Early Detection Of COVID-19 Research Articles

The Epidemiological Analysis of COVID-19 Outbreaks in Nursing Homes during the Period of Omicron Variant Predominance

Background: The main purpose of this study was to evaluate the epidemic trend and risk factors associated with COVID-19 outbreaks in nursing homes during the period of Omicron variant predominance. Methods: The study analyzed the risk factors associated with SARS-CoV-2 infection and death among the 327 residents and 129 healthcare workers (HCWs) in three hospital-affiliated nursing homes through a multivariate Cox regression model. Results: The rates of receiving a COVID-19 booster dose were 70.3% for the residents and 93.0% for the healthcare workers (HCWs), respectively. A number of asymptomatic individuals, including 54 (16.5%) residents and 15 (11.6%) HCWs, were detected through mass screening surveillance tests. The COVID-19 infection rates during the outbreaks were 41.6% among residents and 48.1% among HCWs, respectively. The case fatality rate among residents was 10.3%. None of the HCWs were hospitalized or died. The multivariate Cox regression model showed that the risk of COVID-19 infection increased in males (HR 2.46; 95% CI 1.47–4.11; p = 0.001), Barthel index ≥ 61 (HR 1.93; 95% CI 1.18–3.17; p = 0.009), and dementia (HR 1.61; 95% CI 1.14–2.27; p = 0.007). The risk of COVID-19 death increased with pneumonia (HR 11.03; 95% CI 3.02–40.31; p < 0.001), hospitalization (HR 7.18; 95% CI 1.97–26.25; p = 0.003), and admission to an intensive care unit (HR 8.67; 95% CI 2.79–26.89; p < 0.001). Conclusions: This study highlighted the high infection rates with a substantial proportion of asymptomatic infections for both residents and HCWs, as well as a high case fatality rate for the residents among nursing homes during the Omicron epidemic period. We suggest implementing mass screening through regular surveillance testing as an effective strategy for early detection of COVID-19 and for preventing transmission during an epidemic period. Pneumonia is the primary risk associated with COVID-19 death. Early detection and prompt treatment of pneumonia for vulnerable residents in nursing homes are crucial to protect them from potential mortality.

Association of N and E Genes with ORF1b Gene for Early Detection of COVID-19 in Pakistani Patients

OBJECTIVE: To investigate the role of the first line and additional confirmatory assay to detect coronavirus based on Ct RT-PCR values. METHODOLOGY: A collaborative cross-sectional study was conducted using a systematic sampling type at Hyderabad's diagnostic and research laboratory and the SIOVS, Hyderabad, after getting ethical approval from the LUMHS ERC committee from July 2021 to June 2022. A total of 4822 patients have enrolled; 1200 patients were positive for COVID-19, and a nasopharyngeal swab was collected from patients for RNA extraction; the patients positive with COVID-19 RT-PCR test were included, and patients negative with COVID-19 RT-PCR were excluded out from this study. The RT-PCR was performed, and the Ct values of each potential target were recorded. RESULTS: The RT-PCR finding of potential targets revealed that the N and E genes are correlated and simultaneously positive with OFRb1 and RdRP genes and are crucial for detecting coronavirus. In 77.5% (310/400) of patients, the E gene was positive, and the N gene was positive in 85.8% (1030/1200) patients with ORF1b and Rdrp genes. 71% (850/1200) of males were infected in our cohort, and young patients carried the highest viral load than old age patients with asymptomatic features. Each target's obtained cycler threshold values by different kits were recorded and analyzed in SPSS-17. CONCLUSION: The data showed N and E genes are simultaneously associated with the ORFb1 gene for detecting COVID-19 in our patients. KEY WORDS: SARS CoV-2, COVID-19, E gene, N gene, ORF1b gene, RT-PCR

Machine Learning-based Early Detection and Prognosis of the Covid-19 Pandemic

The outbreak of Covid-19 has caused a global health crisis, presenting numerous challenges to the healthcare system with its severe respiratory symptoms and variable presentation. Early and accurate diagnosis of the virus is critical in controlling its spread and reducing the burden on healthcare facilities. To address this issue and relieve the strain on the healthcare system, this paper proposes a machine learning-based approach for Covid-19 diagnosis. Four algorithms were used for analyzing early Covid-19 detection, i.e., logistic regression, random forest, decision tree, and naive Bayes, using a data set of basic symptoms such as fever, shortness of breath, etc. for predicting positive and negative Covid-19 cases. Furthermore, development of a web portal that provides information on global vaccine distribution and the most widely used vaccines by country along with Covid-19 predictions. Our evaluation results demonstrate that the decision tree model outperformed the other models, achieving an accuracy of 97.69%. This study provides a practical solution to the ongoing Covid-19 crisis through an improved diagnosis method and access to vaccination information.

