Concept Drift Adaptation Methods under the Deep Learning Framework: A Literature Review

With the advent of the fourth industrial revolution, data-driven decision making has also become an integral part of decision making. At the same time, deep learning is one of the core technologies of the fourth industrial revolution that have become vital in decision making. However, in the era of epidemics and big data, the volume of data has increased dramatically while the sources have become progressively more complex, making data distribution highly susceptible to change. These situations can easily lead to concept drift, which directly affects the effectiveness of prediction models. How to cope with such complex situations and make timely and accurate decisions from multiple perspectives is a challenging research issue. To address this challenge, we summarize concept drift adaptation methods under the deep learning framework, which is beneficial to help decision makers make better decisions and analyze the causes of concept drift. First, we provide an overall introduction to concept drift, including the definition, causes, types, and process of concept drift adaptation methods under the deep learning framework. Second, we summarize concept drift adaptation methods in terms of discriminative learning, generative learning, hybrid learning, and others. For each aspect, we elaborate on the update modes, detection modes, and adaptation drift types of concept drift adaptation methods. In addition, we briefly describe the characteristics and application fields of deep learning algorithms using concept drift adaptation methods. Finally, we summarize common datasets and evaluation metrics and present future directions.

Studying the impact of COVID-19 on the European Air Transportation Network

The European Air Transportation Network was significantly impacted by the COVID-19 pandemic, resulting in an unprecedented loss of flight connections. Utilizing a combination of graph representation learning and time series analysis, this paper studies the evolution of both the global connectivity as well as the structure of the European Air Transportation Network from January 2020 to December 2022. Specifically, it finds strong differences in recovery rates for flights across six different market segments. In terms of network structure, the study finds that structural roles that are present in the pre-covid network have seen a loss in performance over the course of the pandemic, but have recovered to pre-covid levels. Using regional changes in structural roles, this study identifies Italy as the region with the strongest increase and the United Kingdom as the region with the strongest decrease in structural role, finding substantial differences in recovery rates per market segment. Lastly, this study pays special attention on the effect of the Russia-Ukrainian war on the European Air Transportation Network. © 2023 IEEE.

Impact of the COVID-19 Pandemic on Cervical Cancer Screening Rates in Colombia: An Interrupted Time Series Analysis, Stratified By Region

Objectives: The objective of this study is to measure the national impact of COVID-19 on cervical cancer screening rates in Colombia in five of its geographic regions to inform future health policy decision making. Method(s): This study utilized a quasi-experimental interrupted time-series design to examine changes in trends for the number of cervical cancer screenings performed in five geographic regions of Colombia. Result(s): In the rural region of Vichada, we found the lowest incidence of cervical cancer screenings, totaling at 3,771 screenings. In Cundinamarca, the region which hosts the capital city, a total of 1,213,048 cervical cancer screenings were performed. The researcher measured the impact on cervical cancer screenings in December 2021 against the counterfactual. This impact was ~269 cases that were not performed in December 2021 as a result of the COVID-19 pandemic compared to the counterfactual. In Cundinamarca, unlike other regions, we observed a stagnant pre-pandemic trend, a sharp drop in screenings in March 2020, and an immediate upward trend starting in April 2020. In the month of April 2020, compared to the counterfactual, there were 27,359 screenings missed, and by the month of December 2021, there were only 5,633 cervical cancer screenings missed. Conclusion(s): The region of Cundinamarca's sharp climb back to pre-pandemic screening levels could signal the relatively stronger communication system in the region, and especially in the capital district of Bogota, in re-activating the economy. This can serve as an example of what should be implemented in other regions to improve cervical cancer screening rates. Areas for further research include the examination of social determinants of health, such as the breakdown of the type of insurance screened patients hold (public versus private), zone (urban versus rural), insurance providers of those screened, ethnicities of the patients screened, and percentage of screenings that resulted in early detection of cervical cancer.Copyright © 2023

Integration of climate, transmission, and spread of dengue hemorrhagic fever in endemic areas

