Machine learning-based diffusion model for prediction of coronavirus-19 outbreak.

The coronavirus pandemic has been globally impacting the health and prosperity of people. A persistent increase in the number of positive cases has boost the stress among governments across the globe. There is a need of approach which gives more accurate predictions of outbreak. This paper presents a novel approach called diffusion prediction model for prediction of number of coronavirus cases in four countries: India, France, China and Nepal. Diffusion prediction model works on the diffusion process of the human contact. Model considers two forms of spread: when the spread takes time after infecting one person and when the spread is immediate after infecting one person. It makes the proposed model different over other state-of-the art models. It is giving more accurate results than other state-of-the art models. The proposed diffusion prediction model forecasts the number of new cases expected to occur in next 4 weeks. The model has predicted the number of confirmed cases, recovered cases, deaths and active cases. The model can facilitate government to be well prepared for any abrupt rise in this pandemic. The performance is evaluated in terms of accuracy and error rate and compared with the prediction results of support vector machine, logistic regression model and convolution neural network. The results prove the efficiency of the proposed model.

External validation of the ISARIC 4C Mortality Score to predict in-hospital mortality among patients with COVID-19 in a Canadian intensive care unit: a single-centre historical cohort study.

PURPOSE: With uncertain prognostic utility of existing predictive scoring systems for COVID-19-related illness, the International Severe Acute Respiratory and Emerging Infection Consortium (ISARIC) 4C Mortality Score was developed by the International Severe Acute Respiratory and Emerging Infection Consortium as a COVID-19 mortality prediction tool. We sought to externally validate this score among critically ill patients admitted to an intensive care unit (ICU) with COVID-19 and compare its discrimination characteristics to that of the Acute Physiology and Chronic Health Evaluation (APACHE) II and Sequential Organ Failure Assessment (SOFA) scores. METHODS: We enrolled all consecutive patients admitted with COVID-19-associated respiratory failure between 5 March 2020 and 5 March 2022 to our university-affiliated and intensivist-staffed ICU (Jewish General Hospital, Montreal, QC, Canada). After data abstraction, our primary outcome of in-hospital mortality was evaluated with an objective of determining the discriminative properties of the ISARIC 4C Mortality Score, using the area under the curve of a logistic regression model. RESULTS: A total of 429 patients were included, 102 (23.8%) of whom died in hospital. The receiver operator curve of the ISARIC 4C Mortality Score had an area under the curve of 0.762 (95% confidence interval [CI], 0.717 to 0.811), whereas those of the SOFA and APACHE II scores were 0.705 (95% CI, 0.648 to 0.761) and 0.722 (95% CI, 0.667 to 0.777), respectively. CONCLUSIONS: The ISARIC 4C Mortality Score is a tool that had a good predictive performance for in-hospital mortality in a cohort of patients with COVID-19 admitted to an ICU for respiratory failure. Our results suggest a good external validity of the 4C score when applied to a more severely ill population.

RéSUMé: OBJECTIF: Compte tenu de l'utilité pronostique incertaine des systèmes de notation prédictive existants pour les maladies liées à la COVID-19, le score de mortalité ISARIC 4C a été mis au point par l'International Severe Acute Respiratory and Emerging Infection Consortium en tant qu'outil de prédiction de la mortalité associée à la COVID-19. Nous avons cherché à valider en externe ce score chez les patient·es gravement malades atteint·es de COVID-19 admis·es dans une unité de soins intensifs (USI) et à comparer ses caractéristiques de discrimination à celles des scores APACHE II (Acute Physiology and Chronic Health Evaluation) et SOFA (Sequential Organ Failure Assessment). MéTHODE: Nous avons recruté toutes les personnes consécutives admises pour insuffisance respiratoire associée à la COVID-19 entre le 5 mars 2020 et le 5 mars 2022 dans notre unité de soins intensifs affiliée à l'université et dotée d'intensivistes (Hôpital général juif, Montréal, QC, Canada). Après l'abstraction des données, notre critère d'évaluation principal de mortalité à l'hôpital a été évalué dans le but de déterminer les propriétés discriminatives du score de mortalité ISARIC 4C, en utilisant la surface sous la courbe d'un modèle de régression logistique. RéSULTATS: Au total, 429 patient·es ont été inclus·es, dont 102 (23,8 %) sont décédé·es à l'hôpital. La fonction d'efficacité du récepteur (courbe ROC) du score de mortalité ISARIC 4C avait une surface sous la courbe de 0,762 (intervalle de confiance [IC] à 95 %, 0,717 à 0,811), tandis que celles des scores SOFA et APACHE II étaient de 0,705 (IC 95%, 0,648 à 0,761) et 0,722 (IC 95%, 0,667 à 0,777), respectivement. CONCLUSION: Le score de mortalité ISARIC 4C est un outil qui a affiché une bonne performance prédictive de la mortalité à l'hôpital dans une cohorte de patient·es atteint·es de COVID-19 admis·es dans une unité de soins intensifs pour insuffisance respiratoire. Nos résultats suggèrent une bonne validité externe du score 4C lorsqu'il est appliqué à une population plus gravement malade.

