The m7G Modification Level and Immune Infiltration Characteristics in Patients with COVID-19

Purpose: The 7-methylguanosine (m7G)-related genes were used to identify the clinical severity and prognosis of patients with coronavirus disease 2019 (COVID-19) and to identify possible therapeutic targets. Patients and Methods: The GSE157103 dataset provides the transcriptional spectrum and clinical information required to analyze the expression of m7G-related genes and the disease subtypes. R language was applied for immune infiltration analysis, functional enrichment analysis, and nomogram model construction. Results: Most m7G-related genes were up-regulated in COVID-19 and were closely related to immune cell infiltration. Disease subtypes were grouped using a clustering algorithm. It was found that the m7G-cluster B was associated with higher immune infiltration, lower mechanical ventilation, lower intensive care unit (ICU) status, higher ventilator-free days, and lower m7G scores. Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis showed that differentially expressed genes (DEGs) between m7G-cluster A and B were enriched in viral infection and immune-related aspects, including COVID-19 infection;Th17, Th1, and Th2 cell differentiation, and human T-cell leukemia virus 1 infection. Finally, through machine learning, six disease characteristic genes, NUDT4B, IFIT5, LARP1, EIF4E, LSM1, and NUDT4, were screened and used to develop a nomogram model to estimate disease risk. Conclusion: The expression of most m7G genes was higher in COVID-19 patients compared with that in non-COVID-19 patients. The m7G-cluster B showed higher immune infiltration and milder symptoms. The predictive nomogram based on the six m7G genes can be used to accurately assess risk.

Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review

Background: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other hand, studies have shown that artificial intelligence (AI) is highly potential in complementing the work of clinicians to diagnose heart failure accurately and rapidly. Methods: We systematically searched Europe PMC, ProQuest, Science Direct, PubMed, and IEEE following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and our inclusion and exclusion criteria. The 14 selected works of literature were then assessed for their quality and risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). Results: A total of 2105 studies were retrieved, and 14 were included in the analysis. Five studies posed risks of bias. Nearly all studies included datasets in the form of 3D (three dimensional) or 2D (two dimensional) images, along with apical four-chamber (A4C) and apical two-chamber (A2C) being the most common echocardiography views used. The machine learning algorithm for each study differs, with the convolutional neural network as the most common method used. The accuracy varies from 57% to 99.3%. Conclusions: To conclude, current evidence suggests that the application of AI leads to a better and faster diagnosis of left heart failure through echocardiography. However, the presence of clinicians is still irreplaceable during diagnostic processes and overall clinical care;thus, AI only serves as complementary assistance for clinicians.

In Silico Identification of Anti-SARS-CoV-2 Medicinal Plants Using Cheminformatics and Machine Learning

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative pathogen of COVID-19, is spreading rapidly and has caused hundreds of millions of infections and millions of deaths worldwide. Due to the lack of specific vaccines and effective treatments for COVID-19, there is an urgent need to identify effective drugs. Traditional Chinese medicine (TCM) is a valuable resource for identifying novel anti-SARS-CoV-2 drugs based on the important contribution of TCM and its potential benefits in COVID-19 treatment. Herein, we aimed to discover novel anti-SARS-CoV-2 compounds and medicinal plants from TCM by establishing a prediction method of anti-SARS-CoV-2 activity using machine learning methods. We first constructed a benchmark dataset from anti-SARS-CoV-2 bioactivity data collected from the ChEMBL database. Then, we established random forest (RF) and support vector machine (SVM) models that both achieved satisfactory predictive performance with AUC values of 0.90. By using this method, a total of 1011 active anti-SARS-CoV-2 compounds were predicted from the TCMSP database. Among these compounds, six compounds with highly potent activity were confirmed in the anti-SARS-CoV-2 experiments. The molecular fingerprint similarity analysis revealed that only 24 of the 1011 compounds have high similarity to the FDA-approved antiviral drugs, indicating that most of the compounds were structurally novel. Based on the predicted anti-SARS-CoV-2 compounds, we identified 74 anti-SARS-CoV-2 medicinal plants through enrichment analysis. The 74 plants are widely distributed in 68 genera and 43 families, 14 of which belong to antipyretic detoxicate plants. In summary, this study provided several medicinal plants with potential anti-SARS-CoV-2 activity, which offer an attractive starting point and a broader scope to mine for potentially novel anti-SARS-CoV-2 drugs. © 2022 by the authors.

