Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data

In this paper, we approach the problem of detecting and diagnosing COVID-19 infections using multisource scan images including CT and X-ray scans to assist the healthcare system during the COVID-19 pandemic. Here, a computer-aided diagnosis (CAD) system is proposed that utilizes analysis of the CT or X-ray to diagnose the impact of damage in the respiratory system per infected case. The CAD was utilized and optimized by hyper-parameters for shallow learning, e.g., SVM and deep learning. For the deep learning, mini-batch stochastic gradient descent was used to overcome fitting problems during transfer learning. The optimal parameter list values were found using the naïve Bayes technique. Our contributions are (i) a comparison among the detection rates of pre-trained CNN models, (ii) a suggested hybrid deep learning with shallow machine learning, (iii) an extensive analysis of the results of COVID-19 transition and informative conclusions through developing various transfer techniques, and (iv) a comparison of the accuracy of the previous models with the systems of the present study. The effectiveness of the proposed CAD is demonstrated using three datasets, either using an intense learning model as a fully end-to-end solution or using a hybrid deep learning model. Six experiments were designed to illustrate the superior performance of our suggested CAD when compared to other similar approaches. Our system achieves 99.94, 99.6, 100, 97.41, 99.23, and 98.94 accuracy for binary and three-class labels for the CT and two CXR datasets.

Advanced Physiotherapy of Supracondylar Femur Fracture with Implant In situ: A Case Report

Patient main concerns were restriction of movements of right knee and pus discharge from wound over right knee. In this case, the main clinical findings were a substantial loss in range of motion at right knee joints. There was also fixed flexion deformity seen over right knee. Diagnosis of the case was non united operated infected case of supracondylar femur fracture right side with implant in situ. In these types of circumstances, therapeutic approaches have been demonstrated to be useful. A 35-year-old male visited the orthopaedics who referred department of physiotherapy with complaints of restriction of movement of right knee and pus discharge from wound over right knee. Patient was examine in standing and supine position .On inspection, patient keeps right hip in flexion, knee in flexion patella pointing upwards and foot in equinus. According to the research, starting weight-bearing too soon can lead to failure of implant and mal-union. Supracondylar femoral fracture is a challenging condition to deal with and is associated with many secondary complications. An important role is played by physiotherapist in rehabilitation and supracondylar femur fracture management.

Individual-level Evaluation of the Exposure Notification Cascade in the SwissCovid Digital Proximity Tracing App: An Observational Study (Preprint)

BACKGROUND Digital proximity tracing (DPT) aims to complement manual contact tracing (MCT) in identifying exposed contacts and preventing further transmission of SARS-CoV-2 in the population. While several DPT apps, including SwissCovid, have shown to have promising effects on mitigating the pandemic, several challenges have impeded them from fully achieving the desired results. A key question now relates to how the effectiveness of DPT can be improved which requires better understanding of factors influencing its processes. OBJECTIVE In this study, we aimed to provide a detailed examination of the exposure notification (EN) cascade and to evaluate potential contextual influences for successful receipt of EN and subsequent actions taken by cases and contacts in different exposure settings. METHODS We used data from 285 pairs of SARS-CoV-2-infected cases and their contacts within an observational cohort study of cases and contacts identified by MCT and enrolled between 06 August and 17 January 2021 in the Canton of Zurich, Switzerland. We surveyed participants with electronic questionnaires. Data were summarized descriptively and stratified by exposure setting. RESULTS We found that only 60% of contacts using the app whose corresponding case reported to have triggered the EN also received one. Among those, 23% received the EN before being contacted by MCT. Compared to those receiving an EN after MCT, we observed that a higher proportion of contacts receiving an EN before MCT were exposed in non-household settings (67% versus 56%) and their corresponding cases had more frequently reported mild to moderate symptoms (78% versus 69%). Among the 18 contacts receiving an EN before MCT, 14 (78%) took preventive measures: 12 (67%) were tested for SARS-CoV-2 and 7 (39%) called the SwissCovid Infoline. In non-household settings, the proportion of contacts taking preventive actions after receiving an EN was higher compared to same-household settings (82% versus 67%). One in eleven ENs received before MCT led to the identification of a SARS-CoV-2-infected case by prompting the contact to get tested. This corresponds to one in 85 exposures of a contact to a case in a non-household setting, in which both were app users and the case triggered the EN. CONCLUSIONS Our descriptive evaluation of the DPT notification cascade provides further evidence that DPT is an important complementary tool in pandemic mitigation, especially in non-household exposure settings. However, the effect of DPT apps can only be exerted if code generation processes are efficient and exposed contacts are willing to undertake preventive actions. This highlights the need to focus efforts on keeping barriers to efficient code generation as low as possible and promoting not only app adoption but also compliance with the recommended measures upon EN. CLINICALTRIAL ISRCTN14990068

Numbers of close contacts of individuals infected with SARS-CoV-2 and their association with government intervention strategies