Dynamic associations between the respiratory tract and gut antibiotic resistome of patients with COVID-19 and its prediction power for disease severity.

The antibiotic resistome is the collection of all antibiotic resistance genes (ARGs) present in an individual. Whether an individual's susceptibility to infection and the eventual severity of coronavirus disease 2019 (COVID-19) is influenced by their respiratory tract antibiotic resistome is unknown. Additionally, whether a relationship exists between the respiratory tract and gut ARGs composition has not been fully explored. We recruited 66 patients with COVID-19 at three disease stages (admission, progression, and recovery) and conducted a metagenome sequencing analysis of 143 sputum and 97 fecal samples obtained from them. Respiratory tract, gut metagenomes, and peripheral blood mononuclear cell (PBMC) transcriptomes are analyzed to compare the gut and respiratory tract ARGs of intensive care unit (ICU) and non-ICU (nICU) patients and determine relationships between ARGs and immune response. Among the respiratory tract ARGs, we found that Aminoglycoside, Multidrug, and Vancomycin are increased in ICU patients compared with nICU patients. In the gut, we found that Multidrug, Vancomycin, and Fosmidomycin were increased in ICU patients. We discovered that the relative abundances of Multidrug were significantly correlated with clinical indices, and there was a significantly positive correlation between ARGs and microbiota in the respiratory tract and gut. We found that immune-related pathways in PBMC were enhanced, and they were correlated with Multidrug, Vancomycin, and Tetracycline ARGs. Based on the ARG types, we built a respiratory tract-gut ARG combined random-forest classifier to distinguish ICU COVID-19 patients from nICU patients with an AUC of 0.969. Cumulatively, our findings provide some of the first insights into the dynamic alterations of respiratory tract and gut antibiotic resistome in the progression of COVID-19 and disease severity. They also provide a better understanding of how this disease affects different cohorts of patients. As such, these findings should contribute to better diagnosis and treatment scenarios.

Predicting missed health care visits during the COVID-19 pandemic using machine learning methods: evidence from 55,500 individuals from 28 European countries.

BACKGROUND: Pandemics such as the COVID-19 pandemic and other severe health care disruptions endanger individuals to miss essential care. Machine learning models that predict which patients are at greatest risk of missing care visits can help health administrators prioritize retentions efforts towards patients with the most need. Such approaches may be especially useful for efficiently targeting interventions for health systems overburdened during states of emergency. METHODS: We use data on missed health care visits from over 55,500 respondents of the Survey of Health, Ageing and Retirement in Europe (SHARE) COVID-19 surveys (June - August 2020 and June - August 2021) with longitudinal data from waves 1-8 (April 2004 - March 2020). We compare the performance of four machine learning algorithms (stepwise selection, lasso, random forest, and neural networks) to predict missed health care visits during the first COVID-19 survey based on common patient characteristics available to most health care providers. We test the prediction accuracy, sensitivity, and specificity of the selected models for the first COVID-19 survey by employing 5-fold cross-validation, and test the out-of-sample performance of the models by applying them to the data from the second COVID-19 survey. RESULTS: Within our sample, 15.5% of the respondents reported any missed essential health care visit due to the COVID-19 pandemic. All four machine learning methods perform similarly in their predictive power. All models have an area under the curve (AUC) of around 0.61, outperforming random prediction. This performance is sustained for data from the second COVID-19 wave one year later, with an AUC of 0.59 for men and 0.61 for women. When classifying all men (women) with a predicted risk of 0.135 (0.170) or higher as being at risk of missing care, the neural network model correctly identifies 59% (58%) of the individuals with missed care visits, and 57% (58%) of the individuals without missed care visits. As the sensitivity and specificity of the models are strongly related to the risk threshold used to classify individuals, the models can be calibrated depending on users' resource constraints and targeting approach. CONCLUSIONS: Pandemics such as COVID-19 require rapid and efficient responses to reduce disruptions in health care. Based on characteristics available to health administrators or insurance providers, simple machine learning algorithms can be used to efficiently target efforts to reduce missed essential care.