Academic performance prediction associated with synchronous online interactive learning behaviors based on the machine learning approach

With long-term impact of COVID-19 on education, online interactive live courses have been an effective method to keep learning and teaching from being interrupted, attracting more and more attention due to their synchronous and real-time interaction. However, there is no suitable method for predicting academic performance for students participating in online class. Five machine learning models are employed to predict academic performance of an engineering mechanics course, taking online learning behaviors, comprehensive performance as input and final exam scores (FESs) as output. The analysis shows the gradient boosting regression model achieves the best performance with the highest correlation coefficient (0.7558), and the lowest RMSE (9.3595). Intellectual education score (IES) is the most important factor of comprehensive performance while the number of completed assignment (NOCA), the live viewing rate (LVR) and the replay viewing rate (RVR) of online learning behaviors are the most important factors influencing FESs. Students with higher IES are more likely to achieve better academic performance, and students with lower IES but higher NOCA tend to perform better. Our study can provide effective evidences for teachers to adjust teaching strategies and provide precise assistance for students at risk of academic failure in advance.

Unsupervised clustering reveals phenotypes of AKI in ICU COVID-19 patients

Background: Acute Kidney Injury (AKI) is a very frequent condition, occurring in about one in three patients admitted to an intensive care unit (ICU). AKI is a syndrome defined as a sudden decrease in glomerular filtration rate. However, this unified definition does not reflect the various mechanisms involved in AKI pathophysiology, each with its own characteristics and sensitivity to therapy. In this study, we aimed at developing an innovative machine learning based method able to subphenotype AKI according to its pattern of risk factors. Methods: We adopted a three-step pipeline of analyses. First, we looked for factors associated with AKI using a generalized additive model. Second, we calculated the importance of each identified AKI related factor in the estimated AKI risk to find the main risk factor for AKI, at the single patient level. Lastly, we clusterized AKI patients according to their profile of risk factors and compared the clinical characteristics and outcome of every cluster. We applied this method to a cohort of severe COVID-19 patients hospitalized in the ICU of the Geneva University Hospitals. Results: Among the 248 patients analyzed, we found 7 factors associated with AKI development. Using the individual expression of these factors, we identified three groups of AKI patients, based on the use of Lopinavir/Ritonavir, baseline eGFR, use of dexamethasone and AKI severity. The three clusters expressed distinct characteristics in terms of AKI severity and recovery, metabolic patterns and hospital mortality. Conclusion: We propose here a new method to phenotype AKI patients according to their most important individual risk factors for AKI development. When applied to an ICU cohort of COVID-19 patients, we were able to differentiate three groups of patients. Each expressed specific AKI characteristics and outcomes, which probably reflect a distinct pathophysiology.

Comprehensively identifying Long Covid articles with human-in-the-loop machine learning

A significant percentage of COVID-19 survivors experience ongoing multisystemic symptoms that often affect daily living, a condition known as Long Covid or post-acute-sequelae of SARS-CoV-2 infection. However, identifying scientific articles relevant to Long Covid is challenging since there is no standardized or consensus terminology. We developed an iterative human-in-the-loop machine learning framework combining data programming with active learning into a robust ensemble model, demonstrating higher specificity and considerably higher sensitivity than other methods. Analysis of the Long Covid Collection shows that (1) most Long Covid articles do not refer to Long Covid by any name, (2) when the condition is named, the name used most frequently in the literature is Long Covid, and (3) Long Covid is associated with disorders in a wide variety of body systems. The Long Covid Collection is updated weekly and is searchable online at the LitCovid portal: https://www.ncbi.nlm.nih.gov/research/coronavirus/docsum?filters=e_condition.LongCovid. © 2022

Twenty-First Century Global ADR Management: A Need for Clarification, Redesign, and Coordinated Action

Adverse drug reactions (ADRs) are estimated to be between the fourth and sixth most common cause of death worldwide, taking their place among other prevalent causes of mortality such as heart disease, cancer, and stroke. ADRs impact a broad range of populations across a wide variety of global geography and demographics, with significant mortality and morbidity burden in vulnerable groups such as older people, pediatric populations, and individuals in low-income settings. Too large a share of medicines risk management remains limited to signal detection in big ADR databases (USFDA, EMA, WHO, etc.) This resource allocation is antiquated and applied statistical signal detection methodologies have reached their limits of usefulness. In addition, existing databases are designed for short-term reactions, closely related to medication use and, thus, can only partially assess important broader consequences across geography, time, and clinical relevance. There is an urgent need change the dynamic. We need to identify (earlier and more regularly) many of the important but often overlooked or missed ADRs. Rather than assigning blame, we need to identify the root causes of the problem so they can be clearly addressed and fixed. The public health implications are profound—particularly as we recognize the importance of predicting and mitigating the next pandemic. Consequently, medicines risk management must be integrated within a broader global public health vision. To accomplish this, we need to develop the new tools and methodologies critical to assessing these public health imperatives. © 2022, The Author(s), under exclusive licence to The Drug Information Association, Inc.

