An observer comparison study to evaluate a machine learning model to quantify the infected pneumonia on lung CT images

Quantification of infected lung volume using computed tomography (CT) images can play a critical role in predicting the severity of pulmonary infectious disease. Manual segmentation of infected areas from several CT image slices, however, is not efficient and viable in clinical practice. To assist clinicians in overcoming this challenge, we developed a new method to automatically segment and quantify the percentage of the infected lung volume. First, we used a public dataset of 20 COVID-19 patients, which consists of manually annotated lung and infection masks, to train a new joint deep learning (DL) model for lung and infection segmentation. As for lung segmentation, a Mask-RCNN model was applied to the lung volume with a novel postprocessing technique. Following that, an ensemble model with a customized residual attention UNet model and feature pyramid network (FPN) models was employed for infection segmentation. Next, we assembled another set of 80 CT scans of Covid-19 patients. Two chest radiologists manually evaluated each CT scan and reported the infected lung volume percentage using a customized graphical user interface (GUI). The developed DL-model was also employed to process these CT images. Then, we compared the agreement between the radiologist (manual) and model-based (automated) percentages of diseased regions. Additionally, the GUI was used to let radiologists rate acceptance of the DL-model generated segmentation results. Analyzing the results demonstrate that the agreement between manual and automated segmentation is >95% in 28 testing cases. Furthermore, >53% of testing cases received the top assessment rating scores from two radiologists (between four-five- score). Thus, this study illustrates the feasibility of developing a DL-model based automated tool to effectively provide quantitative evaluation of infected lung regions to assist in improving the efficiency of radiologists in infection diagnosis. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

A Hybrid CNN-LSTM Model with Word-Emoji Embedding for Improving the Twitter Sentiment Analysis on Indonesia's PPKM Policy

The policy of limiting community mobilization is implemented to reduce the daily rate of COVID-19. However, a high-accuracy sentiment analysis model can determine public sentiment toward such policies. Our research aims to improve the accuracy of the LSTM model on sentiment analysis of the Jakarta community towards PPKM using Indonesian language Tweets with emoji embedding. The first stage is modeling using the hybrid CNN-LSTM model. It is a combination between CNN and LSTM. The CNN model cites word embedding and emoji embedding features that reflect the dependence on temporary short-term sentiment. At the same time, LSTM builds long-term sentiment relationships between words and emojis. Next, the model evaluation uses Accuracy, Loss, the receiver operating curve (ROC), the precision and recall curve, and the area under curve (AUC) value to see the performance of the designed model. Based on the results of the tests, we conclude that the CNN-LSTM Hybrid Model performs better with the words+emoji dataset. The ROC AUC is 0.966, while the precision-recall curve AUC is 0.957. © 2022 IEEE.

Epidemic Prediction using Machine Learning and Deep Learning Models on COVID-19 Data

A catastrophic epidemic of Severe Acute Respiratory Syndrome-Coronavirus, commonly recognised as COVID-19, introduced a worldwide vulnerability to human community. All nations around the world are making enormous effort to tackle the outbreak towards this deadly virus through various aspects such as technology, economy, relevant data, protective gear, lives-risk medications and all other instruments. The artificial intelligence-based researchers apply knowledge, experience and skill set on national level data to create computational and statistical models for investigating such a pandemic condition. In order to make a contribution to this worldwide human community, this paper recommends using machine-learning and deep-learning models to understand its daily accelerating actions together with predicting the future reachability of COVID-19 across nations by using the real-time information from the Johns Hopkins dashboard. In this work, a novel Exponential Smoothing Long-Short-Term Memory Networks Model (ESLSTM) learning model is proposed to predict the virus spread in the near future. The results are evaluated using RMSE and R-Squared values.

A New Hybrid Artificial Intelligence Model for Diseases Identification

Artificial intelligence is increasingly applied in many fields, specially in medicine to assist patients and physicians. Growing datasets provide a sound basis to adapt machine learning methods to identify and detect some diseases. These later, are often very similar which make difficult their identification by chest X-ray images. In this paper, we introduce a diagnostic AI model that allow to separate, diagnose and classify three various diseases: tuberculosis, covid19 and Pneumonia. The proposed model is based on a combination of Deep Learning using the deep SqueezeNet model and Machine Learning: SVM, KNN, Logistic Regression, decision tree and Naive Bayes. The model is applied to a chest X-ray dataset containing images for each type of disease. To train and test our model, we split the image dataset into two training and test subsets in order to differentiate between different disease types. The accuracy show clearly that our model provides better results of diagnosis and identification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Classification of Covid19 Vaccine-Related Tweets Using Deep Learning

