Multifactor data analysis to forecast an individual's severity over novel COVID-19 pandemic using extreme gradient boosting and random forest classifier algorithms

AI and machine learning are increasingly often applied in the medical industry. The COVID-19 epidemic will start to spread quickly over the planet around the start of 2020. At hospitals, there were more patients than there were beds. It was challenging for medical personnel to identify the patient who needed treatment right away. A machine learning approach is used to predict COVID-19 pandemic patients at high risk. To provide input data and output results that execute the machine learning model on the backend, a straightforward Python Flask web application is employed. Here, the XGBoost algorithm, a supervised machine learning method, is applied. In order to predict high-risk patients based on their current underlying health issues, the model uses patient characteristics as well as criteria like age, sex, health issues including diabetes, asthma, hypertension, and smoking, among others. The XGBoost model predicts the patient's severity with an accuracy of about 98% after data pre-processing and training. The most important factors to the models are chosen to be age, diabetes, sex, and obesity. Patients and hospital personnel will benefit from this project's assistance in making timely choices and taking appropriate action. This will let medical personnel decide how much time and space to devote to the COVID-19 high-risk patients. providing a treatment that is both efficient and ideal. With this programme and the necessary patient data, hospitals may decide whether a patient need immediate care or not.

Spatiotemporal Modeling of the Association between Neighborhood Factors and COVID-19 Incidence Rates in Scotland

This study aims to investigate the association between neighborhood-level factors and COVID-19 incidence in Scotland from a spatiotemporal perspective. The outcome variable is the COVID-19 incidence in Scotland. Based on the identification of the wave peaks for COVID-19 cases between 2020 and 2021, confirmed COVID-19 cases in Scotland can be divided into four phases. To model the COVID-19 incidence, sixteen neighborhood factors are chosen as the predictors. Geographical random forest models are used to examine spatiotemporal variation in major determinants of COVID-19 incidence. The spatial analysis indicates that proportion of religious people is the most strongly associated with COVID-19 incidence in southern Scotland, whereas particulate matter is the most strongly associated with COVID-19 incidence in northern Scotland. Also, crowded households, prepandemic emergency admission rates, and health and social workers are the most strongly associated with COVID-19 incidence in eastern and central Scotland, respectively. A possible explanation is that the association between predictors and COVID-19 incidence might be influenced by local context (e.g., people's lifestyles), which is spatially variant across Scotland. The temporal analysis indicates that dominant factors associated with COVID-19 incidence also vary across different phases, suggesting that pandemic-related policy should take spatiotemporal variations into account. © 2023 by American Association of Geographers.

Intelligent Methods and Models for Assessing Level of Student Adaptation to Online Learning

The problem of introducing online learning is becoming more and more popular in our society. Due to COVID-19 and the war in Ukraine, there is an urgent need for the transition of educational institutions to online learning, so this paper will help people not make mistakes in the process and afterward. The paper's primary purpose is to investigate the effectiveness of machine learning tools that can solve the problem of assessing student adaptation to online learning. These tools include intelligent methods and models, such as classification techniques and neural networks. This work uses data from an online survey of students at different levels: school, college, and university. The survey consists of questions such as gender, age, level of education, whether the student is in the city, class duration, quality of Internet connection, government/non-government educational institution, availability of virtual learning environment, whether the student is familiar with IT, financial conditions, type of Internet connection, a device used for studying, etc. To obtain the results on the effectiveness of online education were used the following machine learning algorithms and models: Random Forest (RF), Extra Trees (ET), Extreme, Light, and Simple Gradient Boosting (GB), Decision Trees (DT), K-neighbors (K-mean), Logistic Regression (LR), Support Vector Machine (SVM), Naїve Bayes (NB) classifier and others. An intelligent neural network model (NNM) was built to address the main issue. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (CEUR-WS.org)

Comparison of machine learning algorithms with regression analysis to predict the COVID-19 outbreak in Thailand