A prediction error based reversible data hiding scheme in encrypted image using block marking and cover image pre-processing.

A drastic change in communication is happening with digitization. Technological advancements will escalate its pace further. The human health care systems have improved with technology, remodeling the traditional way of treatments. There has been a peak increase in the rate of telehealth and e-health care services during the coronavirus disease 2019 (COVID-19) pandemic. These implications make reversible data hiding (RDH) a hot topic in research, especially for medical image transmission. Recovering the transmitted medical image (MI) at the receiver side is challenging, as an incorrect MI can lead to the wrong diagnosis. Hence, in this paper, we propose a MSB prediction error-based RDH scheme in an encrypted image with high embedding capacity, which recovers the original image with a peak signal-to-noise ratio (PSNR) of ∞ dB and structural similarity index (SSIM) value of 1. We scan the MI from the first pixel on the top left corner using the snake scan approach in dual modes: i) performing a rightward direction scan and ii) performing a downward direction scan to identify the best optimal embedding rate for an image. Banking upon the prediction error strategy, multiple MSBs are utilized for embedding the encrypted PHR data. The experimental studies on test images project a high embedding rate with more than 3 bpp for 16-bit high-quality DICOM images and more than 1 bpp for most natural images. The outcomes are much more promising compared to other similar state-of-the-art RDH methods.

Using a multiplex serological assay to estimate time since SARS-CoV-2 infection and past clinical presentation in malagasy patients.

Background: The world is facing a 2019 coronavirus (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this context, efficient serological assays are needed to accurately describe the humoral responses against the virus. These tools could potentially provide temporal and clinical characteristics and are thus paramount in developing-countries lacking sufficient ongoing COVID-19 epidemic descriptions. Methods: We developed and validated a Luminex xMAP® multiplex serological assay targeting specific IgM and IgG antibodies against the SARS-CoV-2 Spike subunit 1 (S1), Spike subunit 2 (S2), Spike Receptor Binding Domain (RBD) and the Nucleocapsid protein (N). Blood samples collected periodically for 12 months from 43 patients diagnosed with COVID-19 in Madagascar were tested for these antibodies. A random forest algorithm was used to build a predictive model of time since infection and symptom presentation. Findings: The performance of the multiplex serological assay was evaluated for the detection of SARS-CoV-2 anti-IgG and anti-IgM antibodies. Both sensitivity and specificity were equal to 100% (89.85-100) for S1, RBD and N (S2 had a lower specificity = 95%) for IgG at day 14 after enrolment. This multiplex assay compared with two commercialized ELISA kits, showed a higher sensitivity. Principal Component Analysis was performed on serologic data to group patients according to time of sample collection and clinical presentations. The random forest algorithm built by this approach predicted symptom presentation and time since infection with an accuracy of 87.1% (95% CI = 70.17-96.37, p-value = 0.0016), and 80% (95% CI = 61.43-92.29, p-value = 0.0001) respectively. Interpretation: This study demonstrates that the statistical model predicts time since infection and previous symptom presentation using IgM and IgG response to SARS-CoV2. This tool may be useful for global surveillance, discriminating recent- and past- SARS-CoV-2 infection, and assessing disease severity. Fundings: This study was funded by the French Ministry for Europe and Foreign Affairs through the REPAIR COVID-19-Africa project coordinated by the Pasteur International Network association. WANTAI reagents were provided by WHO AFRO as part of a Sero-epidemiological "Unity" Study Grant/Award Number: 2020/1,019,828-0 P·O 202546047 and Initiative 5% grant n°AP-5PC-2018-03-RO.

Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19.

Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

Impact of COVID-19 on Clinical Education for Occupational Therapy Students: A 3-Year Longitudinal Study on Fall Risk Prediction Ability.

This study aimed to examine if there were disadvantages to student learning and application when clinical education is canceled due to factors such as COVID-19 pandemic that occurred between 2020-2021. Forty occupational therapy students participated in the study, and they were classified into two groups: those with clinical education (clinical education group) and those without clinical education (inexperienced group). TP-KYT, which assesses a client's ability to predict risk related to falls, was administered in the first and final year. The inexperienced group showed less ability to predict risk related to client falls than the clinical education group.

Updates on the Biofunctionalization of Gold Nanoparticles for the Rapid and Sensitive Multiplatform Diagnosis of SARS-CoV-2 Virus and Its Proteins: From Computational Models to Validation in Human Samples.

Since the outbreak of the pandemic respiratory virus SARS-CoV-2 (COVID-19), academic communities and governments/private companies have used several detection techniques based on gold nanoparticles (AuNPs). In this emergency context, colloidal AuNPs are highly valuable easy-to-synthesize biocompatible materials that can be used for different functionalization strategies and rapid viral immunodiagnosis. In this review, the latest multidisciplinary developments in the bioconjugation of AuNPs for the detection of SARS-CoV-2 virus and its proteins in (spiked) real samples are discussed for the first time, with reference to the optimal parameters provided by three approaches: one theoretical, via computational prediction, and two experimental, using dry and wet chemistry based on single/multistep protocols. Overall, to achieve high specificity and low detection limits for the target viral biomolecules, optimal running buffers for bioreagent dilutions and nanostructure washes should be validated before conducting optical, electrochemical, and acoustic biosensing investigations. Indeed, there is plenty of room for improvement in using gold nanomaterials as stable platforms for ultrasensitive and simultaneous "in vitro" detection by the untrained public of the whole SARS-CoV-2 virus, its proteins, and specific developed IgA/IgM/IgG antibodies (Ab) in bodily fluids. Hence, the lateral flow assay (LFA) approach is a quick and judicious solution to combating the pandemic. In this context, the author classifies LFAs according to four generations to guide readers in the future development of multifunctional biosensing platforms. Undoubtedly, the LFA kit market will continue to improve, adapting researchers' multidetection platforms for smartphones with easy-to-analyze results, and establishing user-friendly tools for more effective preventive and medical treatments.

Drug Potency Prediction of SARS-CoV-2 Main Protease Inhibitors Based on a Graph Generative Model.

The prediction of a ligand potency to inhibit SARS-CoV-2 main protease (M-pro) would be a highly helpful addition to a virtual screening process. The most potent compounds might then be the focus of further efforts to experimentally validate their potency and improve them. A computational method to predict drug potency, which is based on three main steps, is defined: (1) defining the drug and protein in only one 3D structure; (2) applying graph autoencoder techniques with the aim of generating a latent vector; and (3) using a classical fitting model to the latent vector to predict the potency of the drug. Experiments in a database of 160 drug-M-pro pairs, from which the pIC50 is known, show the ability of our method to predict their drug potency with high accuracy. Moreover, the time spent to compute the pIC50 of the whole database is only some seconds, using a current personal computer. Thus, it can be concluded that a computational tool that predicts, with high reliability, the pIC50 in a cheap and fast way is achieved. This tool, which can be used to prioritize which virtual screening hits, will be further examined in vitro.

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review.

During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.

Combining virtual screening with cis-/trans-cleavage enzymatic assays effectively reveals broad-spectrum inhibitors that target the main proteases of SARS-CoV-2 and MERS-CoV.