A Secure Wearable Framework for Stress Detection in Patients Affected by Communicable Diseases

The emergence of COVID-19 has drastically altered the lifestyle of people around the world, resulting in significant consequences on people's physical and mental well-being. Fear of COVID-19, prolonged isolation, quarantine, and the pandemic itself have contributed to a rise in hypertension among the general populace globally. Protracted exposure to stress has been linked with the onset of numerous diseases and even an increased frequency of suicides. Stress monitoring is a critical component of any strategy used to intervene in the case of stress. However, constant monitoring during activities of daily living using clinical means is not viable. During the current pandemic, isolation protocols, quarantines, and overloaded hospitals have made it physically challenging for subjects to be monitored in clinical settings. This study presents a proposal for a framework that uses unobtrusive wearable sensors, securely connected to an artificial intelligence (AI)-driven cloud-based server for early detection of hypertension and an intervention facilitation system. More precisely, the proposed framework identifies the types of wearable sensors that can be utilized ubiquitously, the enabling technologies required to achieve energy efficiency and secure communication in wearable sensors, and, finally, the proposed use of a combination of machine-learning (ML) classifiers on a cloud-based server to detect instances of sustained stress and all associated risks during times of a communicable disease epidemic like COVID-19. © 2001-2012 IEEE.

Hybrid Approach to Predict the Death Rate of COVID-19 Patients

From closedown of December 2019, coronavirus has directly exhibited a lofty rate of transmission, coercing the World Health Organization to contend in the month of March 2020 that this unbeknownst coronavirus can be depicted as a pandemic. COVID-19 epidemic has guided to an operatic misplacement of deathly life over the public and presents an unbeknownst complaint to public fitness. It also affects the food systems of the person and the world of work. Once the person is infected by COVID, the metabolic exertion of vulnerable cells in his or her body is enhanced, similar as the one driven by COVID-19. The country's dietary habits are analyzed to predict the particular person's death rate. By using KNN algorithm, the performance metrics such as accuracy, precision, recall, and F1 score are evaluated for the country's dietary habits. In this research, both clustering and classification are combined to increase the accuracy of the prediction of death rate of the person. K-means is used for the clustering of the countries, and KNN is used for classifying the countries. The 170 countries are clustered based on the country's dietary habits, and other disease affected rate using K-means clustering algorithm. Countries are clustered into high and normal death rate countries based on the country's dietary habits and another cluster into high and normal death rate based on the other disease affected rate rather than COVID-19. Using the country's dietary habits and other disease affected clusters, the death rate of the person is predicted. After clustering the data based on the country's dietary habits and other disease affected rate, the KNN algorithm is used to classify and identify the person's death rate. Using clustering and classification algorithms in a combined way, an accuracy of 79% is achieved. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Post-COVID-19 interstitial lung disease: Insights from a machine learning radiographic model