Background Contact tracing is conducted with the primary purpose of interrupting transmission from individuals who are likely to be infectious to others. Secondary analyses of data on the numbers of close contacts of confirmed cases could also: provide an early signal of increases in contact patterns that might precede larger than expected case numbers; evaluate the impact of government interventions on the number of contacts of confirmed cases; or provide data information on contact rates between age cohorts for the purpose of epidemiological modelling. We analysed data from 140,204 close contacts of 39,861 cases in Ireland from 1st May to 1st December 2020. Results Negative binomial regression models highlighted greater numbers of contacts within specific population demographics, after correcting for temporal associations. Separate segmented regression models of the number of cases over time and the average number of contacts per case indicated that a breakpoint indicating a rapid decrease in the number of contacts per case in October 2020 preceded a breakpoint indicating a reduction in the number of cases by 11 days. Conclusions We found that the number of contacts per infected case was overdispersed, the mean varied considerable over time and was temporally associated with government interventions. Analysis of the reported number of contacts per individual in contact tracing data may be a useful early indicator of changes in behaviour in response to, or indeed despite, government restrictions. This study provides useful information for triangulating assumptions regarding the contact mixing rates between different age cohorts for epidemiological modelling.

The Transmission Dynamic of the COVID 19 Outbreak: A Predictive Dashboard

COVID 19 outbreak gives a great impact worldwide. The disaster of this pandemic has resulted in a large number of human lives being lost. As all countries implemented quarantine and social distancing, the great lockdown all over the world lead to multiple crises including health, economy, financial, and collapse in industrial and educational activities. Movement Control Order (MCO) and social distancing which have been implemented as control measures in Malaysia also affected many sectors. The landscape now has successfully reduced the number of infected people. However, from the economic point of view, the Retail Group Malaysia (RGM) has projected the country’s retail industry suffers a negative growth rate for the first time in 22 years. If the epidemic continues, society will reach an impasse, a time when the lockdown will become more than some of them can tolerate. As recognized by the World Health Organization (WHO), modelling the outbreak based on the prior input data is more appropriate than the ‘risk of bias’ for decision-makers. Thus, this research is conducted to model the outbreak of the disease using the susceptible-infected-recovery-death (SIRD) compartmental model accompanying with the varying infection rate due to changes in MCO measures. The model assumes under the unavailability of the vaccine, recovered people can be reinfected. The epidemic parameters and reproduction numbers are estimated and fitted from the transmission model to the actual data using the Monte Carlo Markov Chain (MCMC) of Metropolis-Hasting. The model is solved using a numerical algorithm of the Runge-Kutta method. The predictive dashboard of a graphical user interface (GUI) is developed, hence monitoring and predicting the outbreak under the control measures of the two different types of MCO scenarios (which are called constant and alternate scenarios) can be performed. GUI for the dynamic transmission of the COVID 19 provides insight for the future outbreak, hence may help the respective stakeholders to propose the best policy of a new norm for all sectors. From the GUI, we can see that, when no or loose MCO is implemented or compliance of the public to the COVID 19 standard operating procedure (SOP), the infected case will increase rapidly up to 7.5 million. With strict MCO regulation or public obedient to the SOP, the infected case will decrease rapidly, but even after a long period of strict regulation, once the quarantine is stopped, the infected case will rise again. An alternative MCO scenario is suggested where a cyclic pattern of strict and loose MCO regulation is upheld, and it shows to flatten the curve while allow periods of less restricted lifestyle. This can be one of the alternatives to balance the life and livelihood.

Implications of Delayed Reopening in Controlling the COVID-19 Surge in Southern and West-Central USA

In the wake of the rapid surge in the COVID-19-infected cases seen in Southern and West-Central USA in the period of June-July 2020, there is an urgent need to develop robust, data-driven models to quantify the effect which early reopening had on the infected case count increase. In particular, it is imperative to address the question: How many infected cases could have been prevented, had the worst affected states not reopened early? To address this question, we have developed a novel COVID-19 model by augmenting the classical SIR epidemiological model with a neural network module. The model decomposes the contribution of quarantine strength to the infection time series, allowing us to quantify the role of quarantine control and the associated reopening policies in the US states which showed a major surge in infections. We show that the upsurge in the infected cases seen in these states is strongly corelated with a drop in the quarantine/lockdown strength diagnosed by our model. Further, our results demonstrate that in the event of a stricter lockdown without early reopening, the number of active infected cases recorded on 14 July could have been reduced by more than 40% in all states considered, with the actual number of infections reduced being more than 100,000 for the states of Florida and Texas. As we continue our fight against COVID-19, our proposed model can be used as a valuable asset to simulate the effect of several reopening strategies on the infected count evolution, for any region under consideration.