Introduction. Dengue Hemorrhagic Fever (DHF) is still a public health problem even in the era of the COVID-19 pandemic in 2020, including in Indonesia. This study aimed to analyze the incidence of DHF based on the integration of climatic factors, including rainfall, humidity, air temperature, and duration of sunlight and their distribution. Materials and Methods. This was an ecological time series study with secondary data from the Surabaya City Health Office covering the incidence of DHF and larva-free rate and climate data on rainfall, humidity, air temperature, and duration of sunlight obtained from the Meteorology and Geophysics Agency (BMKG). Silver station in Surabaya, the distribution of dengue incidence during 2018-2020. Results and Discussion. The results showed that humidity was correlated with the larvae-free rate. Meanwhile, the larva-free rate did not correlate with the number of DHF cases. DHF control is estimated due to the correlation of climatic factors and the incidence of DHF, control of vectors and disease agents, control of transmission media, and exposure to the community. Conclusions. The integration of DHF control can be used for early precautions in the era of the COVID-19 pandemic by control-ling DHF early in the period from January to June in Surabaya. It is concluded that humidity can affect the dengue outbreak and it can be used as an early warning system and travel warning regarding the relative risk of DHF outbreak.Copyright © the Author(s), 2023.

Forecasting COVID-19 Vaccination Rates using Social Media Data

The COVID-19 pandemic has had a profound impact on the global community, and vaccination has been recognized as a crucial intervention. To gain insight into public perceptions of COVID-19 vaccines, survey studies and the analysis of social media platforms have been conducted. However, existing methods lack consideration of individual vaccination intentions or status and the relationship between public perceptions and actual vaccine uptake. To address these limitations, this study proposes a text classification approach to identify tweets indicating a user's intent or status on vaccination. A comparative analysis between the proportions of tweets from different categories and real-world vaccination data reveals notable alignment, suggesting that tweets may serve as a precursor to actual vaccination status. Further, regression analysis and time series forecasting were performed to explore the potential of tweet data, demonstrating the significance of incorporating tweet data in predicting future vaccination status. Finally, clustering was applied to the tweet sets with positive and negative labels to gain insights into underlying focuses of each stance. © 2023 ACM.

Detecting COVID-19 spreading phases with time series analysis

Piecewise linear regression (PLR) method is applied to study cumulative cases of COVID-19 evolving everyday in England up to 6th February 2022 just before travel restrictions are removed and people started not to get tested anymore in the UK and factors e.g. the lockdowns behind the spread COVID-19 are also investigated. It is clear that different periods exhibit distinct patterns depending on variants and government-imposed restriction. Therefore, the effectiveness of lockdown measures is evaluated by comparing the rate of increase after a certain period (delay effect of measures) and that of time before as well as how new variants take over as a dominant variant. In addition, autoregression function is studied to show strong effect of cases in the past on today's cases since the disease is highly infectious. Most of work is carried out thorough python built-in libraries such as pandas for preprocessing data and matplotlib which allows us to gain more insight and better visualization into the real scenario. Visualization is conducted by Geoda showing the regional level of infections. © 2023 SPIE.

The Impact of COVID-19 on Outcome Indicators of Hospitals of Shahid Beheshti University of Medical Sciences: An Interrupted Time Series Analysis

Background and Aim: With the outbreak of the COVID-19 pandemic, the performance of hospitals were affected, and changes were made in the utilization of hospital services. Analyzing hospital performance data during the COVID-19 pandemic can provide insights into service utilization patterns and care outcomes for managers and policymakers. This study was conducted to investigate the impact of COVID-19 on selected outcome indicators in the hospitals of Shahid Beheshti University of Medical Sciences, Tehran. Materials and Methods: This research was descriptive-analytical and of the time series analysis type. Six outcome indicators were considered: hospitalization rate, bed occupancy rate, the average length of stay, emergency visits, laboratory tests, and imaging requests. Related data from 12 affiliated hospitals from 2017-2019 (pre-COVID) and 2020 (post-COVID) were obtained from the hospital's intelligent management system. The data were analyzed using R software's interrupted time series analysis method. Results: The hospitalization rate (P=0.015), bed occupancy rate (P=0.04), and the number of laboratory tests (P=0.003) significantly increased immediately after the outbreak of the pandemic. In contrast, emergency visits (P=0.034) have significantly decreased. The bed occupancy rate and the number of imaging requests showed no significant change. The decrease in emergency room visits within one year after the pandemic was significant, but the changes in other outcome indicators were non-significant (P>0.05). Conclusion: Understanding the changes and impact of a major event on hospital outcome indicators is necessary for decision-makers to effectively plan for resource allocation and effective pandemic response. The outbreak of COVID-19 has caused a change in performance and hospital outcomes by affecting the supply and demand of services. In a year after the pandemic's beginning, except for emergency visits, the other indicators have not experienced significant changes. Preservation of essential services such as emergency room visits is recommended in the strategy of rapid response to an epidemic outbreak and public campaigns to encourage people to seek medical care if needed in future waves of the pandemic. © 2022 the Authors.

