Budget Impact Analysis of COVID-19 Vaccines on U.S. Medicare and Commercial Health Plans after Depletion of the Federally-Purchased Supply

Objectives: To analyze the budget impact (BI) of Covid-19 vaccines from a mixed U.S commercial and Medicare payer perspective after depletion of the Federally-Purchased Supply (FPS). Method(s): BI analyses were conducted in a hypothetical one-million member health plan with a mixed commercial (55%) and Medicare (45%) population over a one-year time horizon based on the current (January 2023) Covid-19 vaccine recommendations from the Centers for Disease Control and Prevention (CDC). The two scenarios in the model include 1) the health plan does not pay for Covid-19 vaccines, and 2) after the depletion of FPS, the health plan must cover all costs for Covid-19 vaccines. Model inputs include the market shares of available Covid-19 vaccines in the US as of December 2022, Covid-19 vaccine utilization trends stratified into age groups (<12, 12-17, 18-24, 25-49, 50-64, >=65 years old) between commercial and Medicare populations, and predicted Covid-19 vaccine costs. Model inputs were based on the CDC publicly available data, real world evidence, published literature, and expert opinions. Sensitivity analyses (SA) were conducted to test uncertainties arising from the input values in the model. Result(s): The number of members receiving one primary dose, completed Covid-19 vaccine series, one booster dose and two booster doses was estimated at 9,253, 49,720, 594,933 and 29,387, respectively. The incremental Covid-19 vaccine cost per member per month over one year after depletion of the FPS was $5.92 for the commercial population, $8.93 for the Medicare population, and $7.27 for the total population in the health plan. In the SA, the largest effect was observed for the scenario which varied the percentage of population >=65 years old receiving one booster dose. Conclusion(s): The model results indicate that there will be a high budget impact from a mixed U.S commercial and Medicare perspective after depletion of the FPS of Covid-19 vaccines.Copyright © 2023

Brand Personality and Revisit Intention: The Mediating Role of Tourists' Self-Image Congruity

Purpose- Brand personality plays an important role in the development of tourists' self-image congruence and revisit intention. This paper attempts to shed light on the relationship between brand personality and self-image congruence and revisit intention through a quantitative analysis.Design - Data were collected from 496 Vietnamese tourists who visited the top five tourist sites in Vietnam, including Ha Long, Phu Quoc, Sapa, Nha Trang, and Hoi An. Methodology - By using SEM in AMOS version 24 CFA was performed to test the the overall measurement model.Findings - Multivariate data analysis demonstrated that five dimensions of brand personality. (Excitement, Sincerity, Sophistication, Competence, and Ruggedness) have a positive effect on self-image congruence and revisit intention. While excitement appears to be most helpful for developing self-image congruence, sincerity has the highest benefit for increasing revisit intention, sincerity has the highest utility for increasing revisit intention. In addition, revisit intention is most influenced by excitement and least influenced by sophistication through self-image congruence. Originality of the research - The findings highlight the important role of attributes associated with tourist destinations. Managers in the tourism sector should be familiar with these characteristics in order to position or strengthen their destination's brand with the aim of delivering to each tourist group a customized experience that resonate with their shared values. The insights provided by this paper also have important implications for travel companies in the gradual recovery of the country's smoke-free industry under the conditions of the COVID-19 pandemic.

Indoor Chemical Exposures in Secondary Schools post-COVID-19 Pandemic: A Cohort Study of New Work-Based Learning Teachers

We obtained cross-sectional repeated measures self-report survey data on workplace safety and health and wellness from newer, early-to-mid-career New Jersey (NJ) secondary or high school (HS) teachers supervising work-based learning on- and off-campus in specific career clusters within career-technical-vocational education. This cohort study in the 2021-2024 school years (SYs) is a unique opportunity. It immediately proceeded the 2019-2021 SYs. Due to COVID-19, most 2020 2nd semester (3/18-6/30/2020) and 2020-2021 SY in-person classes went online;extracurricular activities were cancelled or substantially altered for online/virtual substitutes;and, no-to-little in-person HS teaching and off- or on-campus activities. Upon return 8-9/2021, classrooms, labs, shops, etc. were cleaned. Data suggested risks of human exposure to chemical agents from cleaning, disinfecting and sanitation consumer products use, given concerns about viral (and bacterial) loads collecting and potentially remaining on frequently contacted surfaces. We present study design, recruitment data, and selected survey content responses from ongoing research 2021-2024. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