Sistem Screening Mandiri Covid-19 Berbasis Internet of Things (IoT)

The increasing need to perform Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR) during the COVID-19 pandemic is time-consuming and costly. An IoT-based self-screening system of COVID-19, is expected to be a solution. In this study, instruments were created to monitor SpO2 and heart rate using the MAX30102 sensor, body temperature using the MLX90614 sensor, and breathing rate using a flex sensor as a COVID-19 detection parameter. The measured vital sign results are also transmitted to the website using the Wi-Fi module ESP32. The method used is a decision tree that has two classifications, indicated healthy and indicated COVID-19. Decision tree accuracy is 90% and recall is 100%. Temperature readings have a 98.68% accuracy, SpO2 readings and heartbeats are 98.74% and 98.64%, respectively, and breathing rate per minute readings are 100% accurate. This autonomous COVID-19 screening system can be used as an alternative solution for early detection of COVID-19.

Classification of COVID-19 Cough Sounds using Mel Frequency Cepstral Coefficient (MFCC) Feature Extraction and Support Vector Machine

A lot of research has been carried out to detect COVID-19, such as swabs, rapid antigens, and using x-ray images. However, this method has the disadvantage that it requires taking samples through physical contact with the patient. One way to avoid physical contact is to use audio through coughing with the aim of reducing the transmission of COVID-19. Audio feature extraction such as the Mel Frequency Cepstral Coefficient (MFCC) has often been used in audio classification research, such as the classification of musical genres and so on. This study aims to compare more or less the features of audio classification performance through coughing sounds for early detection of COVID-19 using a Support Vector Machine based on the Linear and Radial Basis Function (RBF). The dataset used is the COVID-19 Cough audio dataset, before classifying, the audio data is processed into a spectrogram and then feature extraction is carried out. Classification is divided into 2 schemes, using default parameters, then using the specified configuration parameters. From the research results, the highest AUC is 0.572266 in the linear kernel-based SVM classification. Meanwhile, when using the RBF kernel, the highest AUC is 0.560181.

Early Detection of COVID-19 in Female Athletes Using Wearable Technology.

Heart rate variability (HRV), respiratory rate (RR), and resting heart rate (RHR) are common variables measured by wrist-worn activity trackers to monitor health, fitness, and recovery in athletes. Variations in RR are observed in lower-respiratory infections, and preliminary data suggest changes in HRV and RR are linked to early detection of COVID-19 infection in nonathletes. Wearable technology measuring HRV, RR, RHR, and recovery will be successful for early detection of COVID-19 in NCAA Division I female athletes. Cohort study. Level 2. Female athletes wore WHOOP, Inc. bands through the 2020 to 2021 competitive season. Of the athletes who tested positive for COVID (n = 33), 14 had enough data to be assessed (N = 14; 20.0 ± 1.3 years; 69.8 ± 7.2 kg; 172.0 ± 8.3 cm). Roughly 2 weeks of noninfected days were used to set baseline levels of HRV, RR, recovery, and RHR to compare with -3, -2, and -1 days before a positive COVID-19 result. Increases in RR (P = 0.02) were detected on day -3. RHR (P < 0.01) and RR increased (P < 0.01), while HRV decreased (P < 0.05) on day -1, compared with baseline. Differences were noted in all variables on the day of the positive COVID-19 result: decreased HRV (P < 0.05) and recovery scores (P < 0.01), and increased RHR (P < 0.01) and RR (P < 0.01). In female athletes, wearable technology was successful in predicting COVID-19 infection through changes in RR 3 days before a positive test, and also HRV and RHR the day before a positive test. Wearable technology may be used, as part of a multifaceted approach, for the early detection of COVID-19 in elite athletes through monitoring of HRV, RR, and RHR for overall team health.