Generalized Linear Regression Model to Determine the Threshold Effects of Climate Variables on Dengue Fever: A Case Study on Bangladesh

One of the leading causes of the increase in the intensity of dengue fever transmission is thought to be climate change. Examining panel data from January 2000 to December 2021, this study discovered the nonlinear relationship between climate variables and dengue fever cases in Bangladesh. To determine this relationship, in this study, the monthly total rainfall in different years has been divided into two thresholds: (90 to 360 mm) and (<90 or >360 mm), and the daily average temperature in different months of the different years has been divided into four thresholds: (16degreeC to <=20degreeC), (>20degreeC to <=25degreeC), (>25degreeC to <=28degreeC), and (>28degreeC to <=30degreeC). Then, quasi-Poisson and zero-inflated Poisson regression models were applied to assess the relationship. This study found a positive correlation between temperature and dengue incidence and furthermore discovered that, among those four average temperature thresholds, the total number of dengue cases is maximum if the average temperature falls into the threshold (>28degreeC to <=30degreeC) and minimum if the average temperature falls into the threshold (16degreeC to <=20degreeC). This study also discovered that between the two thresholds of monthly total rainfall, the risk of a dengue fever outbreak is approximately two times higher when the monthly total rainfall falls into the thresholds (90 mm to 360 mm) compared to the other threshold. This study concluded that dengue fever incidence rates would be significantly more affected by climate change in regions with warmer temperatures. The number of dengue cases rises rapidly when the temperature rises in the context of moderate to low rainfall. This study highlights the significance of establishing potential temperature and rainfall thresholds for using risk prediction and public health programs to prevent and control dengue fever.Copyright © 2023 Shamima Hossain.

U.S. Public Transportation Ridership Analysis and Prediction based on COVID-19

In this paper, a research was conducted to analyse and predict the impacts of COVID-19 on public transportation ridership in the U.S. and 5 most populous cities of the U.S. (New York City, Los Angeles, Chicago, Houston, Philadelphia). The paper aims to exploit the correlation between COVID-19 and public transportation ridership in the U.S. and make the reasonable prediction by machine learning models, including ARIMA and Prophet, to help the local governments improve the rationality of their policy implementation. After correlation analyses, high level of significant and negative correlations between monthly growth rate of COVID-19 infections and monthly growth rate of public transportation ridership are decidedly validated in the total U.S., and New York City, Los Angeles, Chicago, Philadelphia, except Houston. To analyse the errors of Houston, we consult the literature and made a discussion of Influencing factors. We find that the level of public transportation in quantity and utilization is terribly low in Houston. In addition, the factors, such as the lack of planning law and estimation of urban expressways, the high level of citizens' dependence on private cars and pride of owning cars play a considerable roll in the errors. And the impacts can be predicted to a certain extent through two forecasting models (ARIMA and Prophet), although the precision of our models is not enough to make a precise forecast due to the limitations of model tuning and model design. According to the comparison of the two models, ARIMA models' forecasting accuracy is between 6% and 10%, and Prophet's forecasting accuracy is between 8%-12%, depending on the city. Since the insufficient stationarity, periodicity, seasonality of time series, the Prophet models are hard be more refined. © 2023 SPIE.