"Monday Feels Like Friday!” - Towards Overcoming Anxiety and Stress of Autistic Young Adults During Times of Isolation

Autistic young adults are at a higher risk of experiencing elevated mental and psychological distress during times of isolation, such as the COVID-19 pandemic, due to the challenges related to uncertainty and abrupt changes in every aspect of daily life. In this research, we aim to develop participant-centric interventions for assisting autistic young adults in addressing their anxiety and stress during times of isolation. We first conducted an exploratory literature review to gather the design requirements for an effective stress management technology. Based on our findings, we designed our initial high-fidelity prototype, MindBot, a mindfulness and AI-based chatbot application. We conducted an in-depth qualitative study (semi-structured interviews with 15 autistic young adults and a cognitive walkthrough with 20 participants who have training in HCI and usability evaluation techniques) to identify the design and usability issues to improve the effectiveness of MindBot. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Psoriasiform Spongiotic Dermatitis Drug Eruption following Pfizer-BioNTech SARS-CoV-2 mRNA Vaccine Administration

Introduction: Cutaneous manifestations such as morbilliform rashes, lichen planus, and local injection site patches have been recently published in case reports to occur within days of receiving the coronavirus disease 2019 (COVID-19) vaccine. The most common drug eruptions have been noted to be delayed hypersensitivity reactions. Objective: To spotlight a vaccine drug eruption case in a patient with a long history of the autoimmune condition, psoriasis vulgaris. Case Presentation: A 51-year-old Caucasian female presented with pruritic and erythematous rashes covering her back, abdomen, pelvis, and both upper extremities emerging one week after receiving the Pfizer BioNTech mRNA vaccine. The rashes worsened, rapidly spreading toward the lower extremities within five days after her second dose. The patient was diagnosed with psoriasiform spongiotic dermatitis compatible with a drug eruption and began loratadine and clobetasol cream treatment and phototherapy. Conclusion: With limited published data available on skin reactions to the COVID-19 vaccine, our case report is among one of the first presentations to describe a morbilliform rash induced by a Pfizer BioNTech mRNA drug-eruption. Although this is a rare case, we may expect more reported drug eruptions to be documented as mass vaccinations continue to be dispensed across the globe. Physicians must be prepared to accurately diagnose and treat dermatologic conditions on patients with and without pre-existing illnesses. © 2022 THE AUTHORS. Published by the National Society for Cutaneous Medicine.

Air Quality Improvement Following COVID-19 Lockdown Measures and Projected Benefits for Environmental Health

Many regions worldwide suffer from heavy air pollution caused by particulate matter (PM2.5) and nitrogen dioxide (NO2), resulting in a huge annual disease burden and significant welfare costs. Following the outbreak of the COVID-19 global pandemic, enforced curfews and restrictions on human mobility (so-called periods of 'lockdown') have become important measures to control the spread of the virus. This study aims to investigate the improvement in air quality following COVID-19 lockdown measures and the projected benefits for environmental health. China was chosen as a case study. The work projects annual premature deaths and welfare costs by integrating PM2.5 and NO2 pollutant measurements derived from satellite imagery (MODIS instruments on Terra and Aqua, and TROPOMI on Sentinel-5P) with census data archived by the Organization for Economic Co-operation and Development (OECD). A 91-day timeframe centred on the initial lockdown date of 23 January 2020 was investigated. To perform the projections, OECD data on five variables from 1990 to 2019 (mean population exposure to ambient PM2.5, premature deaths, welfare costs, gross domestic product and population) were used as training data to run the Autoregressive Integrated Moving Average (ARIMA) and multiple regression models. The analysis of the satellite imagery revealed that across the regions of Beijing, Hebei, Shandong, Henan, Xi'an, Shanghai and Hubei, the average concentrations of PM2.5 decreased by 6.2, 30.7, 14.1, 20.7, 29.3, 5.5 and 17.3%, while the NO2 decreased by 45.5, 54.7, 60.5, 58.7, 63.6, 50.5 and 66.5%, respectively, during the period of lockdown restrictions in 2020, as compared with the equivalent period in 2019. Such improvements in air quality were found to be beneficial, reducing in 2020 both the number of premature deaths by approximately 97,390 and welfare costs by over USD 74 billion.