In recent years, the majority of the world's population has been impacted by the COVID-19 pandemic, but owing to the invention of vaccinations, the epidemic has been brought under control. Most people are hesitant to share their experiences on official platforms after being vaccinated. As a result, information about vaccine-related adverse effects other than clinical trial results is challenging to identify. However, most people have shared their opinions about vaccines on social media since the COVID-19 immunization program began worldwide. This study aims to assess, using social media, the adverse effects of the COVID-19 vaccination as perceived by the general population. The authors of the previous studies did not categorize tweets on the COVID-19 vaccine adverse effects as personal experience, informative, or advice-seeking. The authors of this study aim to classify tweets in the manner described above to fill a research gap and increase public awareness of the COVID-19 vaccine's side effects. The Kaggle repository collected tweets pertaining to COVID-19 vaccinations for this investigation. The authors manually classified collected tweets into two categories: those connected to COVID-19 vaccinations' adverse effects and those unrelated to COVID-19 vaccines' adverse effects. Then, valid tweets were further classified into three categories: personal experience, informative, and seeking advice. The authors then used the data to train four ML models. There are also SVM, Logistic Regression, LSTM, and ANN. The LSTM algorithm generated the most outstanding results, with an accuracy of 97.64&. In addition, the researchers conclude that the SVM may not be suitable for planned research since it gave the lowest degree of accuracy, 80%. © 2022 IEEE.

Sequential spatiotemporal distribution of PM2.5, SO2 and Ozone in China from 2015 to 2020

Currently, in the modeling of various atmospheric pollutants, the simulation of independent trace gases (SO2 and O3) is constrained by the insufficient resolution of key remote sensing products, resulting in insufficient simulation reliability. In this study, spatial sampling and parameter convolution are combined to optimize LightGBM by utilizing ground observations, remote sensing products, meteorological data, assistance data, and random ID. Through the above techniques and an sequentialsimulation of air pollutants, we produce seamless daily 1-km-resolution products of PM2.5, SO2 and O3 for most parts of China from 2015 to 2020. Through random sampling, random site sampling, area-specific validation, comparisons of different models, and a cross26 sectional comparison of different studies, we verified that our simulations of the spatial distribution of multiple atmospheric pollutants are reliable and effective. The CV of the random sample yielded an R² of 0.88 and an RMSE of 9.91 ㎍/m³ for PM2.5, an R² of 0.89 and an RMSE of 4.62 ㎍/m³ for SO2, and an R² of 0.91 and an RMSE of 6.88 ㎍/m3 for O3. Combined with the SHapley Additive exPlanations (SHAP) approach, the roles of different parameters in the simulation process were clarified, and the positive role of parameter convolution was confirmed. Our dataset was used to assess the changes in the Air Pollution Index (API) in China before and after the outbreak of COVID-19, and the results indicate that these 34 changes were relatively small huge, suggesting that the epidemic control measures in 2020 were effective. The study demonstrates that the multipollutant datasets produced with the proposed models are of great value for long-term, large-scale, and regional-scale air pollution monitoring and prediction, as well as population health evaluation. [ABSTRACT FROM AUTHOR] Copyright of Earth System Science Data Discussions is the property of Copernicus Gesellschaft mbH and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Prediction of Unemployment using Machine Learning Approach

Unemployment is a circumstance which arises when people above a specific age are not engaged in any kind of activities which contribute to the economic welfare of the individual and country. Unemployment is becoming a rising concern which is making the daily life of people difficult. Unemployment causes poverty and depression among the citizens. Nowadays there are different opportunities in different sectors. But people are not aware of those opportunities. Different states are there where there is a lack of skilled labour whereas many states are there that have skilled labour but less opportunities. Another reason for unemployment since 2020 is the COVID-19 pandemic. We have selected this topic to spread awareness among the citizens. This work attempts to detect the states of India which are in serious need of increasing employment opportunities. We have applied the concept of Supervised Machine Learning algorithms to detect the states with the lowest employment rate. The data visualization gives a better picture of the trends in unemployment rate over years. There has been a use of different popular algorithms like Logistic Regression, Support Vector Machine, K-nearest neighbors (kNN) Algorithm and Decision Tree. In the end we have tried to find the algorithm which is going to give us more accuracy so that necessary steps can be taken for the employment of the eligible and deserving people. © 2022 IEEE.