The main protease (Mpro) of SARS-CoV-2 is essential for viral replication, which suggests that the Mpro is a critical target in the development of small molecules to treat COVID-19. This study used an in-silico prediction approach to investigate the complex structure of SARS-CoV-2 Mpro in compounds from the United States National Cancer Institute (NCI) database, then validate potential inhibitory compounds against the SARS-CoV-2 Mpro in cis- and trans-cleavage proteolytic assays. Virtual screening of ∼280,000 compounds from the NCI database identified 10 compounds with highest site-moiety map scores. Compound NSC89640 (coded C1) showed marked inhibitory activity against the SARS-CoV-2 Mpro in cis-/trans-cleavage assays. C1 strongly inhibited SARS-CoV-2 Mpro enzymatic activity, with a half maximal inhibitory concentration (IC50) of 2.69 µM and a selectivity index (SI) of >74.35. The C1 structure served as a template to identify structural analogs based on AtomPair fingerprints to refine and verify structure-function associations. Mpro-mediated cis-/trans-cleavage assays conducted with the structural analogs revealed that compound NSC89641 (coded D2) exhibited the highest inhibitory potency against SARS-CoV-2 Mpro enzymatic activity, with an IC50 of 3.05 µM and a SI of >65.57. Compounds C1 and D2 also displayed inhibitory activity against MERS-CoV-2 with an IC50 of <3.5 µM. Thus, C1 shows potential as an effective Mpro inhibitor of SARS-CoV-2 and MERS-CoV. Our rigorous study framework efficiently identified lead compounds targeting the SARS-CoV-2 Mpro and MERS-CoV Mpro.

A Novel Deep Learning-Based Classification Framework for COVID-19 Assisted with Weighted Average Ensemble Modeling.

COVID-19 is an infectious disease caused by the deadly virus SARS-CoV-2 that affects the lung of the patient. Different symptoms, including fever, muscle pain and respiratory syndrome, can be identified in COVID-19-affected patients. The disease needs to be diagnosed in a timely manner, otherwise the lung infection can turn into a severe form and the patient's life may be in danger. In this work, an ensemble deep learning-based technique is proposed for COVID-19 detection that can classify the disease with high accuracy, efficiency, and reliability. A weighted average ensemble (WAE) prediction was performed by combining three CNN models, namely Xception, VGG19 and ResNet50V2, where 97.25% and 94.10% accuracy was achieved for binary and multiclass classification, respectively. To accurately detect the disease, different test methods have been proposed and developed, some of which are even being used in real-time situations. RT-PCR is one of the most successful COVID-19 detection methods, and is being used worldwide with high accuracy and sensitivity. However, complexity and time-consuming manual processes are limitations of this method. To make the detection process automated, researchers across the world have started to use deep learning to detect COVID-19 applied on medical imaging. Although most of the existing systems offer high accuracy, different limitations, including high variance, overfitting and generalization errors, can be found that can degrade the system performance. Some of the reasons behind those limitations are a lack of reliable data resources, missing preprocessing techniques, a lack of proper model selection, etc., which eventually create reliability issues. Reliability is an important factor for any healthcare system. Here, transfer learning with better preprocessing techniques applied on two benchmark datasets makes the work more reliable. The weighted average ensemble technique with hyperparameter tuning ensures better accuracy than using a randomly selected single CNN model.

Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19.

Background: Most existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission. Methods: We conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance. Results: A total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722-0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set. Conclusion: An easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.

A crowd clustering prediction and captioning technique for public health emergencies.

The COVID-19 pandemic has come to the end. People have started to consider how quickly different industries can respond to disasters due to this public health emergency. The most noticeable aspect of the epidemic regarding news text generation and social issues is detecting and identifying abnormal crowd gatherings. We suggest a crowd clustering prediction and captioning technique based on a global neural network to detect and caption these scenes rapidly and effectively. We superimpose two long convolution lines for the residual structure, which may produce a broad sensing region and apply our model's fewer parameters to ensure a wide sensing region, less computation, and increased efficiency of our method. After that, we can travel to the areas where people are congregating. So, to produce news material about the present occurrence, we suggest a double-LSTM model. We train and test our upgraded crowds-gathering model using the ShanghaiTech dataset and assess our captioning model on the MSCOCO dataset. The results of the experiment demonstrate that using our strategy can significantly increase the accuracy of the crowd clustering model, as well as minimize MAE and MSE. Our model can produce competitive results for scene captioning compared to previous approaches.

Identification of 3 key genes as novel diagnostic and therapeutic targets for OA and COVID-19.