Characteristics of Hospital Onset SARS Cov-2 Infections Before and After the Emergence of The Highly Transmissible Variant B.1.1.529 In a Comprehensive Cancer Center

Background. SARS-CoV-2 B.1.1.529 (Omicron) variant was first identified in November 2021 in South Africa and was notable for its increased transmissibility and rapid spread world wide. In the United States, this variant led to a surge inCOVID-19 cases by December 2021. As a result, we experienced a steep rise in cases among patients and employees at our institution starting December 22nd, 2021. Therefore, we compared the incidence and characteristics of hospital-onset COVID-19 (HO-COVID-19) in our cancer patients prior to and during the surge of the Omicron variant. Methods. We identified HO-COVID-19, as per the CDC definition, from our infection control surveillance database, and additional contact tracing information was reviewed to determine the possible sources of HO-COVID-19. Whole-genome sequencing studies were conducted randomly on nasopharyngeal swabs of patients and employees who had COVID-19 during the study period. Results. Twenty-six HO-COVID-19 infections were identified from the beginning of the pandemic (February 2020) through February 2022 (Table 1). Only 17 cases occurred over 22 months from the beginning of the pandemic through early December 2021 (Figure 1). These HO-COVID-19 occurred during the 3 COVID-19 surges that were epidemiologically attributed to the variants seen prior to Omicron. Among these 17 patients, 12 (70%) were symptomatic, 9 (53%) had a link to an infected employee, 7 (41%) died during their hospitalization (3 of the deaths were attributable to COVID-19), and 10 (59%) recovered and were discharged. Over 6 weeks (from December 22nd, 2021, through February 1st, 2022), 9 HO-COVID-19 were discovered during the Omicron variant surge (Figure 1). Six (67%) of these patients were symptomatic, 8 (89%) had a link to an infected employee, 2 (22%) died (1 death was attributed to COVID-19 ), and 7 (78%) recovered and were discharged. Conclusion. The Omicron variant surge led to marked increases in HO-COVID-19 despite the continuous adoption of enhanced infection control practices, testing on admission, and daily symptoms screening of patients and employees.

The Impact of the COVID-19 Pandemic on Hospital-Acquired Infections at a Comprehensive Cancer Center

Background. Robust infection control (IC) measures were deployed across healthcare institutions at the start of the COVID-19 pandemic, resulting in increased use of personal protective equipment (PPE), enhanced contact precautions, and emphasis on hand hygiene. The impact of these IC measures on the rates of hospitalacquired infections (HAIs), such as multidrug-resistant organisms (MDROs), device-related infections (DRIs), Clostridium difficile infection (CDI), and respiratory viral infections (RVIs) is not known. Here, we aim to evaluate the effect of the enhanced IC practices on the occurrence of various HAIs in a comprehensive cancer center. Methods. We analyzed the monthly HAIs rates from September 2017 through March 2022, including data 42 months pre-pandemic (September 2016-February 2020) and 24 months during the pandemic (March 2020-August 2021). Reported HAIs were calculated using denominators of patient days for CDI and MDROs, per 1,000 admissions for RVIs, and catheter days for DRIs. The incidence rate ratios (IRR) were calculated for all HAIs. Results. When comparing pre-pandemic to the pandemic period, a significant increase in the overall incidence rate (IR) of MDROs from 0.56 to 0.67 per 1,000 patient days with an IRR of 1.19 (95% CI 1.02-1.39), a decrease in the IR of CLABSIs and a stable IR of CAUTIs and VAEs were observed (Table 1). A significant decrease was observed in the IR of CDI (IRR 0.65 (95% CI 0.55-0.78)). The total IR of hospital-acquired RVIs per 1,000 admissions (5.24 to 1.82;IRR 0.36;95% CI 0.30-0.44) decreased, as did each respiratory virus (Respiratory Syncytial Virus (0.51 to 0.15;IRR 0.30), Influenza (0.50 to 0.24;IRR 0.50), Parainfluenza (1.21- to 0.34;IRR 0.28), Rhinovirus (1.91 to 0.5;IRR 0.26), and Human Metapneumovirus (0.19 to 0.05;IRR 0.24) during their respective respiratory viral seasons (Figure 1). (Table Presented) Conclusion. Implementing strict IC measures during the COVID-19 pandemic in a cancer hospital led to a significant decrease in many HAIs and a reduction in nosocomial RVIs. However, whether these enhanced measures, such as masking at all times as part of patient care, are needed during the upcoming respiratory viral seasons is not known.