Coronavirus disease (COVID-19) is a public health problem in Thailand. Currently, there are more than 5 million infected people and the rate has been increasing at some point. It is therefore important to forecast the number of new cases over a short period of time to assist in strategic planning for the response to COVID-19. The purpose of this research paper was to compare the efficiency and prediction of the number of COVID-19 cases in Thailand using machine learning of 8 models using a regression analysis method. Using the 475-day dataset of COVID-19 cases in Thailand, the results showed that the predictive accuracy model (R2 score) from the testing dataset was the random forest (RF) model, which was 99.06%, followed by K-nearest neighbor (KNN), XGBoost. And the decision tree (DT) had the precision of 98.97, 98.67, and 98.64, respectively. And the results of the comparison of the number of infected people obtained from the prediction The models that predicted the number of real infections were the decision tree, random forest, and XGBoost, which were effective at predicting the number of infections correctly in the 2-4 day period. © 2023 Institute of Advanced Engineering and Science. All rights reserved.

Prediction of Corona Virus Disease Outcome and Future Forecast the Trend of COVID-19 in India: Observational Study

This work is motivated by the disease caused by the novel corona virus Covid-19, rapid spread in India. An encyclopaedic search from India and worldwide social networking sites was performed between 1 March 2020 and 20 Jun 2020. Nowadays social network platform plays a vital role to track spreading behaviour of many diseases earlier then government agencies. Here we introduced the approach to predict and future forecast the disease outcome spread through corona virus in society to give earlier warning to save from life threats. We compiled daily data of Covid-19 incidence from all state regions in India. Five states (Maharashtra, Delhi, Gujarat, Rajasthan and Madhya-Pradesh) with higher incidence and other states considered for time series analysis to construct a predictive model based on daily incidence training data. In this study we have applied the predictive model building approaches like k-nearest neighbour technique, Random-Forest technique and stochastic gradient boosting technique in COVID-19 dataset and the simulated outcome compared with the observed outcome to validate model and measure the performance of model by accuracy (ACC) and Kappa measures. Further forecast the future trends in number of cases of corona virus deceased patients using the Holt Winters Method. Time series analysis is effective tool for predict the outcome of corona virus disease. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Detecting Ransomware Attacks in Cloud Environment Using Machine Learning-Based Intelligence System in COVID-19 Chaos

2020-2022 provided nearly ideal circumstances for cybercriminals, with confusion and uncertainty dominating the planet due to COVID-19. Our way of life was altered by the COVID-19 pandemic, which also sparked a widespread shift to digital media. However, this change also increased people's susceptibility to cybercrime. As a result, taking advantage of the COVID-19 events' exceedingly unusual circumstances, cybercriminals launched widespread Phishing, Identity theft, Spyware, Trojan-horse, and Ransomware attacks. Attackers choose their victims with the intention of stealing their information, money, or both. Therefore, if we wish to safeguard people from these frauds at a time when millions have already fallen into poverty and the remaining are trying to survive, it is imperative that we put an end to these attacks and assailants. This manuscript proposes an intelligence system for identifying ransomware attacks using nature-inspired and machine-learning algorithms. To classify the network traffic in less time and with enhanced accuracy, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), two widely used algorithms are coupled in the proposed approach for Feature Selection (FS). Random Forest (RF) approach is used for classification. The system's effectiveness is assessed using the latest ransomware-oriented dataset of CIC-MalMem-2022. The performance is evaluated in terms of accuracy, model building, and testing time and it is found that the proposed method is a suitable solution to detect ransomware attacks. © 2022 IEEE.