Report on COVID-19 infection prevention and control training sessions for care homes provided by Kawaguchi city and comparison with those provided by the local governments in Japan

Objectives We compared COVID-19 prevention and control information provided to care homes (CHs) by the Kawaguchi City public health center (PHC), which utilizes our precedent advice on nfection, with the information from several local governments (LGs) in Japan. This study aimed to highlight the role of LG-associated doctors in providing information to CHs, utilizing their precedent advice on infection control in CHs and medical facilities. This study analyzed the sector and type of information the LGs should provide to CHs to prevent and control COVID-19.Methods We compared training sessions on COVID-19 prevention and control information provided to CHs by the Kawaguchi City PHC with training sessions offered by several other LGs in Japan that are available on their websites.Results The Kawaguchi City PHC has been providing COVID-19 information to CHs when needed, including prevention and control information, through their doctors, utilizing our precedent advice on infection control, management of health conditions of staff and residents, and early detection of COVID-19. In contrast, 68 LGs announced that they have provided training sessions to CHs for the prevention and control of COVID-19 through their official homepages from March to September 2022. These training sessions involved information dissemination by infection control specialist nurses (42.6%), clinic or hospital doctors (32.4%), infection control specialist doctors (11.8%), and staff from LG headquarters, PHC, or LG-associated doctors (51.5%). Among the 68 LGs, 41 provided information that included hand hygiene (95.1%), personal protective equipment (92.7%), proper ventilation (51.2%), and management of staff (90.2%) and resident (58.5%) health conditions. Furthermore, Kawaguchi City PHC and several LGs provided information for the early detection of COVID-19.Conclusion We suggest that LGs provide COVID-19 training sessions conducted by LG doctors that include management of staff and resident health conditions, provision of early detection information, and utilization of precedent advice on infection in CHs and medical facilities.

Deep learning framework for early detection of COVID-19 using X-ray images

Deep learning framework for early detection of COVID-19 using X-ray images

Diagnosis of COVID-19 Using Chest X-ray Images and Disease Symptoms Based on Stacking Ensemble Deep Learning.

The COVID-19 virus is one of the most devastating illnesses humanity has ever faced. COVID-19 is an infection that is hard to diagnose until it has caused lung damage or blood clots. As a result, it is one of the most insidious diseases due to the lack of knowledge of its symptoms. Artificial intelligence (AI) technologies are being investigated for the early detection of COVID-19 using symptoms and chest X-ray images. Therefore, this work proposes stacking ensemble models using two types of COVID-19 datasets, symptoms and chest X-ray scans, to identify COVID-19. The first proposed model is a stacking ensemble model that is merged from the outputs of pre-trained models in the stacking: multi-layer perceptron (MLP), recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU). Stacking trains and evaluates the meta-learner as a support vector machine (SVM) to predict the final decision. Two datasets of COVID-19 symptoms are used to compare the first proposed model with MLP, RNN, LSTM, and GRU models. The second proposed model is a stacking ensemble model that is merged from the outputs of pre-trained DL models in the stacking: VGG16, InceptionV3, Resnet50, and DenseNet121; it uses stacking to train and evaluate the meta-learner (SVM) to identify the final prediction. Two datasets of COVID-19 chest X-ray images are used to compare the second proposed model with other DL models. The result has shown that the proposed models achieve the highest performance compared to other models for each dataset.

Health Counseling and COVID-19 Screening Test at Universitas Nasional in 2021

Rapid tests for initial screening of COVID-19 are urgently needed given the very fast spread of the disease. However, WHO emphasized that this examination does not establish a clinical diagnosis of COVID-19 and is not recommended for triaging patients with suspected COVID-19, the rapid test is only an initial screening; Real-Time Reverse-Transcriptase Polymerase Chain Reaction (RT-PCR) must still confirm the results. Meanwhile, triage of patients uses a rapid risk assessment from the Ministry of Health which refers to the WHO Rapid Risk Assessment of Acute Public Health guidelines. In order to assist the government's program in preventing the spread of Covid-19, it is necessary to carry out health education about the behavior of preventing Covid-19 and early detection of Covid-19 by testing rapid antibodies at the National University. The results of the dedication activity showed that the participants were enthusiastic about listening to the material provided and participating in the inspection activities. Participants admitted that this inspection activity provided great benefits for breaking the chain of the spread of the coronavirus in the National University environment.

Early Detection of Asymptomatic Covid-19 Infection with Artificial Neural Network Model Through Voice Recording of Forced Cough

SARS-CoV-2 is a virus that spreads the infection known as COVID-19, or Coronavirus 2019. According to data from the World Health Organization as of March 15, 2021, Indonesia has 1,419,455 cumulative cases and 38,426 cumulative deaths, ranking third among countries in terms of fatalities, behind Iran and India. Because COVID-19 was disseminated through direct contact with respiratory droplets from an infected individual, it spread swiftly and widely. According to the American Centers for Disease Control and Prevention, more than 50% of transmission rates are anticipated from asymptomatic individuals. The antigen tests have an accuracy of results ranging from 80–90% and are utilized for early detection of COVID-19. The cost of the antigen test is set to increase as of September 3, 2021, with prices ranging from IDR 99.000 to IDR 109.000; however, researchers are steadfastly searching for the best alternate methods for the early diagnosis of COVID-19. According to MIT News Office, a forced cough recording can identify an asymptomatic COVID-19 infection. Through the vocal recording of a forced cough, this study uses an artificial neural network (ANN) deep learning model to identify asymptomatic COVID-19 patients. The Artificial Neural Network (ANN) can distinguish asymptomatic people from forced cough recordings with an accuracy of up to 98% and a loss value of less than 3% by employing oversampling data. This model can be applied as a free, universal method for the early identification of COVID-19 infection.