Caregiving Experiences during the COVID-19 Pandemic

Background: Caring for a family member with cognitive impairment can be emotionally and physically exhausting. Caregiver challenges have been exacerbated by the COVID-19 pandemic. This qualitative study examined caregiving experiences during the pandemic, exploring what caregivers perceived as most important in their caregiving experience while navigating through the pandemic. Method(s): We enrolled 158 adults (non-Hispanic White (NHW): 66%;Latino: 16%;Black: 9%;Asian: 8%) caring for a family member with MCI, mild cognitive impairment, (35%) or dementia (65%). Approximately 37% were recruited from an Alzheimer's Disease Research Center (ADRC) and 63% from the community. Caregivers completed demographic questionnaires and open-ended questions about their experience during the pandemic. They were asked (1) what was the most important thing to them in terms of providing care;(2) if they felt that they had enough support to help them provide care;(3) how the COVID-19 pandemic has impacted them and the care they provide;and (4) what strategies have they used to help them provide care. Responses were open-coded by 2 teams of 2, who met several times with the principal investigator to discuss and refine the themes. Result(s): Several themes emerged from the analyses, including (1) caregivers managing their own physical health and safety, or that of their care recipient;(2) changes in relationship dynamics and familial support;(3) fluctuations in availability of formal support;(4) focus on wellness;and (5) employment/financial concerns brought upon by the pandemic. Conclusion(s): The pandemic has filled the lives of caregivers with more adversities and struggles, which can exacerbate the stress of caregiving and call attention to the need for more formal support. These findings highlight the urgent need for more online and at-home caregiving resources that can continue beyond the pandemic. Copyright © 2022 the Alzheimer's Association.

VBlock—Blockchain-Based Traceability in Medical Products Supply Chain Management: A Case Study in VietNam

The COVID-19 is putting tremendous pressure on the medical facilities supply, as the demand for facilities has significantly outweighed the production capability. Several rogue traders have taken advantage of this issue to distribute counterfeit products. Moreover, some sellers advertise genuine products with unreasonably high prices. Our team believes that fake or overpriced facilities will significantly complicate the battle against COVID, thereby posing millions of lives to risk. That is why our team is developing V-Block. V-Block is a supply chain management system that harnesses the power of Blockchain. Its primary goals are to assist the government in tracking the product’s distribution process and help customers avoid questionable deals. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A novel PA-led urgent care model for medical oncology patients at a large academic cancer center

Background: Oncology patients are high users of the emergency department (ED), which often results in hospital admissions for management of cancer symptoms or cancer treatment toxicities. Interventions such as urgent care (UC) models can decrease such visits, and help improve patient management, health care utilization, and patient experience. Sunnybrook Health Sciences Centre, a large tertiary care hospital in Toronto, Canada has a high volume of medical oncology ED visits (average 4 per day) with about 50% admitted for management. Method(s): A novel physician-assistant (PA) led and physician supervised UC model was developed to assist in medical oncology patient phone triage, assessment, and management of cancer or treatment related issues that would otherwise have been sent to the ED by the oncology team. There were two phases: 1) due to COVID, the patients were managed in a dedicated stream primarily using space and nursing in the ED, 2) a dedicated UC clinic with nursing support was opened for these patients. Result(s): In phase 1, there were 424 referrals over 24 months;84% would have otherwise been sent through the usual ED process. 26% of patients were managed with PA navigation outside the UC program in other hospital settings. Of the 204 patients formally treated in the UC stream, 67.7% were discharged home. At 48 hours, 89% of discharged patients were stable or improved;this was 80% at 14 days, and 17.3% came back to the ED or were admitted within 14 days of the UC visit. In phase 2, there have so far been 214 referrals over 5 months;83.6% would have otherwise been sent to the ED. Of the patients who were assessed, 77.9% were discharged home. Outcomes of these patients are being collected. The top 3 patient issues managed during both phases were: fever, pain, and dyspnea. Fifteen patient telephone surveys were completed, and 93.3% were either satisfied or highly satisfied with their UC experience. Conclusion(s): A novel PAled triage and management model for urgent medical oncology patient issues was found in initial phase to be feasible and effective with streamlined care through the ED. Once a dedicated UC clinic was opened, referral volumes increased, and a high rate of ED diversion, patient discharge, and effective care was continued. Patients were also highly satisfied. Several ongoing process and outcome measures are being evaluated to help expand the scope and impact of this resource.

