people in the Brazilian dataset were tested for COVID-19 between January 1, 2020 and April 20, 2022, with a median [IQR] age of 36 [25, 76] and 38 (27, 50); 40.3% and 56.5% were female in Pakistan and Brazil, respectively. 1.2% percent individuals in the Pakistan dataset had Afghan ethnicity. In Brazil, 52.3% had mixed ethnicity. In agreement with international findings, COVID-19 outcomes were more severe in men, elderly, and those with underlying health conditions. CONCLUSIONS: COVID-19 data from 2 large countries in the Global South were harmonized and analyzed using a standardized health informatics framework developed by an international community of health informaticians. This proof-of-concept study demonstrates a potential open science framework for global knowledge mobilization and clinical translation for timely response to healthcare needs in pandemics and beyond.

The Right or Wrong to the City? Understanding Citizen Participation in the Pre- and Post-COVID-19 Eras in Malaysia

The right to the city concept is widely debated in academic discourse yet ambiguously executed in public discourse. In much of the discussion, the right to the city is advocated as a right that humans should claim—i.e., participating in urban space living. Nonetheless, constraints and limits are imposed on such advocacy, resulting in a tokenized implementation state. With such a background surmounting the COVID-19 pandemic era, this study is aimed at understanding the right to the city propagation and revealing the possible wrongs of such civic advocacy. Multiple cases in Malaysia were selected for analysis and as the discussion context representing the state-of-the-art aspect of right to the city in the context of an emerging country. Two potential misconceptions through the action of right to the city were identified: first, the concept of right to the city has the potential to infringe the centrality of power, which both citizens and the authority have to make clear;second, the lack of a sign of contribution from citizens poses a severe challenge to build a co-created urban space for all. This paper contributes to removing a blind spot—the possible wrong to the right to the city—and provides ideas to achieve authentic citizen participation.

Automated grading of chest x-ray images for viral pneumonia with convolutional neural networks ensemble and region of interest localization.

Following its initial identification on December 31, 2019, COVID-19 quickly spread around the world as a pandemic claiming more than six million lives. An early diagnosis with appropriate intervention can help prevent deaths and serious illness as the distinguishing symptoms that set COVID-19 apart from pneumonia and influenza frequently don't show up until after the patient has already suffered significant damage. A chest X-ray (CXR), one of many imaging modalities that are useful for detection and one of the most used, offers a non-invasive method of detection. The CXR image analysis can also reveal additional disorders, such as pneumonia, which show up as anomalies in the lungs. Thus these CXRs can be used for automated grading aiding the doctors in making a better diagnosis. In order to classify a CXR image into the Negative for Pneumonia, Typical, Indeterminate, and Atypical, we used the publicly available CXR image competition dataset SIIM-FISABIO-RSNA COVID-19 from Kaggle. The suggested architecture employed an ensemble of EfficientNetv2-L for classification, which was trained via transfer learning from the initialised weights of ImageNet21K on various subsets of data (Code for the proposed methodology is available at: https://github.com/asadkhan1221/siim-covid19.git). To identify and localise opacities, an ensemble of YOLO was combined using Weighted Boxes Fusion (WBF). Significant generalisability gains were made possible by the suggested technique's addition of classification auxiliary heads to the CNN backbone. The suggested method improved further by utilising test time augmentation for both classifiers and localizers. The results for Mean Average Precision score show that the proposed deep learning model achieves 0.617 and 0.609 on public and private sets respectively and these are comparable to other techniques for the Kaggle dataset.

An Explainable AI-Enabled Framework for Interpreting Pulmonary Diseases from Chest Radiographs.

Explainable Artificial Intelligence is a key component of artificially intelligent systems that aim to explain the classification results. The classification results explanation is essential for automatic disease diagnosis in healthcare. The human respiration system is badly affected by different chest pulmonary diseases. Automatic classification and explanation can be used to detect these lung diseases. In this paper, we introduced a CNN-based transfer learning-based approach for automatically explaining pulmonary diseases, i.e., edema, tuberculosis, nodules, and pneumonia from chest radiographs. Among these pulmonary diseases, pneumonia, which COVID-19 causes, is deadly; therefore, radiographs of COVID-19 are used for the explanation task. We used the ResNet50 neural network and trained the network on extensive training with the COVID-CT dataset and the COVIDNet dataset. The interpretable model LIME is used for the explanation of classification results. Lime highlights the input image's important features for generating the classification result. We evaluated the explanation using radiologists' highlighted images and identified that our model highlights and explains the same regions. We achieved improved classification results with our fine-tuned model with an accuracy of 93% and 97%, respectively. The analysis of our results indicates that this research not only improves the classification results but also provides an explanation of pulmonary diseases with advanced deep-learning methods. This research would assist radiologists with automatic disease detection and explanations, which are used to make clinical decisions and assist in diagnosing and treating pulmonary diseases in the early stage.

Impact of Trade Policy Uncertainty and Sustainable Development on Medical Innovation for Developed Countries: An Application of DID Approach

Covering the period from 1980 through 2020, with an emphasis on COVID-19, this paper analyzes how trade policy uncertainty and sustainable development policies affected investment in medical innovation. In a twofold difference-in-differences (DiD) approach, using autoregressive distributed lag (ARDL), the paper takes account of exogenous and heterogeneous exposure to trade policy uncertainty and trade policy adjustment in developing nations, which limited tariff increases on imported products. Both long- and short-term effects have been analyzed. Beyond patent applications, margin responses, and exports, the study indicates that eliminating tariff uncertainty boosts innovation. Developing countries have had little effect on the long-term ramifications of sectoral innovation patterns, political shifts, and imported technology. A negative response to the innovation shock and a positive response by R&D corroborate bidirectional and unidirectional causality, respectively. They demonstrate a long-term link between medical innovation, trade policy uncertainty, and R&D spending. As regards sustainable development, GDP growth and HDI have positive, and GINI index and CO2 emissions, have negative long-run relations with medical innovation. This study contributes to the literature on innovation and policy uncertainty together with sustainable development factors in developed countries, and especially on innovation trends in the medical sector, where there is a current policy ambiguity regarding the influx of foreign technology and its significance.