Pandemic Effect of COVID-19: Identification, Present Scenario, and Preventive Measures Using Machine Learning Model

Mutation in viruses is known to be an unavoidable phenomenon. But at times, it may become a life-threatening pandemic just like in the case of the 2019 novel coronavirus, formally named as SARS-CoV-2, which consumed around 36,405 lives out of 750,890 infections as per the data available with the World Health Organization as of the end of March 2020. Found to be from the family of earlier known outbreaks (SARS and MERS) of the twenty-first century, it has now become a public health emergency of international concern (PHEIC). Countries around the world have spent millions of dollars to get a positive sign of finding vaccines, but still it remains an unsolved mystery. Even though there is implementation of strict lockdown measures from several affected countries around the globe, the trend line of COVID-19 epidemic is still increasing exponentially. Being in this scenario, this paper deals about the outbreak of 2019-nCoV and its structure, growing stages, global statistics, transmission modes, and most possible precautionary methods and also its emphasis on creating public awareness by answering few key clarifications about novel beta coronavirus disease. The machine learning method used in this study was taught using records from COVID-positive tests. Results from a week were included in the testing set (individuals who were confirmed to have COVID-19). This proposed model predicted the COVID-19 lab findings with high accuracy by only using eight numeric data, age 60, knowing contact with an infected individual, and the existence of five early clinical signs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

A methylation clock model of mild SARS-CoV-2 infection provides insight into immune dysregulation.

DNA methylation comprises a cumulative record of lifetime exposures superimposed on genetically determined markers. Little is known about methylation dynamics in humans following an acute perturbation, such as infection. We characterized the temporal trajectory of blood epigenetic remodeling in 133 participants in a prospective study of young adults before, during, and after asymptomatic and mildly symptomatic SARS-CoV-2 infection. The differential methylation caused by asymptomatic or mildly symptomatic infections was indistinguishable. While differential gene expression largely returned to baseline levels after the virus became undetectable, some differentially methylated sites persisted for months of follow-up, with a pattern resembling autoimmune or inflammatory disease. We leveraged these responses to construct methylation-based machine learning models that distinguished samples from pre-, during-, and postinfection time periods, and quantitatively predicted the time since infection. The clinical trajectory in the young adults and in a diverse cohort with more severe outcomes was predicted by the similarity of methylation before or early after SARS-CoV-2 infection to the model-defined postinfection state. Unlike the phenomenon of trained immunity, the postacute SARS-CoV-2 epigenetic landscape we identify is antiprotective.

Effects of Antecedent Precipitation Amount and COVID-19 Lockdown on Water Quality along an Urban Gradient

Water quality is affected by multiple spatial and temporal factors, including the surrounding land characteristics, human activities, and antecedent precipitation amounts. However, identifying the relationships between water quality and spatially and temporally varying environmental variables with a machine learning technique in a heterogeneous urban landscape has been understudied. We explore how seasonal and variable precipitation amounts and other small-scale landscape variables affect E. coli, total suspended solids (TSS), nitrogen-nitrate, orthophosphate, lead, and zinc concentrations in Portland, Oregon, USA. Mann-Whitney tests were used to detect differences in water quality between seasons and COVID-19 periods. Spearman's rank correlation analysis was used to identify the relationship between water quality and explanatory variables. A Random Forest (RF) model was used to predict water quality using antecedent precipitation amounts and landscape variables as inputs. The performance of RF was compared with that of ordinary least squares (OLS). Mann-Whitney tests identified statistically significant differences in all pollutant concentrations (except TSS) between the wet and dry seasons. Nitrate was the only pollutant to display statistically significant reductions in median concentrations (from 1.5 mg/L to 1.04 mg/L) during the COVID-19 lockdown period, likely associated with reduced traffic volumes. Spearman's correlation analysis identified the highest correlation coefficients between one-day precipitation amounts and E. coli, lead, zinc, and TSS concentrations. Road length is positively associated with E. coli and zinc. The Random Forest (RF) model best predicts orthophosphate concentrations (R-2 = 0.58), followed by TSS (R-2 = 0.54) and nitrate (R-2 = 0.46). E. coli was the most difficult to model and had the highest RMSE, MAE, and MAPE values. Overall, the Random Forest model outperformed OLS, as evaluated by RMSE, MAE, MAPE, and R-2. The Random Forest was an effective approach to modeling pollutant concentrations using both categorical seasonal and COVID data along with continuous rain and landscape variables to predict water quality in urban streams. Implementing optimization techniques can further improve the model's performance and allow researchers to use a machine learning approach for water quality modeling.

Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy

Background: Radiomical data are redundant but they might serve as a tool for lung quantitative assessment reflecting disease severity and actual physiological status of COVID-19 patients. Objective: Test the effectiveness of machine learning in eliminating data redundancy of radiomics and reflecting pathophysiologic changes in patients with COVID-19 pneumonia. Methods: We analyzed 605 cases admitted to Al Ain Hospital from 24 February to 1 July, 2020. They met the following inclusion criteria: age $\geq 18$ years;inpatient admission;PCR positive for SARS-CoV-2;lung CT available at PACS. We categorized cases into 4 classes: mild < 5% of pulmonary parenchymal involvement, moderate - 5-24%, severe - 25-49%, and critical $\geq50$ %. We used CT scans to build regression models predicting the oxygenation level, respiratory and cardiovascular functioning. Results: Radiomical findings are a reliable source of information to assess the functional status of patients with COVID-19. Machine learning models can predict the oxygenation level, respiratory and cardiovascular functioning from a set of demographics and radiomics data regardless of the settings of reconstructionkernels. The regression models can be used for scoring lung impairment and comparing disease severity in followup studies. The most accurate prediction we achieved was 6.454 +/- 3.715% of mean absolute error/range for all thefeatures and 7.069 +/- 4.17% for radiomics.Conclusion:The models may contribute to the proper risk evaluation anddisease management especially when the oxygen therapy impacts the actual values of the functional findings. Still,the structural assessment of an acute lung injury reflects the severity of the disease.

Using machine learning models to predict the duration of the recovery of COVID-19 patients hospitalized in Fangcang shelter hospital during the Omicron BA. 2.2 pandemic.

Background: Factors that may influence the recovery of patients with confirmed SARS-CoV-2 infection hospitalized in the Fangcang shelter were explored, and machine learning models were constructed to predict the duration of recovery during the Omicron BA. 2.2 pandemic. Methods: A retrospective study was conducted at Hongqiao National Exhibition and Convention Center Fangcang shelter (Shanghai, China) from April 9, 2022 to April 25, 2022. The demographics, clinical data, inoculation history, and recovery information of the 13,162 enrolled participants were collected. A multivariable logistic regression model was used to identify independent factors associated with 7-day recovery and 14-day recovery. Machine learning algorithms (DT, SVM, RF, DT/AdaBoost, AdaBoost, SMOTEENN/DT, SMOTEENN/SVM, SMOTEENN/RF, SMOTEENN+DT/AdaBoost, and SMOTEENN/AdaBoost) were used to build models for predicting 7-day and 14-day recovery. Results: Of the 13,162 patients in the study, the median duration of recovery was 8 days (interquartile range IQR, 6-10 d), 41.31% recovered within 7 days, and 94.83% recovered within 14 days. Univariate analysis showed that the administrative region, age, cough medicine, comorbidities, diabetes, coronary artery disease (CAD), hypertension, number of comorbidities, CT value of the ORF gene, CT value of the N gene, ratio of ORF/IC, and ratio of N/IC were associated with a duration of recovery within 7 days. Age, gender, vaccination dose, cough medicine, comorbidities, diabetes, CAD, hypertension, number of comorbidities, CT value of the ORF gene, CT value of the N gene, ratio of ORF/IC, and ratio of N/IC were related to a duration of recovery within 14 days. In the multivariable analysis, the receipt of two doses of the vaccination vs. unvaccinated (OR = 1.118, 95% CI = 1.003-1.248; p = 0.045), receipt of three doses of the vaccination vs. unvaccinated (OR = 1.114, 95% CI = 1.004-1.236; p = 0.043), diabetes (OR = 0.383, 95% CI = 0.194-0.749; p = 0.005), CAD (OR = 0.107, 95% CI = 0.016-0.421; p = 0.005), hypertension (OR = 0.371, 95% CI = 0.202-0.674; p = 0.001), and ratio of N/IC (OR = 3.686, 95% CI = 2.939-4.629; p < 0.001) were significantly and independently associated with a duration of recovery within 7 days. Gender (OR = 0.736, 95% CI = 0.63-0.861; p < 0.001), age (30-70) (OR = 0.738, 95% CI = 0.594-0.911; p < 0.001), age (>70) (OR = 0.38, 95% CI = 0292-0.494; p < 0.001), receipt of three doses of the vaccination vs. unvaccinated (OR = 1.391, 95% CI = 1.12-1.719; p = 0.0033), cough medicine (OR = 1.509, 95% CI = 1.075-2.19; p = 0.023), and symptoms (OR = 1.619, 95% CI = 1.306-2.028; p < 0.001) were significantly and independently associated with a duration of recovery within 14 days. The SMOTEEN/RF algorithm performed best, with an accuracy of 90.32%, sensitivity of 92.22%, specificity of 88.31%, F1 score of 90.71%, and AUC of 89.75% for the 7-day recovery prediction; and an accuracy of 93.81%, sensitivity of 93.40%, specificity of 93.81%, F1 score of 93.42%, and AUC of 93.53% for the 14-day recovery prediction. Conclusion: Age and vaccination dose were factors robustly associated with accelerated recovery both on day 7 and day 14 from the onset of disease during the Omicron BA. 2.2 wave. The results suggest that the SMOTEEN/RF-based model could be used to predict the probability of 7-day and 14-day recovery from the Omicron variant of SARS-CoV-2 infection for COVID-19 prevention and control policy in other regions or countries. This may also help to generate external validation for the model.