The management of adherence outlier population in a pharmacy-based patient care model during COVID years

BACKGROUND: Since early 2020 systems have been dealing with the impacts of the COVID-19 pandemic, social isolation, and restricted movement of people on access to medications and management services, this poster will describe and assess the capture of adherence outliers into UI TEAM RX an outpatient pharmacy-based patient care delivery model. OBJECTIVE(S): To assess the capture of EQuIPP adherence outlier patients into a pharmacy-based patient care model (UI TEAM RX), days to medication pick up, and improvement in adherence in an outpatient pharmacy during COVID calendar years (CY) 2020 and 2021. METHOD(S): A monthly list of patients who have not met the adherence benchmark is obtained from EQuIPP. These patients are captured within the UI TEAM RX patient care model. Capture rate was defined as the ratio of the total number of patients captured in UI TEAM RX over the total number of potential captures. The total number of potential captures represents the total number of adherence outliers attributed to the pharmacy minus the patients that are captured by other pharmacy-managed services. The average number of days to pick up the medications was quantified as the days gap between medication ready status to pick up by the patient. Improvement in adherence was defined based on whether the patient remained an outlier at the end of the year. RESULT(S): For the outpatient care center pharmacy, 146 and 119 unique EQuIPP adherence outlier patients were identified for CY2020 and 2021, respectively. During the peak of the COVID pandemic in 2020, the capture rate for the model was only 43%. In 2021, the patient capture rate for the model rose to 100%. The average days to pick up were 2.9 and 2.6 for CY 2020 and 2021, respectively. At the end of 2020, five UI TEAM RX patients were no longer outliers vs one patient at the end of CY 2021. The number of Non-UI TEAM RX patients (patients not captured in the model) that remained outliers for CY 2020 and CY 2021 are one and ten. CONCLUSION(S): A lower capture rate was observed during CY 2020, which may be attributed to the start of the pandemic. There was a significant improvement in the capture rate in 2021. The average days to medication pick-up were shorter in 2021 vs 2020. A fewer number of patients remained as outliers at the end of 2021 vs 2020 as well. Engaging patients in the UI TEAM RX model appears to impact achieving adherence benchmarks positively;however, this needs to be further researched appropriately.

Does National Governance Affect the Capital Structure of Listed Firms during the COVID-19 Pandemic?

This study estimates the macro-economic factors affecting the listed small and medium enterprises' capital structures in Vietnam from 2010 to 2020. The author conducts the quantitative method (generalized method of moments—GMM) with valid instrument variables to solve the endogeneity in regression models, which refers to the determinants of capital structures. Based on the trade-off theory and the pecking order theory, the author provides evidence of macro-economic factors and firm-specific factors in explanations for the capital choices of the Vietnamese firms, including national governance, inflation, COVID-19, firm age, and asset structure. In particular, this study highlights how national governance and COVID-19 influence the capital structure of small and medium enterprises in Vietnam. © 2023 by the authors. Licensee ESJ, Italy. This iCommons Attribution (CC-BY) license (https://c.

Panic Purchasing: Food Hoarding in a City under Lockdown during the COVID-19 Pandemic

This research aimed to investigate the determinants of panic purchasing to hoard food in Ho Chi Minh City during the lockdown caused by the COVID-19 pandemic. Pragma-tism and the deduction approach were used for the research. During the lockdown period in Ho Chi Minh City, the purposive sampling technique was the first method used to reach the popula- tion that needed to be measured. Then, simple sampling was the second technique to collect data in the city in July and August 2021. Data were collected from 584 participants-higher than the required minimum sample size-who fulfilled the essential criteria to be included in the sample's population. Multi-quantitative methods, including descriptive statistics, reliability tests for items, exploratory factor analysis, and linear regression analysis, were used to analyze the data obtained. The main findings are that perceived scarcity, susceptibility, severity, cues to action, and self -ef- ficacy impacted panic purchasing to hoard foods. The results of this study are compared to the literature review in order to discuss panic buying behaviour, and recommendations are offered to policymakers and researchers in the future.