Background: Corona Virus Disease 2019 (COVID-19) and Osteoarthritis (OA) are diseases that seriously affect the physical and mental health and life quality of patients, particularly elderly patients. However, the association between COVID-19 and osteoarthritis at the genetic level has not been investigated. This study is intended to analyze the pathogenesis shared by OA and COVID-19 and to identify drugs that could be used to treat SARS-CoV-2-infected OA patients. Methods: The four datasets of OA and COVID-19 (GSE114007, GSE55235, GSE147507, and GSE17111) used for the analysis in this paper were obtained from the GEO database. Common genes of OA and COVID-19 were identified through Weighted Gene Co-Expression Network Analysis (WGCNA) and differential gene expression analysis. The least absolute shrinkage and selection operator (LASSO) algorithm was used to screen key genes, which were analyzed for expression patterns by single-cell analysis. Finally, drug prediction and molecular docking were carried out using the Drug Signatures Database (DSigDB) and AutoDockTools. Results: Firstly, WGCNA identified a total of 26 genes common between OA and COVID-19, and functional analysis of the common genes revealed the common pathological processes and molecular changes between OA and COVID-19 are mainly related to immune dysfunction. In addition, we screened 3 key genes, DDIT3, MAFF, and PNRC1, and uncovered that key genes are possibly involved in the pathogenesis of OA and COVID-19 through high expression in neutrophils. Finally, we established a regulatory network of common genes between OA and COVID-19, and the free energy of binding estimation was used to identify suitable medicines for the treatment of OA patients infected with SARS-CoV-2. Conclusion: In the present study, we succeeded in identifying 3 key genes, DDIT3, MAFF, and PNRC1, which are possibly involved in the development of both OA and COVID-19 and have high diagnostic value for OA and COVID-19. In addition, niclosamide, ciclopirox, and ticlopidine were found to be potentially useful for the treatment of OA patients infected with SARS-CoV-2.

The Impact of COVID-19 Lockdown on Ambient Air Quality in Shanghai, 2022

The COVID-19 lockdown contributes to the improvement of air quality. Most previous studies have attributed this to the reduction of human activity while ignoring the meteorological changes, this may lead to an overestimation or underestimation of the impact of COVID-19 lockdown measures on air pollution levels. To investigate this issue, we propose an XGBoost-based model to predict the concentrations of PM2.5 and PM10 during the COVID-19 lockdown period in 2022, Shanghai, and thus explore the limits of anthropogenic emission on air pollution levels by comprehensively employing the meteorological factors and the concentrations of other air pollutants. Results demonstrate that actual observations of PM2.5 and PM10 during the COVID-19 lockdown period were reduced by 60.81% and 43.12% compared with the predicted values (regarded as the period without the lockdown measures). In addition, by comparing with the time series prediction results without considering meteorological factors, the actual observations of PM2.5 and PM10 during the lockdown period were reduced by 50.20% and 19.06%, respectively, against the predicted values during the non-lockdown period. The analysis results indicate that ignoring meteorological factors will underestimate the positive impact of COVID-19 lockdown measures on air quality. © 2023 by the authors.

Travel behavior adjustment based epidemic spreading model and prediction for COVID-19

Owing to the continuous variant of the COVID-19 virus, the present epidemic may persist for a long time, and each breakout displays strongly region/time-dependent characteristics. Predicting each specific burst is the basic task for the corresponding strategies. However, the refinement of prevention and control measures usually means the limitation of the existing records of the evolution of the spread, which leads to a special difficulty in making predictions. Taking into account the interdependence of people' s travel behaviors and the epidemic spreading, we propose a modified logistic model to mimic the COVID-19 epidemic spreading, in order to predict the evolutionary behaviors for a specific bursting in a megacity with limited epidemic related records. It continuously reproduced the COVID-19 infected records in Shanghai, China in the period from March 1 to June 28, 2022. From December 7, 2022 when Mainland China adopted new detailed prevention and control measures, the COVID-19 epidemic broke out nationwide, and the infected people themselves took "ibuprofen” widely to relieve the symptoms of fever. A reasonable assumption is that the total number of searches for the word "ibuprofen” is a good representation of the number of infected people. By using the number of searching for the word "ibuprofen” provided on Baidu, a famous searching platform in Mainland China, we estimate the parameters in the modified logistic model and predict subsequently the epidemic spreading behavior in Shanghai, China starting from December 1, 2022. This situation lasted for 72 days. The number of the infected people increased exponentially in the period from the beginning to the 24th day, reached a summit on the 31st day, and decreased exponentially in the period from the 38th day to the end. Within the two weeks centered at the summit, the increasing and decreasing speeds are both significantly small, but the increased number of infected people each day was significantly large. The characteristic for this prediction matches very well with that for the number of metro passengers in Shanghai. It is suggested that the relevant departments should establish a monitoring system composed of some communities, hospitals, etc. according to the sampling principle in statistics to provide reliable prediction records for researchers. © 2023 Chinese Physical Society.