IntroductionPost-acute sequelae of COVID-19 seem to be an emerging global crisis. Machine learning radiographic models have great potential for meticulous evaluation of post-COVID-19 interstitial lung disease (ILD). MethodsIn this multicenter, retrospective study, we included consecutive patients that had been evaluated 3 months following severe acute respiratory syndrome coronavirus 2 infection between 01/02/2021 and 12/5/2022. High-resolution computed tomography was evaluated through Imbio Lung Texture Analysis 2.1. ResultsTwo hundred thirty-two (n = 232) patients were analyzed. FVC% predicted was >= 80, between 60 and 79 and <60 in 74.2% (n = 172), 21.1% (n = 49), and 4.7% (n = 11) of the cohort, respectively. DLCO% predicted was >= 80, between 60 and 79 and <60 in 69.4% (n = 161), 15.5% (n = 36), and 15.1% (n = 35), respectively. Extent of ground glass opacities was >= 30% in 4.3% of patients (n = 10), between 5 and 29% in 48.7% of patients (n = 113) and <5% in 47.0% of patients (n = 109). The extent of reticulation was >= 30%, 5-29% and <5% in 1.3% (n = 3), 24.1% (n = 56), and 74.6% (n = 173) of the cohort, respectively. Patients (n = 13, 5.6%) with fibrotic lung disease and persistent functional impairment at the 6-month follow-up received antifibrotics and presented with an absolute change of +10.3 (p = 0.01) and +14.6 (p = 0.01) in FVC% predicted at 3 and 6 months after the initiation of antifibrotic. ConclusionPost-COVID-19-ILD represents an emerging entity. A substantial minority of patients presents with fibrotic lung disease and might experience benefit from antifibrotic initiation at the time point that fibrotic-like changes are "immature." Machine learning radiographic models could be of major significance for accurate radiographic evaluation and subsequently for the guidance of therapeutic approaches.

Social Media Sentiment Analysis Related to COVID-19 Vaccinations

The wake of the COVID-19 pandemic has yet again highlighted how vital immunization is for public health. Despite the dramatic spread of SARS-CoV-2 and its variants, there is a rising trend of people refusing to be vaccinated. As a result, governments and health experts must gather and understand public ideas and perceptions about vaccines to design engagement and education efforts about vaccine advantages. Sentiment analysis is a common method for acquiring a broad picture of public opinion, that enables the classification of people as those who are in favor or against vaccination, as well as the determination of the factors that influence their attitudes and beliefs. The purpose of this chapter is to describe the general approach to sentiment analysis in the context of vaccinations and review its different use cases. The chapter's experimental component integrates the utilization of a dataset retrieved from Kaggle, which contains COVID-19 vaccine-related Twitter data. When attempting to perform sentiment analysis, certain methodological steps need to be considered after data collection, including data pre-processing, technique selection and model construction, as well as model evaluation and results interpretation. Both supervised and unsupervised sentiment analysis methods are investigated in the model construction step, with the former involving the implementation of Support Vector Machines and Logistic Regression algorithms, and the latter involving the use of TextBlob and Valence Aware Dictionary and sEntiment Reasoner (VADER) sentiment analysis tools. The performance of each algorithm and tool is evaluated, as is the performance of each sentiment detection approach in order to select the best performing one. Social media platforms have become a common source of information and misinformation regarding vaccines. Our effort aims to emphasize the importance of mining such readily available public attitudes, as well as forecast opinions and reactions related to vaccine uptake in near real-time. Such insights could be critical in dealing with health emergency situations like the ongoing coronavirus pandemic. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Cough Audio Analysis for COVID-19 Diagnosis

Humanity has suffered catastrophically due to the COVID-19 pandemic. One of the most reliable diagnoses of COVID-19 is RT-PCR (reverse-transcription polymer chain reaction) testing. This method, however, has its limitations. It is time consuming and requires scalability. This research work carries out a preliminary prognosis of COVID-19, which is scalable and less time consuming. The research carried out a competitive analysis of four machine-learning models namely, Multilayer Perceptron, Convolutional Neural Networks, Recurrent Neural Networks with Long Short-Term Memory, and VGG-19 with Support Vector Machines. Out of these models, Multilayer Perceptron outperformed with higher specificity of 94.5% and accuracy of 96.8%. The results show that Multilayer Perceptron was able to distinguish between positive and negative COVID-19 coughs by a robust feature embedding technique. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

Forecasting domestic waste generation during successive COVID-19 lockdowns by Bidirectional LSTM super learner neural network

Accurate prediction of domestic waste generation is a challenging task for municipalities to implement sustainable waste management strategies. In the present study, domestic waste generation in the Kingdom of Bahrain, representing a Small Island Developing State (SIDS) case study, has been investigated during successive COVID-19 lockdowns due to the pandemic in 2020. Temporal trends of daily domestic waste generation between 2019 and 2020 and their statistical analyses exhibited remarkable variations highlighting the impact of consecutive COVID-19 lockdowns on domestic waste generation. Machine learning has great potential for predicting solid waste generation rates, but only a few studies utilized deep learning approaches. The state-of-the-art Bidirectional Long Short-Term Memory (BiLSTM) network model as a deep learning method is applied to forecast daily domestic waste data in 2020. Bayesian optimization algorithm (BOA) was hybridized with BiLSTM to generate a super learner approach. The performance of the BOA-BiLSTM super learner model was further compared with the statistical ARIMA model. Performance indicators of the developed models using ARIMA and BiLSTM showed that the latter yielded superior performance for short-term forecasts of domestic waste generation. The MAE, RMSE, MAPE, and R2 were 47.38, 60.73, 256.43, and 0.46, respectively, for the ARIMA model, compared to 3.67, 12.57, 0.24, and 0.96, respectively, for the BiLSTM model. Additionally, the relative errors for the BiLSTM model were lower than those of the ARIMA model. This study highlights that the BiLSTM can be a reliable forecasting tool for solid waste management policymakers during public health emergencies. © 2022 Elsevier B.V.