Caregiver perceptions of the early COVID-19 pandemic rescheduling process at one academic pediatric ophthalmology practice

Introduction: The American Academy of Ophthalmology's recommendation to provide only urgent/emergent care during the COVID-19 pandemic resulted in high-volume appointment cancellations. We aim to evaluate how the rescheduling process at one academic medical center's pediatric ophthalmology clinic was perceived by caregivers and to identify factors contributing to caregiver satisfaction, attitudes toward alternative appointments, and perception of patient harm. Method(s): Caregivers of children whose pediatric ophthalmology appointment was cancelled during the early pandemic, 3/18-5/18/2020, were recruited via telephone consent to complete an 18-question, 10-point Likert scale, anonymous online survey. Result(s): 110/484(23%) of respondents completed the survey. Most were rescheduled < 7months from the original date (25%- < 4wks, 23%-5wks-3mos, 36%, 4-6 mos, 16%, >7 mos;P = 0.003). Of the ocular diagnoses rescheduled, 41% were low acuity, 50% moderate, and 9% high, which correlated to the length of time to reschedule (57% high acuity, < 4 wks;74% low acuity, >4 mos;P = 0.006). There was no difference in willingness to accept alternative appointments between new (n = 95) versus established (n = 15) patients, (phone call: p = 0.555, audio-visual telemedicine: p = 0.403). Overall frustration with rescheduling was low (mean: 2.61 +/- 2.91) and was higher in those with a longer interval to reschedule (< 4 wks vs >7 mos P = 0.0419, 5wks-3mos vs >7 mos P = 0.019). Perception of harm caused by delay in care was most associated with length of time to reschedule (P = 0.006). Conclusion(s): Overall caregiver frustration toward the rescheduling process was low at one academic medical center's pediatric ophthalmology clinic during the early COVID-19 pandemic. Survey results suggest that more interpersonal methods of patient examination/communication such as audio-visual telemedicine or transfer to another provider were preferred over audio-only telemedicine. Copyright © 2022

Management of nontraditional security for Vietnam’s sustainable development: an integrated approach

In recent years, nontraditional security (NTS) studies have been the focus of growing interest in the security literature. However, this work only focuses on conceptualization and associated risks and makes only limited connections between nontraditional security and sustainability. Furthermore, the United Nations Sustainable Development Goals (SDGs) have been threatened by NTS concerns such as the COVID-19 pandemic. The aim of this article is to contribute to the current debate about NTS and to formulate an integrated approach with sustainable development. We devote attention to sustainability and security studies to understand the challenges and opportunities for achieving sustainable outcomes. To highlight the role of the management of NTS in achieving the SDGs, we review the literature and analyze the main threats of NTS in Vietnam. This article shows that sustainability studies should not be separated from nontraditional issues. By analyzing case studies of NTS threats in Vietnam, we find that the economic, social, and environmental pillars of Vietnam’s sustainable development are threatened despite the country’s great success in economic growth in recent decades. We conclude by noting that the lack of integrated linkages between NTS and sustainability creates obstacles for Vietnam’s sustainable development and nontraditional sources of insecurity pose a serious threat to the development prospects of the country. Therefore, in the context of an integrated approach, countries should incorporate certain aspects of the human-security agenda as nontraditional matters into their national development policies. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

Audio Feature Ranking for Sound-Based COVID-19 Patient Detection

Audio classification using breath and cough samples has recently emerged as a low-cost, non-invasive, and accessible COVID-19 screening method. However, a comprehensive survey shows that no application has been approved for official use at the time of writing, due to the stringent reliability and accuracy requirements of the critical healthcare setting. To support the development of Machine Learning classification models, we performed an extensive comparative investigation and ranking of 15 audio features, including less well-known ones. The results were verified on two independent COVID-19 sound datasets. By using the identified top-performing features, we have increased COVID-19 classification accuracy by up to 17% on the Cambridge dataset and up to 10% on the Coswara dataset compared to the original baseline accuracies without our feature ranking. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.