COVID-19 Data Prediction and Visualization in Mainland China

Contemporarily, COVID-19 shows a sign of recurrence in Mainland China. To better understand the situation, this paper investigates the growth pattern of COVID-19 based on the research of past data through regression models. The proposed work collects the data on COVID-19 in Mainland China from January 21st, 2020, to April 30th, 2020, including confirmed, recovered, and death cases. Based on polynomial regression and support vector machine regressor, it predicts the further trend of COVID-19. The paper uses root mean squared error to evaluate the performance of both models and concludes that there is no best model due to the high frequency of daily changes. According to the analysis, support vector machine regressors fit the growth of COVID-19 confirmed case better than polynomial regression does. The best solution is to utilize different types of models to generate a range of prediction result. These results shed light on guiding further exploration of the growth of COVID-19. © 2023 SPIE.

Predicting the climate impact of aviation for en-route emissions: the algorithmic climate change function submodel ACCF 1.0 of EMAC 2.53

Using climate-optimized flight trajectories is one essential measure to reduce aviation's climate impact. Detailed knowledge of temporal and spatial climate sensitivity for aviation emissions in the atmosphere is required to realize such a climate mitigation measure. The algorithmic Climate Change Functions (aCCFs) represent the basis for such purposes. This paper presents the first version of the Algorithmic Climate Change Function submodel (ACCF 1.0) within the European Centre HAMburg general circulation model (ECHAM) and Modular Earth Submodel System (MESSy) Atmospheric Chemistry (EMAC) model framework. In the ACCF 1.0, we implement a set of aCCFs (version 1.0) to estimate the average temperature response over 20 years (ATR20) resulting from aviation CO2 emissions and non-CO2 impacts, such as NOx emissions (via ozone production and methane destruction), water vapour emissions, and contrail cirrus. While the aCCF concept has been introduced in previous research, here, we publish a consistent set of aCCF formulas in terms of fuel scenario, metric, and efficacy for the first time. In particular, this paper elaborates on contrail aCCF development, which has not been published before. ACCF 1.0 uses the simulated atmospheric conditions at the emission location as input to calculate the ATR20 per unit of fuel burned, per NOx emitted, or per flown kilometre.In this research, we perform quality checks of the ACCF 1.0 outputs in two aspects. Firstly, we compare climatological values calculated by ACCF 1.0 to previous studies. The comparison confirms that in the Northern Hemisphere between 150–300 hPa altitude (flight corridor), the vertical and latitudinal structure of NOx-induced ozone and H2O effects are well represented by the ACCF model output. The NOx-induced methane effects increase towards lower altitudes and higher latitudes, which behaves differently from the existing literature. For contrail cirrus, the climatological pattern of the ACCF model output corresponds with the literature, except that contrail-cirrus aCCF generates values at low altitudes near polar regions, which is caused by the conditions set up for contrail formation. Secondly, we evaluate the reduction of NOx-induced ozone effects through trajectory optimization, employing the tagging chemistry approach (contribution approach to tag species according to their emission categories and to inherit these tags to other species during the subsequent chemical reactions). The simulation results show that climate-optimized trajectories reduce the radiative forcing contribution from aviation NOx-induced ozone compared to cost-optimized trajectories. Finally, we couple the ACCF 1.0 to the air traffic simulation submodel AirTraf version 2.0 and demonstrate the variability of the flight trajectories when the efficacy of individual effects is considered. Based on the 1 d simulation results of a subset of European flights, the total ATR20 of the climate-optimized flights is significantly lower (roughly 50 % less) than that of the cost-optimized flights, with the most considerable contribution from contrail cirrus. The CO2 contribution observed in this study is low compared with the non-CO2 effects, which requires further diagnosis.