The COVID-19 pandemic: prediction study based on machine learning models.

COVID-19 was first discovered in Wuhan, China in December 2019. It is one of the worst pandemics in human history. Recent studies reported that COVID-19 is transmitted among humans by droplet infection or direct contact. COVID-19 pandemic has invaded more than 210 countries around the world and as of February 18th, 2021, just after a year has passed, a total of 110,533,973 confirmed cases of COVID-19 were reported and its death toll reached about 2,443,091. COVID-19 is a new member of the family of corona viruses, its nature, behaviour, transmission, spread, prevention, and treatment are to be investigated. Generally, a huge amount of data is accumulating regarding the COVID-19 pandemic, which makes hot research topics for machine learning researchers. However, the panicked world's population is asking when the COVID-19 will be over? This study considered machine learning approaches to predict the spread of the COVID-19 in many countries. The experimental results of the proposed model showed that the overall R2 is 0.99 from the perspective of confirmed cases. A machine learning model has been developed to predict the estimation of the spread of the COVID-19 infection in many countries and the expected period after which the virus can be stopped. Globally, our results forecasted that the COVID-19 infections will greatly decline during the first week of September 2021 when it will be going to an end shortly afterward.

Reliability of machine learning in reflecting severity and pathophysiology in COVID-19 pneumonia: impact of CT reconstruction kernels on accuracy

Background: Radiomical data are redundant but they might serve as a tool for lung quantitative assessment reflecting disease severity and actual physiological status of COVID-19 patients. Objective: Test the effectiveness of machine learning in eliminating data redundancy of radiomics and reflecting pathophysiologic changes in patients with COVID-19 pneumonia. Methods: We analyzed 605 cases admitted to Al Ain Hospital from 24 February to 1 July, 2020. They met the following inclusion criteria: age≥18 years;inpatient admission;PCR positive for SARS-CoV-2;lung CT available at PACS. We categorized cases into 4 classes: mild ≤25% of pulmonary parenchymal involvement, moderate - 25-50%, severe - 50-75%, and critical –over 75%. We used CT scans to build regression models predicting the oxygenation level, respiratory and cardiovascular functioning. Results: Radiomical findings are a reliable source of information to assess the functional status of patients with COVID-19. Machine learning models can predict the oxygenation level, respiratory and cardiovascular functioning from a set of demographics and radiomics data regardless of the settings of reconstruction kernels. The regression models can be used for scoring lung impairment and comparing disease severity in follow up studies. The most accurate prediction we achieved was 6.454±3.715% of mean absolute error/range for all the features and 7.069±4.17% for radiomics. Conclusion: The models may contribute to the proper risk evaluation and disease management especially when the oxygen therapy impacts the actual values of the functional findings. Still, the structural assessment of an acute lung injury reflects the severity of the disease. Author