Postpartum screening results in Ontario, Canada before and after the COVID-19 pandemic: An interrupted time-series analysis

Aims: This study examined the impact of the COVID-19 pandemic on mothers or childbearing parents using ongoing, systematic screening of a representative Ontario sample. Method(s): An interrupted time series analysis was conducted on data captured in the Healthy Babies Healthy Children (HBHC) screening tool to determine effects of the pandemic on relationships, support, mental health, and related clinical outcomes at the time of postpartum discharge from hospital. The ability to parent or care for the baby/child and other psychosocial and behavioural outcomes were assessed. Result(s): The co-primary outcomes of inability to parent or care for the baby/child were infrequently observed in both the pre -pandemic (March 9, 2019-March 15, 2020) and initial pandemic periods (March 16, 2020-March 23, 2021) ((parent 209/63,006 (0.33%) to 177/56,117 (0.32%), care 537/62,955 (0.85%) to 324/56,086 (0.58%)). Changes following pandemic onset were not observed for either outcome although a significant (beta = 1.013, 95% CI 1.002-1.025, p = 0.02) increase in slope was observed for inability to parent (with questionable clinical significance). For secondary outcomes, worsening was only seen for complications during labour/delivery. Significant improvements were observed in the likelihood of being unable to identify a support person to assist with care, need of newcomer support, and concerns about money over time. Conclusion(s): Despite more complications during labour/delivery, there were no substantive changes in concerns about ability to parent or care for children. Adverse impacts of the pandemic may have been mitigated by accommodations for remote work and social safety net policies.Copyright © 2023

Factors Associated with COVID-19 Infections and Deaths in the Gulf Cooperation Council (GCC) Countries: A Time Series Cross-Section Analysis

Objectives: COVID19 pandemic has caused significant health and economic burden globally. Compared with high-income nations, prevalence of COVID19 infections and mortality has been lower in GCC countries, but it was higher than MENA region average. There is limited evidence in the literature on pattern and factors associated with COVID19 infections and deaths, especially for six GCC countries. The study aims to investigate this trend and associations. Method(s): We used world-o-meter online global database for COVID19 infections and deaths, and other databases to capture country-level socio-economic, demographic, and interventional factors linked with COVID19. Trends in monthly COVID19 data were reported via graphs and a negative binomial regression was estimated to determine the association between factors and monthly COVID19 infections and deaths per million population during March 2020 to October 2021. Result(s): An increasing trend observed in monthly COVID19 cases and deaths up to month 8, followed by a drop and then further increasing trend from month 12 to month 18. For COVID19 infections, negative binomial regression estimates incidence rate ratio (IRR) for 'stringency index' as 1.04 (p<0.001), GDP per capita, IRR=0.99 (p<0.001), CVD death rate, IRR= 0.99 (p<0.001), diabetes prevalence, IRR= 2.26 (p=0.001), hospital beds per 1,000 population, IRR= 0.002 (p=0.010) and containment health index, IRR= 0.88 (p=0.037). These factors also appeared to be statistically significantly associated with monthly COVID19 deaths per million population. Conclusion(s): The study contributes to current evidence-base on factors which are potentially associated with COVID19 infections and mortality in six GCC nations. Healthcare policy makers in the region can lessen their COVID19 related health burden by taking appropriate preventing and mitigating measures in relation to factors that have significant associations with the infection and severe disease.Copyright © 2023

Stillbirth Rates before and during the COVID-19 Pandemic in Manitoba (Canada) and Japan

Background: Conflicting evidence exists on the impact of the COVID-19 pandemic restrictions on stillbirth rates in developed countries. We aimed to examine and compare the incidence rates of stillbirth before and after the implementation of COVID-19 measures in Canada and Japan. Method(s): We conducted two populationbased studies using mother-infant linked data from JMDC hospitalizations database (JMDC Inc.) in Japan and administrative health databases in Manitoba, Canada, from October 2016 to March 2021. We used interrupted time series analysis (generalized linear models) to investigate the immediate change in level and rebound change in quarterly rates of stillbirth (fetal death > 20 weeks of gestation). We modeled the forecasted trends based on prepandemic data via autoregressive moving average models. Result(s): We included 70,931 and 169,883 pregnancies in Manitoba and Japan during the study period, respectively. On average, stillbirth rates were 0.66% in Manitoba and 0.31% in Japan. The pandemic restrictions were associated with an immediate relative increase in stillbirths in Japan by 19.19% (beta2=0.05;p=0.5693) and in Manitoba by 18.6% (beta2=0.12;p=0.4434). However, the quarterly stillbirth rates decreased (beta3=0.1625, p=0.5066) in Japan and Manitoba (beta3=0.011, p=0.8296) during the pandemic period. During the first quarter of 2021, the absolute differences in the observed and forecasted rates in Manitoba and Japan were 0.04% and -0.05%, respectively. Conclusion(s): Although various approaches were implemented to address the pandemic in Manitoba (Canada) and Japan, we found no evidence of a significant increase in the incidence of stillbirth rates during the first year of the pandemic. Healthcare services in Canada and Japan have experienced substantial changes since the start of the COVID-19 pandemic, with little influence on stillbirth rates at population level. This study will further examine the effect of the pandemic measures on other adverse pregnancy outcomes in both countries.