Towards Detection of Cyberbullying in Hinglish Code Mixed Data

Covid-19 eruption and lockdown situation have increased the usages of online platforms which have impacted the users. Cyberbullying is one of the negative outcomes of using social media platforms which leads to mental and physical distress. This study proposes a machine learning-based approach for the detection of cyberbullying in Hinglish text. We use the Hinglish Code-Mixed Corpus, which consists of over 6,000 tweets, for our experiments. We use various machine learning algorithms, including Logistic regression (LR), Multinomial Naive Bayes (MNB), Support vector machine (SVM), Random Forest (RF), to train our models. We evaluate the performance of the models using standard evaluation metrics such as precision, recall, and F1-score. Our experiments show that the LR with Term Frequency-Inverse Document Frequency (TFIDF) outperforms the other models, achieving 92% accuracy. Our study demonstrates that machine learning models can be effective for cyberbullying detection in Hinglish text, and the proposed approach can help identify and prevent cyberbullying on social media platforms. © 2023 Bharati Vidyapeeth, New Delhi.

Random forest regression on joint role of meteorological variables, demographic factors, and policy response measures in COVID-19 daily cases: global analysis in different climate zones.

Different sources of factors in environment can affect the spread of COVID-19 by influencing the diffusion of the virus transmission, but the collective influence of which has hardly been considered. This study aimed to utilize a machine learning algorithm to assess the joint effects of meteorological variables, demographic factors, and government response measures on COVID-19 daily cases globally at city level. Random forest regression models showed that population density was the most crucial determinant for COVID-19 transmission, followed by meteorological variables and response measures. Ultraviolet radiation and temperature dominated meteorological factors, but the associations with daily cases varied across different climate zones. Policy response measures have lag effect in containing the epidemic development, and the pandemic was more effectively contained with stricter response measures implemented, but the generalized measures might not be applicable to all climate conditions. This study explored the roles of demographic factors, meteorological variables, and policy response measures in the transmission of COVID-19, and provided evidence for policymakers that the design of appropriate policies for prevention and preparedness of future pandemics should be based on local climate conditions, population characteristics, and social activity characteristics. Future work should focus on discerning the interactions between numerous factors affecting COVID-19 transmission.

Wastewater-based prediction of COVID-19 cases using a random forest algorithm with strain prevalence data: A case study of five municipalities in Latvia.

Wastewater-based epidemiology (WBE) is a rapid and cost-effective method that can detect SARS-CoV-2 genomic components in wastewater and can provide an early warning for possible COVID-19 outbreaks up to one or two weeks in advance. However, the quantitative relationship between the intensity of the epidemic and the possible progression of the pandemic is still unclear, necessitating further research. This study investigates the use of WBE to rapidly monitor the SARS-CoV-2 virus from five municipal wastewater treatment plants in Latvia and forecast cumulative COVID-19 cases two weeks in advance. For this purpose, a real-time quantitative PCR approach was used to monitor the SARS-CoV-2 nucleocapsid 1 (N1), nucleocapsid 2 (N2), and E genes in municipal wastewater. The RNA signals in the wastewater were compared to the reported COVID-19 cases, and the strain prevalence data of the SARS-CoV-2 virus were identified by targeted sequencing of receptor binding domain (RBD) and furin cleavage site (FCS) regions employing next-generation sequencing technology. The model methodology for a linear model and a random forest was designed and carried out to ascertain the correlation between the cumulative cases, strain prevalence data, and RNA concentration in the wastewater to predict the COVID-19 outbreak and its scale. Additionally, the factors that impact the model prediction accuracy for COVID-19 were investigated and compared between linear and random forest models. The results of cross-validated model metrics showed that the random forest model is more effective in predicting the cumulative COVID-19 cases two weeks in advance when strain prevalence data are included. The results from this research help inform WBE and public health recommendations by providing valuable insights into the impact of environmental exposures on health outcomes.