FAIR Machine Learning Model Pipeline Implementation of COVID-19 Data

Research and development are gradually becoming data-driven and the implementation of the FAIR Guidelines (that data should be Findable, Accessible, Interoperable, and Reusable) for scientific data administration and stewardship has the potential to remarkably enhance the framework for the reuse of research data. In this way, FAIR is aiding digital transformation. The ‘FAIRification’ of data increases the interoperability and (re)usability of data, so that new and robust analytical tools, such as machine learning (ML) models, can access the data to deduce meaningful insights, extract actionable information, and identify hidden patterns. This article aims to build a FAIR ML model pipeline using the generic FAIRification workflow to make the whole ML analytics process FAIR. Accordingly, FAIR input data was modelled using a FAIR ML model. The output data from the FAIR ML model was also made FAIR. For this, a hybrid hierarchical k-means (HHK) clustering ML algorithm was applied to group the data into homogeneous subgroups and ascertain the underlying structure of the data using a Nigerian-based FAIR dataset that contains data on economic factors, healthcare facilities, and coronavirus occurrences in all the 36 states of Nigeria. The model showed that research data and the ML pipeline can be FAIRified, shared, and reused by following the proposed FAIRification workflow and implementing technical architecture. © 2022 Chinese Academy of Sciences. Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.

An Interactive Interface for Patient Diagnosis using Machine Learning Model

Hospitals are the most common option for health checks, illness diagnosis, and treatment for sick people. This practice is followed by almost everyone in the world. But there is a drawback with this method of getting diagnosed. There are a lot of patients with various diseases/viruses which have a potential to spread in the hospital premises. People never considered the diseases/viruses present in the hospital atmosphere. People are aware of the risk of viral transmissions in hospital environments, post COVID era. Getting diagnosed and going through the reports with an efficient accuracy takes time and some people in emergency may not have enough time to perform the conventional procedures. Users have a necessity of an online website which can help them diagnose their health problems at the comfort of their homes. This would benefit people as they don't have to travel to the hospitals and reduce their risks of transmitting hospital acquired infections. This paper presents an interactive interface that functions as a virtual therapist which accepts input in the form of text, voice, or video. Data is pushed into the machine learning pipeline that generates results. The end result of this model is a report containing root cause of the disease, a tentative prescription, and any estimated treatment expenses. This model helps to prevent hospital-acquired infections, reduces the costs of treatment as users would be able to diagnose earlier and would prefer frequent testing, reducing surgeries and also reduces the tasks of doctors. © 2022 IEEE.

Hybrid approaches for container traffic forecasting in the context of anomalous events: The case of the Yangtze River Delta region in the COVID-19 pandemic.

The COVID-19 pandemic had a significant impact on container transportation. Accurate forecasting of container throughput is critical for policymakers and port authorities, especially in the context of the anomalous events of the COVID-19 pandemic. In this paper, we firstly proposed hybrid models for univariate time series forecasting to enhance prediction accuracy while eliminating the nonlinearity and multivariate limitations. Next, we compared the forecasting accuracy of different models with various training dataset extensions and forecasting horizons. Finally, we analysed the impact of the COVID-19 pandemic on container throughput forecasting and container transportation. An empirical analysis of container throughputs in the Yangtze River Delta region was performed for illustration and verification purposes. Error metrics analysis suggests that SARIMA-LSTM2 and SARIMA-SVR2 (configuration 2) have the best performance compared to other models and they can better predict the container traffic in the context of anomalous events such as the COVID-19 pandemic. The results also reveal that, with an increase in the training dataset extensions, the accuracy of the models is improved, particularly in comparison with standard statistical models (i.e. SARIMA model). An accurate prediction can help strategic management and policymakers to better respond to the negative impact of the COVID-19 pandemic.

Deep Learning-Based Automatic Assessment of Lung Impairment in COVID-19 Pneumonia: Predicting Markers of Hypoxia With Computer Vision.