Disruptions in Prenatal Care Visits during the Pandemic: A Population-Based Cohort Study in Manitoba, Canada

Background: Limited evidence exists on the pandemic's role in limiting access and use of prenatal care services and the quality of care for pregnant women. We aimed to investigate the impact of the pandemic restrictions on in-person prenatal care visits (PNCV) and the quality of prenatal care. Method(s): Using the mother-infant-linked administrative health databases in Manitoba, Canada, we conducted a province-wide population-based cohort study among independent pregnancies. We examined the quarterly rates of PNCV before (October 2016-March 2020) and during (April 2020-March 2021) the pandemic. Quality of prenatal care was categorized using the Revised Graduated Prenatal Care Utilization Index (R-GINDEX) into inadequate (<50% visits), intermediate (50%-80% visits), adequate (>80% visits), intensive (high-risk), and no care. Interrupted time series analyses were conducted to assess the immediate and lagged changes in PNCV and quality of care after the implementation of pandemic restrictions. Result(s): Amongst 70,931 pregnancies, we observed no significant mean difference in the overall numbers of PNCV during the pandemic compared to prepandemic (8.2 vs. 8.6,p=0.0837). Prenatal care utilization was 3.4% inadequate and 34.7% adequate before the pandemic and 4.8% and 26.6% during the pandemic, respectively. Restrictions were associated with an abrupt decline in adequate and intermediate care during the first trimester by 11.3% (p<0.001) and 11.98%, respectively, followed by non-significant change throughout the pandemic (beta3=-0.25,p=0.694 and beta3=-0.96,p=0.192, respectively). Moreover, restrictions were associated with an increased rate of inadequate care during the first (beta2=1.52,p=0.007) and second trimesters (beta2=0.78,p=0.208), and not among third trimesters (beta2=-0.44,p=0.094). During the pandemic, we found no significant differences in the rates of intensive prenatal care during the first (p=0.478), second (p=0.614), and third (p=0.608) trimesters compared to pre-pandemic. Conclusion(s): Our findings suggest a decline in adequacy levels of prenatal care services after COVID-19 restrictions were enacted, with a higher impact on pregnancies during their first and second trimesters. Although the overall adequacy of care decreased, there were no changes to the rates of intensive visits. This study will further investigate the impact of the pandemic on virtual PNCV and assess the association between the quality of prenatal care and adverse maternal and neonatal outcomes.

The Impact of COVID-19 on Mental Healthcare Utilization in Switzerland Was Strongest Among Young Females-Retrospective Study in 2018-2020.

Objectives: To provide a thorough assessment of the impact of the COVID-19 pandemic on the utilization of inpatient and outpatient mental healthcare in Switzerland. Methods: Retrospective cohort study using nationwide hospital data (n > 8 million) and claims data from a large Swiss health insurer (n > 1 million) in 2018-2020. Incidence proportions of different types of psychiatric inpatient admissions, psychiatric consultations, and psychotropic medication claims were analyzed using interrupted time series models for the general population and for the vulnerable subgroup of young people. Results: Inpatient psychiatric admissions in the general population decreased by 16.2% (95% confidence interval: -19.2% to -13.2%) during the first and by 3.9% (-6.7% to -0.2%) during the second pandemic shutdown, whereas outpatient mental healthcare utilization was not substantially affected. We observed distinct patterns for young people, most strikingly, an increase in mental healthcare utilization among females aged <20 years. Conclusion: Mental healthcare provision for the majority of the population was largely maintained, but special attention should be paid to young people. Our findings highlight the importance of monitoring mental healthcare utilization among different populations.

Impact of the First Year of the COVID-19 Pandemic on Pediatric Emergency Department Attendance in a Tertiary Center in South Italy: An Interrupted Time-Series Analysis.