Preliminary Diagnosis of COVID-19 using Speech Processing Techniques

This project aims to devise an alternative for Coronavirus detection using various audio signals. The aim is to create a machine-learning model assisted by speech processing techniques that can be trained to distinguish symptomatic and asymptomatic Coronavirus cases. Here the features exclusive to the vocal cord of a person is used for covid detection. The procedure is to train the classifier using a data set containing data of people of various ages both infected and disease-free, including patients with comorbidities. We presented a machine learning-based Coronavirus classifier model that can separate Coronavirus positive or negative patients from cough, breathing, and speech recordings. The model was trained and evaluated using several machine learning classifiers such as Random Forest Classifier, Logistic Regression (LR), Decision Tree Classifier, k-nearest Neighbour (KNN), Naive Bayes Classifier, Linear Discriminant Analysis, and a neural network. This project helps track COVID-19 patients at a low cost using a non-contactable procedure and reduces the workload on testing centers. © 2023 IEEE.

Attribution and Regression Analysis Based on Data of COVID-19 and Character Strengths

COVID-19's impact has continued in many sectors and has had a substantial impact on people's lives from 2019 until the present. During this period, human beings in many places experienced a long period of isolation, with or without symptoms. Aside from physical healing, increasing emphasis has been placed on the psychological This paper mainly investigates the relationship between self-efficacy and the personality of isolated people during this period. The multiple linear regression and random forest method were used to find the variables that had a significant impact on self-efficacy. According to the analysis, there is a negative correlation between self-energy efficiency and mental health and depression ratings, In the regression analysis, the influence of hope, choice of beauty, and zest are significant. Based on the random forest model, hope, zest, gradient, and persistence have significant effects on self-efficacy. These results shed light on providing help to those who need it more when the large-scale isolation policy is understaffed. © 2023 SPIE.

COVID-19 vaccination perception and outcome: society sentiment analysis on twitter data in India.

This study examines the perceptions and results of COVID-19 immunization using sentiment analysis of Twitter data from India. The tweets were collected from January 2021 to March 2023 using relevant hashtags and keywords. The dataset was pre-processed and cleaned before conducting sentiment analysis using Natural Language Processing techniques. Our results show that the overall sentiment toward COVID-19 vaccination in India has been positive, with a majority of tweets expressing support for vaccination and encouraging others to get vaccinated. However, we also identified some negative sentiments related to vaccine hesitancy, side effects, and mistrust in the government and pharmaceutical companies. We further analyzed the sentiment based on demographic factors such as gender, age, and location. The analysis revealed that the sentiment varied across different demographics, with some groups expressing more positive or negative sentiments than others. This study provides insights into the perception and outcomes of COVID-19 vaccination in India and highlights the need for targeted communication strategies to address vaccine hesitancy and increase vaccine uptake in specific demographics.

Inflammatory Profiles Are Associated with Long Covid 6 Months after Illness Onset

Background: Systemic hyperinflammation is key to the pathogenesis of severe, acute COVID-19. However, few studies have analysed inflammatory profiles in adults with mild/moderate COVID-19, or in those with post-acute sequelae of COVID-19 (PASC). We aimed to i) describe trajectories of cytokines in a prospective cohort of adults with mild to severe COVID-19, compared to uninfected, healthy controls and ii) identify early (< 4 weeks after illness onset onset) predictors of ongoing PASC and inflammation at 6 months after illness onset. Method(s): RECoVERED is a prospective cohort of adults with laboratoryconfirmed SARS-CoV-2 infection between May 2020 and June 2021 in Amsterdam, the Netherlands. Serum was collected at weeks 4, 12 and 24. Participants completed monthly symptom questionnaires. PASC was defined as having at least one ongoing symptom that originated < 1 month of illness onset. Cytokine concentrations were analysed by human magnetic Luminex screening assay. We performed random forest regression to identify early predictors of PASC and raised CRP/IL-6 at 24 weeks, using Shapley additive explanation values as measures of importance for the different predictors. Result(s): Of 349 RECoVERED participants, 186 (53%) had >=2 serum samples and were included in current analyses. Of these, 101 (54%: 45/101 [45%] female, median age 55 years [IQR=45-64]) reported PASC at 12 weeks after illness onset, of whom none recovered by 24 weeks. We included 37 uninfected controls (17/37 [46%] female, median age 49 years [IQR=40-56]). At 4 weeks after illness onset, levels of IP10, IL10, IL17, IL1beta, IL6 and TNFalpha were significantly elevated among participants infected with SARS-CoV-2 compared to controls. Ongoing PASC was independently associated with raised CRP at 24 weeks. Early raised IL1beta and sCD14 levels and greater BMI at illness onset were the strongest predictors of PASC at 24 weeks. Those with higher early sCD14 or IL1beta and TNFalpha levels were also more likely to have persistently raised CRP and IL6, respectively, at 24 weeks (Fig.1). Conclusion(s): Differences in cytokine concentrations between individuals with COVID-19 and uninfected controls largely were greatest < 4 weeks after illness onset. In our study, ongoing PASC was associated with persistently elevated CRP at 24 weeks. Early immune dysregulation was, alongside BMI, an important determinant for persistent PASC. Further investigation of individuals with PASC and long-term aberrant cytokine levels may help improve our understanding of the condition. (Figure Presented).