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

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

Machine Learning Model for Early Detection of COVID-19 by Heart Rhythm Abnormalities

Introduction. Electronic devices capable of collecting individual telemetry data have opened up prospects for preclinical detection of COVID-19 signs. Known solutions involve the analysis of information that is difficult to obtain at the moment. We are talking, specifically, about the blood condition or a PCR test. This significantly limits the possibility of integrating algorithms with wrist gadgets. At the same time, the cardiovascular system as an object of observation is quite informative, the data collection is well developed. The article describes the problem of detecting covid anomalies in rhythm strips. The work aims at creating a mathematical model based on machine learning algorithms to automate the process of detecting covid abnormalities in the heart rhythm. The possibility of integrating the results obtained with fitness bracelets and smart watches is shown.Materials and Methods. The work involved an open technology stack: Python, Scikit-learn, Lightgbm. When assessing the quality of models for binary classification, metric F1 was used. 229 cardiac rhythm strips (сardiointervalographies) of patients with COVID-19 were studied. The presence or absence of signs of an anomaly was determined taking into account the time of the rhythm strip and the intervals between heartbeats. Deviations that could indicate infection were shown graphically. Based on the exploratory analysis results, a list of signs indicating an anomaly was made.Results. As a result of the work done, a mathematical model was obtained that detected heart rate abnormalities specific to COVID-19 with an accuracy of 83 %. The basic features determining the predictive ability of the model were identified and ranked. They included the current value of the interval between heartbeats, the derivatives at the subsequent and previous points of measuring the duration of the heartbeat, the first derivative at the current point, and the deviation of the current value of the duration of the RR-interval from the median. The first indicator in this list was recognized as the most significant, the last — the least. For machine learning purposes, the potential of five algorithms was evaluated: IsolationForest, LGBMClassifier, RandomForestClassifier, ExtraTreesClassifier, SGDOneClassSVM. The normal and abnormal results of observations in isolation trees were visualized. A parameter was set that corresponded to the probability of regular observation outside the norm, and its value was selected — 0.11. Taking into account this indicator, a graph was constructed for the SGDOneClassSVM model. Based on the data set, using the cross-validation technique, the quality metric was calculated. The case in hand was a rhythm strip with a time series of observations taken in one continuous time interval from one person. A step-by-step process of obtaining averaged metric values for each model was described. In comparison, the highest indicator was recorded for the LGBMClassifier model, the lowest — for SGDOneClassSVM and IsolationForest.Discussion and Conclusions. The resulting mathematical model takes up little space in the memory of a mobile device, i.e., it does not impose significant requirements on computing resources. The solution has an acceptable detection quality for preclinical screening of COVID-19-related cardiovascular disorders. The algorithm detects anomalies in 83 % of cases. Four minutes is enough to record a rhythm strip. The proposed scenario for using an integrated solution is concise and easy to implement. Widespread use of the development can contribute to the detection of COVID-19 at an early stage.

Graph data science and machine learning for the detection of COVID-19 infection from symptoms.

COVID-19 is an infectious disease caused by SARS-CoV-2. The symptoms of COVID-19 vary from mild-to-moderate respiratory illnesses, and it sometimes requires urgent medication. Therefore, it is crucial to detect COVID-19 at an early stage through specific clinical tests, testing kits, and medical devices. However, these tests are not always available during the time of the pandemic. Therefore, this study developed an automatic, intelligent, rapid, and real-time diagnostic model for the early detection of COVID-19 based on its symptoms. The COVID-19 knowledge graph (KG) constructed based on literature from heterogeneous data is imported to understand the COVID-19 different relations. We added human disease ontology to the COVID-19 KG and applied a node-embedding graph algorithm called fast random projection to extract an extra feature from the COVID-19 dataset. Subsequently, experiments were conducted using two machine learning (ML) pipelines to predict COVID-19 infection from its symptoms. Additionally, automatic tuning of the model hyperparameters was adopted. We compared two graph-based ML models, logistic regression (LR) and random forest (RF) models. The proposed graph-based RF model achieved a small error rate = 0.0064 and the best scores on all performance metrics, including specificity = 98.71%, accuracy = 99.36%, precision = 99.65%, recall = 99.53%, and F1-score = 99.59%. Furthermore, the Matthews correlation coefficient achieved by the RF model was higher than that of the LR model. Comparative analysis with other ML algorithms and with studies from the literature showed that the proposed RF model exhibited the best detection accuracy. The graph-based RF model registered high performance in classifying the symptoms of COVID-19 infection, thereby indicating that the graph data science, in conjunction with ML techniques, helps improve performance and accelerate innovations.