BACKGROUND: The evidence shows a reduction in pediatric emergency department (PED) flows during the early stages of the COVID-19 pandemic. Using interrupted time-series analysis, we evaluated the impact of different stages of the pandemic response on overall and cause-specific PED attendance at a tertiary hospital in south Italy. Our methods included evaluations of total visits, hospitalizations, accesses for critical illnesses and four etiological categories (transmissible and non-transmissible infectious diseases, trauma and mental-health) during March-December 2020, which were compared with analogous intervals from 2016 to 2019; the pandemic period was divided into three segments: the "first lockdown" (FL, 9 March-3 May), the "post-lockdown" (PL, 4 May-6 November) and the "second lockdown" (SL, 7 November-31 December). Our results showed that attendance dropped by a mean of 50.09% during the pandemic stages, while hospitalizations increased. Critical illnesses decreased during FL (incidence rate ratio -IRR- 0.37, 95% CI 0.13, 0.88) e SL (IRR 0.09, 95% CI 0.01, 0.74) and transmissible disease related visits reduced more markedly and persistently (FL: IRR 0.18, 95% CI 0.14, 0.24; PL: IRR 0.20, 95% CI 0.13, 0.31, SL: IRR 0.17, 95% CI 0.10, 0.29). Non-infectious diseases returned to pre-COVID-19 pandemic levels by PL. We concluded that that the results highlight the specific effect of the late 2020 containment measures on transmissible infectious diseases and their burden on pediatric emergency resources. This evidence can inform resource allocation and interventions to mitigate the impact of infectious diseases on pediatric populations and the health-care system.

Impact of the COVID-19 restrictions on the epidemiology of Cryptosporidium spp. in England and Wales, 2015-2021: a time series analysis.

Introduction. In England and Wales, cryptosporidiosis cases peak in spring and autumn, associated with zoonotic/environmental exposures (Cryptosporidium parvum, spring/autumn) and overseas travel/water-based activities (Cryptosporidium hominis, autumn). Coronavirus disease 2019 (COVID-19) restrictions prevented social mixing, overseas travel and access to venues (swimming pools/restaurants) for many months, potentially increasing environmental exposures as people sought alternative countryside activities.Hypothesis. COVID-19 restrictions reduced incidence of C. hominis cases and potentially increased incidence of C. parvum cases.Aim. To inform/strengthen surveillance programmes, we investigated the impact of COVID-19 restrictions on the epidemiology of C. hominis and C. parvum cases.Methodology. Cases were extracted from the Cryptosporidium Reference Unit (CRU) database (1 January 2015 to 31 December 2021). We defined two periods for pre- and post-COVID-19 restrictions implementation, corresponding to before and after the first UK-wide lockdown on 23 March 2020. We conducted a time series analysis, assessing differences in C. parvum and C. hominis incidence, trends and periodicity between these periods.Results. There were 21 304 cases (C. parvum=12 246; C. hominis=9058). Post-restrictions implementation incidence of C. hominis dropped by 97.5 % (95 % CI: 95.4-98.6 %; P<0.001). The decreasing incidence trend pre-restrictions was not observed post-restrictions implementation due to lack of cases. No periodicity change was observed post-restrictions implementation. There was a strong social gradient; there was a higher proportion of cases in deprived areas. For C. parvum, post-restrictions implementation incidence fell by 49.0 % (95 % CI: 38.4-58.3 %; P<0.001). There was no pre-restrictions incidence trend but an increasing incidence trend post-restrictions implementation. A periodicity change was observed post-restriction implementation, peaking 1 week earlier in spring and 2 weeks later in autumn. The social gradient was the inverse of that for C. hominis. Where recorded, 22 % of C. hominis and 8 % of C. parvum cases had travelled abroad.Conclusion. C. hominis cases almost entirely ceased post-restrictions implementation, reinforcing that foreign travel seeds infections. C. parvum incidence fell sharply but recovered post-restrictions implementation, consistent with relaxation of restrictions. Future exceedance reporting for C. hominis should exclude the post-restriction implementation period but retain it for C. parvum (except the first 6 weeks post-restrictions implementation). Infection prevention and control advice should be improved for people with gastrointestinal illness (GI) symptoms to ensure hand hygiene and swimming pool avoidance.