Background: Hypoxia is a potentially life-threatening condition that can be seen in pneumonia patients. Objective: We aimed to develop and test an automatic assessment of lung impairment in COVID-19 associated pneumonia with machine learning regression models that predict markers of respiratory and cardiovascular functioning from radiograms and lung CT. Materials and Methods: We enrolled a total of 605 COVID-19 cases admitted to Al Ain Hospital from 24 February to 1 July 2020 into the study. The inclusion criteria were as follows: age ≥ 18 years; inpatient admission; PCR positive for SARS-CoV-2; lung CT available at PACS. We designed a CNN-based regression model to predict systemic oxygenation markers from lung CT and 2D diagnostic images of the chest. The 2D images generated by averaging CT scans were analogous to the frontal and lateral view radiograms. The functional (heart and breath rate, blood pressure) and biochemical findings (SpO2, H C O 3 - , K +, Na +, anion gap, C-reactive protein) served as ground truth. Results: Radiologic findings in the lungs of COVID-19 patients provide reliable assessments of functional status with clinical utility. If fed to ML models, the sagittal view radiograms reflect dyspnea more accurately than the coronal view radiograms due to the smaller size and the lower model complexity. Mean absolute error of the models trained on single-projection radiograms was approximately 11÷12% and it dropped by 0.5÷1% if both projections were used (11.97 ± 9.23 vs. 11.43 ± 7.51%; p = 0.70). Thus, the ML regression models based on 2D images acquired in multiple planes had slightly better performance. The data blending approach was as efficient as the voting regression technique: 10.90 ± 6.72 vs. 11.96 ± 8.30%, p = 0.94. The models trained on 3D images were more accurate than those on 2D: 8.27 ± 4.13 and 11.75 ± 8.26%, p = 0.14 before lung extraction; 10.66 ± 5.83 and 7.94 ± 4.13%, p = 0.18 after the extraction. The lung extraction boosts 3D model performance unsubstantially (from 8.27 ± 4.13 to 7.94 ± 4.13%; p = 0.82). However, none of the differences between 3D and 2D were statistically significant. Conclusion: The constructed ML algorithms can serve as models of structure-function association and pathophysiologic changes in COVID-19. The algorithms can improve risk evaluation and disease management especially after oxygen therapy that changes functional findings. Thus, the structural assessment of acute lung injury speaks of disease severity.

From Policy to Prediction: Forecasting COVID-19 Dynamics Under Imperfect Vaccination.

Understanding the joint impact of vaccination and non-pharmaceutical interventions on COVID-19 development is important for making public health decisions that control the pandemic. Recently, we created a method in forecasting the daily number of confirmed cases of infectious diseases by combining a mechanistic ordinary differential equation (ODE) model for infectious classes and a generalized boosting machine learning model (GBM) for predicting how public health policies and mobility data affect the transmission rate in the ODE model (Wang et al. in Bull Math Biol 84:57, 2022). In this paper, we extend the method to the post-vaccination period, accordingly obtain a retrospective forecast of COVID-19 daily confirmed cases in the US, and identify the relative influence of the policies used as the predictor variables. In particular, our ODE model contains both partially and fully vaccinated compartments and accounts for the breakthrough cases, that is, vaccinated individuals can still get infected. Our results indicate that the inclusion of data on non-pharmaceutical interventions can significantly improve the accuracy of the predictions. With the use of policy data, the model predicts the number of daily infected cases up to 35 days in the future, with an average mean absolute percentage error of [Formula: see text], which is further improved to [Formula: see text] if combined with human mobility data. Moreover, the most influential predictor variables are the policies of restrictions on gatherings, testing and school closing. The modeling approach used in this work can help policymakers design control measures as variant strains threaten public health in the future.

A Supervised Multi-tree XGBoost Model for an Earlier COVID-19 Diagnosis Based on Clinical Symptoms

Efficient screening of Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2) enables quick and efficient diagnosis of SARS-CoV-2 and can mitigate the burden on healthcare systems. The aim was to assist the medical team globally in triaging incoming patients, especially in countries with limited healthcare infrastructure. In this context, the features with imminent infection risk (Test Indication, Fever, and Headache) were obtained using a multi-tree XGBoost algorithm. Based on their feature importance, the top three clinically relevant earlier clinical symptoms (attributes) were employed to create a Multi-tree XGBoost-based model for an earlier prediction of SARS-CoV-2. Overall, our Multi-tree XGBoost model predicted SARS-CoV-2 infection status with a high F1-score (0.9920 +/- 0.008) and AUC value (0.9974 +/- 0.0026) only by assessing the primary three clinical symptoms related to COVID-19 infection. Thus our multi-tree XGBoost - based model suggests a simple and accurate method for earlier detection of SARS-CoV-2 cases and initiating proper treatment protocol for SARS-CoV-2 positive patients. Therefore, we can conclude that our model will allow the health organizations to potentially reduce the infection rate and mortality in masses with COVID-19 infection and fatality due to SARS-CoV-2.