Automatic Diagnosis of COVID-19 Based on Machine Learning

The lives and health of individuals are significantly threatened by the extremely infectious and dangerous Corona Virus Disease 2019 (COVID-19). For the containment of the epidemic, quick and precise COVID-19 detection and diagnosis are essential. Currently, artificial diagnosis based on medical imaging and nucleic acid detection are the major approaches used for COVID-19 detection and diagnosis. However, nucleic acid detection takes a long time and requires a dedicated test box, while manual diagnosis based on medical images relies too much on professional knowledge, and analysis takes a long time, and it is difficult to find hidden lesions. Thanks to the rapid development of pattern recognition algorithms, building a COVID-19 diagnostic model based on machine learning and clinical symptoms has become a feasible rapid detection solution. In this paper, support vector machines and random forest algorithms are used to build a COVID-19 diagnostic model, respectively. Based on the quantitative comparison of the performance of the two methods, the future development trends in this field are discussed. © 2023 IEEE.

A Machine Learning-driven IoT Architecture for Predicting the Growth and Trend of Covid-19 Epidemic Outbreaks to Identify High-risk Locations

Covid-19 has had a destructive influence on global economics, social life, education, and technologies. The rise of the Covid-19 pandemic has increased the use of digital tools and technologies for epidemic control. This research uses machine learning (ML) models to identify populated areas and predict the disease's risk and impact. The proposed system requires only details about mask utilization, temperature, and distance between individuals, which helps protect the individual's privacy. The gathered data is transferred to an ML engine in the cloud to determine the risk probability of public areas concerning Covid-19. Extracted data are input for multiple ML techniques such as Random Forest (RF), Decision tree (DT), Naive Bayes classifier(NBC), Neural network(NN), and Support vector machine (SVM). Expectation maximization (EM), K-means, Density, Filtered, and Farthest first (FF) clustering algorithms are applied for clustering. Compared to other algorithms, the K-means produces better superior accuracy. The regression technique is utilized for prediction. The outcomes of several methods are compared, and the most suitable ML algorithms utilized in this study are used to identify high-risk locations. In comparison to other identical architectures, the suggested architecture retains excellent accuracies. It is observed that the time taken to build the model using locally weighted learning(LWL) was 0.02 seconds, and the NN took more time to build, which is 0.90 seconds. To test the model, an LWL algorithm took more time which is 1.73 seconds, and the NN took less time to test, which is 0.02 seconds. The NBC has a 99.38 percent accuracy, the RF classifier has a 97.33 percent accuracy, and the DT has a 94.51 percent accuracy for the same data set. These algorithms have significant possibilities for predicting the likelihood of crowd risks of Covid-19 in a public space. This approach generates automatic notifications to concerned government authorities in any aberrant detection. This study is likely to aid researchers in modeling healthcare systems and spur additional research into innovative technology. © 2023 IEEE.