Leading Predictors of COVID-19-Related Poor Mental Health in Adult Asian Indians: An Application of Extreme Gradient Boosting and Shapley Additive Explanations

During the COVID-19 pandemic, an increase in poor mental health among Asian Indians was observed in the United States. However, the leading predictors of poor mental health during the COVID-19 pandemic in Asian Indians remained unknown. A cross-sectional online survey was administered to self-identified Asian Indians aged 18 and older (N = 289). Survey collected information on demographic and socio-economic characteristics and the COVID-19 burden. Two novel machine learning techniques-eXtreme Gradient Boosting and Shapley Additive exPlanations (SHAP) were used to identify the leading predictors and explain their associations with poor mental health. A majority of the study participants were female (65.1%), below 50 years of age (73.3%), and had income ≥ $75,000 (81.0%). The six leading predictors of poor mental health among Asian Indians were sleep disturbance, age, general health, income, wearing a mask, and self-reported discrimination. SHAP plots indicated that higher age, wearing a mask, and maintaining social distancing all the time were negatively associated with poor mental health while having sleep disturbance and imputed income levels were positively associated with poor mental health. The model performance metrics indicated high accuracy (0.77), precision (0.78), F1 score (0.77), recall (0.77), and AUROC (0.87). Nearly one in two adults reported poor mental health, and one in five reported sleep disturbance. Findings from our study suggest a paradoxical relationship between income and poor mental health;further studies are needed to confirm our study findings. Sleep disturbance and perceived discrimination can be targeted through tailored intervention to reduce the risk of poor mental health in Asian Indians. © 2022 by the authors.

Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa

Coronavirus disease 2019 (COVID-19) has produced a global pandemic, which has devastating effects on health, economy and social interactions. Despite the less contraction and spread of COVID-19 in Africa compared to some other continents in the world, Africa remains amongst the most vulnerable regions due to less technology and unequipped or poor health system. Recent happenings showed that COVID-19 may stay for years owing to the discoveries of new variants (such as Omicron) and new wave of infections in several countries. Therefore, accurate prediction of new cases is vital to make informed decisions and in evaluating the measures that should be implemented. Studies on COVID-19 prediction are limited in Africa despite the risks and dangers that the virus possessed. Hence, this study was performed to predict daily COVID-19 cases in 10 African countries spread across the north, south, east, west and central Africa considering countries with few and large number of daily COVID-19 cases. Machine learning (ML) models due to their nonlinearity and accurate prediction capabilities were employed for this purpose, including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and conventional multiple linear regression (MLR) models. As any other natural process, the COVID-19 pandemic may contain both linear and nonlinear aspects. In such circumstances, neither nonlinear (ML) nor linear (MLR) models could be sufficient;hence, combining both ML and MLR models may produce better accuracy. Consequently, to improve the prediction efficiency of the ML models, novel ensemble approaches including ANN-E and SVM-E were employed. The advantage of using ensemble approaches is that they provide collective benefits of all the standalone models, thereby reducing their weaknesses and enhancing their prediction capabilities. The obtained results showed that ANFIS led to better prediction performance with MAD = 0.0106, MSE = 0.0003, RMSE = 0.0185 and R2 = 0.9059 in the validation step. The results of the proposed ensemble approaches demonstrated very high improvements in predicting the COVID-19 pandemic in Africa with MAD = 0.0073, MSE = 0.0002, RMSE = 0.0155 and R2 = 0.9616. The ANN-E improved the standalone models performance in the validation step up to 10%, 14%, 42%, 6%, 83%, 11%, 7%, 5%, 7% and 31% for Morocco, Sudan, Namibia, South Africa, Uganda, Rwanda, Nigeria, Senegal, Gabon and Cameroon, respectively. This study results offer a solid foundation in the application of ensemble approaches for predicting COVID-19 pandemic across all regions and countries in the world. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Data-driven assisted model specification for complex choice experiments data: Association rules learning and random forests for Participatory Value Evaluation experiments