Outbreak trends of fatality rate into coronavirus disease-2019 using deep learning

The World Health Organization (WHO) has declared the novel coronavirus as global pandemic on 11 March 2020. It was known to originate from Wuhan, China and its spread is unstoppable due to no proper medication and vaccine. The developed forecasting models predict the number of cases and its fatality rate for coronavirus disease 2019 (COVID-19), which is highly impulsive. This paper provides intrinsic algorithms namely - linear regression and long short-term memory (LSTM) using deep learning for time series-based prediction. It also uses the ReLU activation function and Adam optimiser. This paper also reports a comparative study on existing models for COVID-19 cases from different continents in the world. It also provides an extensive model that shows a brief prediction about the number of cases and time for recovered, active and deaths rate till January 2021.Copyright © 2023 Inderscience Enterprises Ltd.

Vaccine Supply Forecasting and Optimization using Deterministic and Probabilistic Approaches

When the pandemic was at its peak, it was a quite difficult task for the government to schedule vaccine supply in various districts of a state. This task became further difficult when vaccines were required to be supplied to various Covid Vaccination Centers (CVCs) at a granular level. This is because there was no data regarding the trend being acquired at each CVC and the population distribution is non-uniform across the district. This led to the arousal of an ambiguous situation for a certain period and hence mismanagement. Now that we have sufficient data across each CVC, we can work on a time series analysis of vaccine requirements in which we can essentially forecast the number of administered doses and optimize the wastage at all atomic CVC levels. © 2023 IEEE.

Impact of the Coronavirus Disease 2019 Pandemic on Dental Visits in Japan.

PURPOSE: This study aimed to clarify the impact of the coronavirus disease 2019 (COVID-19) pandemic on individual dental-visit behaviour and examine the difference between elderly and other individuals regarding the impact on dental visits. MATERIALS AND METHODS: An interrupted time-series analysis was performed to examine the change in data from the national database before and after the first declaration of a state of emergency. RESULTS: The number of patients visiting a dental clinic (NPVDC), number of dental treatment days (NDTD) and dental expenses (DE) during the first declaration of a state of emergency decreased by 22.1%, 17.9%, and 12.5% in the group under 64 years of age and 26.1%, 26.3%, and 20.1% in the group over 65 years of age, respectively, compared with those in the same month of the previous year. Between March and June 2020, the monthly NPVDC and NDTD were significantly reduced (p < 0.001, p = 0.013) in those over 65 years of age. The DE did not change statistically significantly in either the under 64 group or the over 65 group. There was no statistically significant change in the slope of the regression line in the NPVDC, NDTD, and DE before and after the first state-of-emergency declaration. CONCLUSION: The first state of emergency greatly reduced the NPVDC, NDTD, and DE compared to those in the previous year. In people aged over 65 years, it might still be unresolved 2 years after the postponement of dental treatment owing to the first declaration of a state of emergency.

Implication of COVID-19 pandemic on the incidence of Clostridioides difficile infection in a Greek tertiary hospital.

Introduction. C. difficile infection (CDI) represents an important global threat. In the COVID-19 era, the multifactorial nature of CDI has emerged.Hypothesis - Aim. The aim was to assess the impact of COVID-19 pandemic on the incidence of CDI in a Greek hospital.Methodology. A retrospective study was performed throughout a 51 month period (January 2018 to March 2022), divided into two periods: pre-pandemic (January 2018 to February 2020) and COVID-19 pandemic (March 2020 to March 2022). The effects of the pandemic compared to the pre-pandemic period on the incidence of CDI [expressed as infections per 10 000 bed days (IBD)] were studied using interrupted time-series analysis.Results. Throughout the study, there was an increase in the monthly CDI incidence from 0.00 to 11.77 IBD (P<0.001). Interrupted time-series disclosed an increase in CDI incidence during the pre-pandemic period from 0.00 to 3.36 IBD (P<0.001). During the COVID-19 pandemic period the linear trend for monthly CDI rose from 2.65 to 13.93 IBD (P<0.001). The increase rate was higher during the COVID-19 pandemic period (r2 = +0.47) compared to the pre-pandemic period (r1 = +0.16).Conclusion. A significant increase of CDI incidence was observed, with the rate of the rise being more intense during the COVID-19 pandemic.