Clinical profile and outcomes of patients with COVID-19 respiratory failure requiring renal replacement therapy: a machine learning analysis of 13,576 patients

Introduction: Acute kidney injury (AKI) is a frequent and severe complication of COVID-19 infection in ICU patients. We propose a structured data-driven methodology and develop a model to predict the use of renal replacement therapy for patients on respiratory support with Covid-19 in 126 ICUs from 42 Brazilian hospitals. Method(s): Adult ICU patients (March 2020-December 2021) with confirmed SARS-CoV-2 infection and need of ventilatory support at D1 admission in the ICU. Main outcome was the need of RRT. We estimated 3 prediction models: Logistic Regression (LR), Random Forest (RF) and XGB Boosting. Models were derived in the training set and evaluated in the test set following an 80/20 split ratio, and models' parameters were selected using fivefold cross-validation. We evaluated and selected the best model in terms of discrimination (AUC) and calibration (Brier's Score). Variable importance was estimated for each predictor variable. Result(s): 13,575 ICU patients with need of respiratory support, of which 1828 (14%) needed RRT. ICU and hospital mortality were respectively 15.7%, 20.3% (non-RRT) and 54.3%, 69% (RRT). Mean age was 63.9 and 55.3 years (RRT vs non-RRT). Mean ICU LOS was 27.8 vs. 12 days, in RRT vs non-RRT. RF and XGB models both showed higher discrimination performance compared to LR (95% confidence interval [95% CI]: 0.84 [0.81-0.85] and 0.83 [0.80-0.85] vs 0.78 [0.75-0.80]). RF and XGB models presented similar calibration (Brier's Score: ([95% CI]: 0.09 [0.09- 0.10] and 0.09 [0.09-0.10]), also better than in LR (0.11 [0.10-0.12]). The final model (RF) showed no sign of under or overestimation of predicted probabilities in calibration plots. Conclusion(s): The need of RRT among patients on respiratory support diagnosed with Covid-19 was accurately predicted through machine learning methods. RF and XGB based models using data from general intensive care databases provides an accurate and practical approach for the early prediction of use of RRT in COVID-19 patients.

Detecting deception using machine learning with facial expressions and pulse rate.

Given the ongoing COVID-19 pandemic, remote interviews have become an increasingly popular approach in many fields. For example, a survey by the HR Research Institute (PCR Institute in Survey on hiring activities for graduates of 2021 and 2022. https://www.hrpro.co.jp/research_detail.php?r_no=273. Accessed 03 Oct 2021) shows that more than 80% of job interviews are conducted remotely, particularly in large companies. However, for some reason, an interviewee might attempt to deceive an interviewer or feel difficult to tell the truth. Although the ability of interviewers to detect deception among interviewees is significant for their company or organization, it still strongly depends on their individual experience and cannot be automated. To address this issue, in this study, we propose a machine learning approach to aid in detecting whether a person is attempting to deceive the interlocutor by associating the features of their facial expressions with those of their pulse rate. We also constructed a more realistic dataset for the task of deception detection by asking subjects not to respond artificially, but rather to improvise natural responses using a web camera and wearable device (smartwatch). The results of an experimental evaluation of the proposed approach with 10-fold cross-validation using random forests classifier show that the accuracy and the F1 value were in the range between 0.75 and 0.8 for each subject, and the highest values were 0.87 and 0.88, respectively. Through the analysis of the importance of the features the trained models, we revealed the crucial features of each subject during deception, which differed among the subjects.

Oropharyngeal microbiome profiled at admission is predictive of the need for respiratory support among COVID-19 patients.