Epidemic Location Intelligence System as Response to the COVID-19 Outbreak in Bosnia and Herzegovina

The outbreak of COVID-19 is a public health emergency that caused disastrous results in many countries. The global aim is to stop transmission and prevent the spread of the disease. To achieve it, every country needs to scale up emergency response mechanisms, educate and actively communicate with the public, intensify infected case finding, contact tracing, monitoring, quarantine of contacts, and isolation of cases. Responding to an emergency requires efficient collaboration and a multi-skilled approach (medical, information, statistical, political, social, and other expertise), which makes it hard to define one interface for all. As actors from different perspectives and domain backgrounds need to address diverse functions, the possibility to exchange available information quickly would be desirable. In Bosnia and Herzegovina, a joint state-level public health institution has not been established, but is covered by entity competencies. In this sense, a geoportal has been developed as an epidemiological location-intelligence system (ELIS) that supports the exchange of such information between the entities and the cantons. For its development, open source software components in the cloud were used as a working platform with all the necessary functionalities. The geoportal provides an entry point for access to geospatial, epidemiological, environmental and statistical data used for analysis, geocoding of confirmed COVID-19 cases, identification of disease dynamics, identification of vulnerable groups, mapping of health capacities, and general modeling of infection spread with application support for communication and collaboration between all institutions and the public. The paper describes the challenges and ways to overcome them in the development and use of ELIS.

Epidemic Location Intelligence System as Response to the COVID-19 Outbreak in Bosnia and Herzegovina

The outbreak of COVID-19 is a public health emergency that caused disastrous results in many countries. The global aim is to stop transmission and prevent the spread of the disease. To achieve it, every country needs to scale up emergency response mechanisms, educate and actively communicate with the public, intensify infected case finding, contact tracing, monitoring, quarantine of contacts, and isolation of cases. Responding to an emergency requires efficient collaboration and a multi-skilled approach (medical, information, statistical, political, social, and other expertise), which makes it hard to define one interface for all. As actors from different perspectives and domain backgrounds need to address diverse functions, the possibility to exchange available information quickly would be desirable. Geoportal provides an entry point to access a variety of data (geospatial data, epidemiological data) and could be used for data discovery, view, download, and transformation. It helps to deal with challenges like data analysis, confirmed cases geocoding, recognition of disease dynamics, vulnerable groups identification, and capacity mapping. Predicting and modeling the spread of infection, along with application support for communication and collaboration, are the biggest challenges. In response to all these challenges, we have established the Epidemic Location Intelligence System (ELIS) using open-source software components in the cloud, as a working platform with all the required functionalities.

Trends in COVID-19 Infected Cases Based on Panel Data Regression Modelling

Background and Objective: The novel coronavirus pandemic, known as COVID-19, could not have been more predictable; thus, the world encountered health crises and substantial economic crises. This paper analysed the trends in COVID-19 cases in October 2020 in four southern districts of Tamil Nadu state, India, using a panel regression model. Materials and Methods: Panel data on the number of COVID-19-infected cases were collected from daily bulletins published through the official website www.stopcorona.tn.gov.in maintained by the Government of Tamil Nadu state, India. Panel data regression models were employed to study the trends. EViews Ver.11. Software was used to estimate the model and its parameters. Results: In all four districts, the COVID-19-infected case data followed a normal distribution. Maximum numbers of COVID-19-infected cases were registered in Kanniyakumari, followed by Tirunelveli, Thoothukudi and Tenkasi districts. The fewest COVID-19 cases were registered in Tenkasi, followed by Tirunelveli, Thoothukudi and Kanniyakumari districts. A random effects model was found to be an appropriate model to study the trend.Conclusion: The panel data regression model is found to be more appropriate than traditional models. The Hausman test and Wald test confirmed the selection of the random effects model. The Jarque-Bera normality test ensured the normality of the residuals. In all four districts under study, the number of COVID-19 infections showed a decreasing trend at a rate of 1.68% during October 2020.

Estimating Trends in COVID-19 Infected Cases Based on Panel Data Regression Modelling

Background and Objective: The novel coronavirus pandemic, known as COVID-19, could not have been more predictable; thus, the world encountered health crises and substantial economic crises. This paper analysed the trends in COVID-19 cases in October 2020 in four southern districts of Tamil Nadu state, India, using a panel regression model. Materials and Methods: Panel data on the number of COVID-19-infected cases were collected from daily bulletins published through the official website www.stopcorona.tn.gov.in maintained by the Government of Tamil Nadu state, India. Panel data regression models were employed to study the trends. EViews Ver.11. Software was used to estimate the model and its parameters. Results: In all four districts, the COVID-19-infected case data followed a normal distribution. Maximum numbers of COVID-19-infected cases were registered in Kanniyakumari, followed by Tirunelveli, Thoothukudi and Tenkasi districts. The fewest COVID-19 cases were registered in Tenkasi, followed by Tirunelveli, Thoothukudi and Kanniyakumari districts. A random effects model was found to be an appropriate model to study the trend.Conclusion: The panel data regression model is found to be more appropriate than traditional models. The Hausman test and Wald test confirmed the selection of the random effects model. The Jarque-Bera normality test ensured the normality of the residuals. In all four districts under study, the number of COVID-19 infections showed a decreasing trend at a rate of 1.68% during October 2020.