We propose three procedures based on association rules (AR) learning and random forests (RF) to support the specification of a portfolio choice model applied in data from complex choice experiment data, specifically a Participatory Value Evaluation (PVE) choice experiment. In a PVE choice experiment, respondents choose a combination of alternatives, subject to a resource constraint. We combine a methodological-iterative (MI) procedure with AR learning and RF models to support the specification of parameters of a portfolio choice model. Additionally, we use RF model predictions to contrast the validity of the behavioural assumptions of different specifications of the portfolio choice model. We use data of a PVE choice experiment conducted to elicit the preferences of Dutch citizens for lifting COVID-19 measures. Our results show model fit and interpretation improvements in the portfolio choice model, compared with conventional model specifications. Additionally, we provide guidelines on the use of outcomes from AR learning and RF models from a choice modelling perspective. © 2022 The Author(s)

Genomic image representation of human coronavirus sequences for COVID-19 detection

Coronavirus (CoV) disease 2019 (COVID-19) is a severe pandemic affecting millions worldwide. Due to its rapid evolution, researchers have been working on developing diagnostic approaches to suppress its spread. This study presents an effective automated approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19, among other human CoV diseases, with high acceptable accuracy. The GIP technique was applied as follows: first, genomic graphical mapping techniques were used to convert the genome sequences into genomic grayscale images. The frequency chaos game representation (FCGR) and single gray-level representation (SGLR) techniques were used in this investigation. Then, several statistical features were obtained from the images to train and test many classifiers, including the k-nearest neighbors (KNN). This study aimed to determine the efficacy of the FCGR (with different orders) and SGLR images for accurately detecting COVID-19, using a dataset containing both partial and complete genome sequences. The results recommended the fourth-order FCGR image as a proper genomic image for extracting statistical features and achieving accurate classification. Furthermore, the results showed that KNN achieved an overall accuracy of 99.39% in detecting COVID-19, among other human CoV diseases, with 99.48% precision, 99.31% sensitivity, 99.47% specificity, 0.99 F1-score, and 0.99 Matthew's correlation coefficient. © 2022 THE AUTHORS

Are categorical EPU indices predictable for carbon futures volatility? Evidence from the machine learning method

The purpose of this paper is to explore whether the categorical Economic Policy Uncertainty (EPU) indices are predictable for the volatility of carbon futures, in the mixed data sampling (MIDAS) regression framework. The prediction methods include the MIDAS-RV model, the MIDAS models extended by individual categorical EPU index, combination prediction approaches, the MIDAS models extended by dimensionality reduction techniques as well as the machine learning methods on the basis of MIDAS model and Markov regime switching method. We find firstly that categorical EPU indices are predictable for carbon futures volatility, but the predictive power of individual categorical EPU indices is not robust. Secondly, machine learning methods, especially the machine learning method considering the Markov regime switching structure, help to obtain valid information from multiple categorical EPU indices and produce robust and superior prediction accuracy for carbon futures volatility. The results of the extension analysis also found that machine learning methods, especially the machine learning method considering the Markov regime switching structure help to produce higher investment performance and more accurate long-term carbon futures volatility forecasts. Meanwhile, we also find the advantages of the MIDAS based machine learning methods over the traditional AR based machine learning methods. Finally, the forecasting performance of the machine learning method which considering Markov regime switching structure are superior during both the low and high volatility regimes and even during the COVID-19 pandemic. © 2022 Elsevier Inc.

Forecasting for regulatory credit loss derived from the COVID-19 pandemic: A machine learning approach

The economic onslaught of the COVID-19 pandemic has compromised the risk management of financial institutions. The consequences related to such an unprecedented situation are difficult to foresee with certainty using traditional methods. The regulatory credit loss attached to defaulted mortgages, so-called expected loss best estimate (ELBE), is forecasted using a machine learning technique. The projection of two ELBEs for 2022 and their comparison are presented. One accounts for the outbreak's impact, and the other presumes the nonexistence of the pandemic. Then, it is concluded that the referred crisis surely adversely affects said high-risk portfolios. The proposed method has excellent performance and may serve to estimate future expected and unexpected losses amidst any event of extraordinary magnitude.