The oropharyngeal microbiome, the collective genomes of the community of microorganisms that colonizes the upper respiratory tract, is thought to influence the clinical course of infection by respiratory viruses, including Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), the causative agent of Coronavirus Infectious Disease 2019 (COVID-19). In this study, we examined the oropharyngeal microbiome of suspected COVID-19 patients presenting to the Emergency Department and an inpatient COVID-19 unit with symptoms of acute COVID-19. Of 115 initially enrolled patients, 50 had positive molecular testing for COVID-19+ and had symptom duration of 14 days or less. These patients were analyzed further as progression of disease could most likely be attributed to acute COVID-19 and less likely a secondary process. Of these, 38 (76%) went on to require some form of supplemental oxygen support. To identify functional patterns associated with respiratory illness requiring respiratory support, we applied an interpretable random forest classification machine learning pipeline to shotgun metagenomic sequencing data and select clinical covariates. When combined with clinical factors, both species and metabolic pathways abundance-based models were found to be highly predictive of the need for respiratory support (F1-score 0.857 for microbes and 0.821 for functional pathways). To determine biologically meaningful and highly predictive signals in the microbiome, we applied the Stable and Interpretable RUle Set to the output of the models. This analysis revealed that low abundance of two commensal organisms, Prevotella salivae or Veillonella infantium (< 4.2 and 1.7% respectively), and a low abundance of a pathway associated with LPS biosynthesis (< 0.1%) were highly predictive of developing the need for acute respiratory support (82 and 91.4% respectively). These findings suggest that the composition of the oropharyngeal microbiome in COVID-19 patients may play a role in determining who will suffer from severe disease manifestations.

A machine learning and explainable artificial intelligence triage-prediction system for COVID-19

COVID-19 is a respiratory disease caused by the SARS-CoV-2 contagion, severely disrupted the healthcare infrastructure. Various countries have developed COVID-19 vaccines that have effectively prevented the severe symptoms caused by the virus to a certain extent. However, a small section of people continues to perish. Artificial intelligence advances have revolutionized healthcare diagnosis and prognosis infrastructure. In this study, we predict the severity of COVID-19 using heterogenous Machine Learning and Deep Learning algorithms by considering clinical markers, vital signs, and other critical factors. This study extensively reviews various classifier architectures to predict the COVID-19 severity. We built and evaluated multiple pipelines entailing combinations of five state-of-the-art data-balancing techniques (Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic, Borderline SMOTE, SMOTE with Tomek links, and SMOTE with Edited Nearest Neighbor (ENN)) and twelve heterogeneous classifiers such as Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, Naïve Bayes, Xgboost, Extratrees, Adaboost, Light GBM, Catboost, and 1-D Convolution Neural Network. The best-performing pipeline consists of Random Forest trained on Borderline SMOTE balanced data that produced the highest recall of 83%. We deployed Explainable Artificial Intelligence tools such as Shapley Additive Explanations and Local Interpretable Model-agnostic Explanations, ELI5, Qlattice, Anchor, and Feature Importance to demystify complex tree-based ensemble models. These tools provide valuable insights into the significance of critical features in the severity prediction of a COVID-19 patient. It was observed that changes in respiratory rate, blood pressure, lactate, and calcium values were the primary contributors to the increase in severity of a COVID-19 patient. This architecture aims to be an explainable decision-support triaging system for medical professionals in countries lacking advanced medical technology and infrastructure to reduce fatalities.

HuDA_COVID Human Disposition Analysis During COVID-19 Using Machine Learning

Coronavirus has greatly impacted various aspects of human life, including human psychology and human disposition. In this paper, the authors analyzed the impact of the COVID-19 pandemic on human health. In the proposed work, human disposition analysis during COVID-19 using machine learning (HuDA_COVID), where factors such as age, employment, addiction, stress level are studied. A mass survey is conducted on individuals of various age groups, regions, and professions, and the methodology achieved varied accuracy ranges from 87.5% to 98%. The study shows people are worried about lockdown, work, and relationships. Furthermore, 23% of the respondents have not had any effect. Forty-five percent and 32% have had positive and negative effects, respectively. HuDA_COVID is a novel study in human disposition analysis in COVID-19 where a weighted assignment indicating the health status is also proposed. HuDA_COVID clearly indicates a need for a methodical approach towards the human psychological needs to help the social organizations formulating holistic interventions for affected individuals.