A Multiplexed SERS Microassay for Accurate Detection of SARS-CoV-2 and Variants of Concern.

Severe acute respiratory syndrome coronavirus 2 variants play an important role in predicting patient outcome during postinfection, and with growing fears of COVID-19 reservoirs in domestic and wild animals, it is necessary to adapt detection systems for variant detection. However, variant-specific detection remains challenging. Surface-enhanced Raman scattering is a sensitive and multiplexing technique that allows the simultaneous detection of multiple targets for accurate identification. Here we propose the development of a multiplex SERS microassay to detect both the spike and nucleocapsid structural proteins of SARS-CoV-2. The designed SERS microassay integrates gold-silver hollow nanobox barcodes and electrohydrodynamically induced nanomixing which in combination enables highly specific and sensitive detection of SARS-CoV-2 and the S-protein epitopes to delineate between ancestral prevariant strains with the newer variants of concern, Delta and Omicron. The microassay allows detection from as low as 20 virus/μL and 50 pg/mL RBD protein and can clearly identify the virus among infected versus healthy nasopharyngeal swabs, with the potential to identify between variants. The detection of both S- and N-proteins of SARS-CoV-2 and the differentiation of variants on the SERS microassay can aid the early detection of COVID-19 to reduce transmission rates and lead into adequate treatments for those severely affected by the virus.

COVID -19 Predictions using Transfer Learning based Deep Learning Model with Medical Internet of Things

Early detection of COVID-19 may help medical expert for proper treatment plan and infection control. Internet of Things (IoT) has vital improvement in many areas including medical field. Deep learning also provide tremendous improvement in the field of medical. We have proposed a Transfer learning based deep learning model with medical Internet of Things for predicting COVID-19 from X-ray images. In the proposed method, the X ray images of patient are stored in cloud storage using internet for wide access. Then, the images are retrieved from cloud and Transfer learning based deep learning models namely VGG-16, Inception, Alexnet, Googlenet and Convolution neural Network models are applied on the X-rays images for predicting COVID 19, Normal and pneumonia classes. The pre-trained models helps to the effectiveness of deep learning accuracy and reduced the training time. The experimental analysis show that VGG -16 model gives accuracy of 99% for detecting COVID19 than other models.

Novel neural network architecture using sharpened cosine similarity for robust classification of Covid-19, pneumonia and tuberculosis diseases from X-rays

COVID-19 is a rapidly proliferating transmissible virus that substantially impacts the world population. Consequently, there is an increasing demand for fast testing, diagnosis, and treatment. However, there is a growing need for quick testing, diagnosis, and treatment. In order to treat infected individuals, stop the spread of the disease, and cure severe pneumonia, early covid-19 detection is crucial. Along with covid-19, various pneumonia etiologies, including tuberculosis, provide additional difficulties for the medical system. In this study, covid-19, pneumonia, tuberculosis, and other specific diseases are categorized using Sharpened Cosine Similarity Network (SCS-Net) rather than dot products in neural networks. In order to benchmark the SCS-Net, the model’s performance is evaluated on binary class (covid-19 and normal), and four-class (tuberculosis, covid-19, pneumonia, and normal) based X-ray images. The proposed SCS-Net for distinguishing various lung disorders has been successfully validated. In multiclass classification, the proposed SCS-Net succeeded with an accuracy of 94.05% and a Cohen’s kappa score of 90.70%; in binary class, it achieved an accuracy of 96.67% and its Cohen’s kappa score of 93.70%. According to our investigation, SCS in deep neural networks significantly lowers the test error with lower divergence. SCS significantly increases classification accuracy in neural networks and speeds up training.

Early stage prediction of COVID-19 Using machine learning model

The healthcare sector has traditionally been an early use of technological progress and has achieved significant advantages, especially in the field of machine learning like the prediction of diseases. The COVID-19 epidemic is still having an impact on every facet of life and necessitates a fast and accurate diagnosis. Early detection of COVID-19 is exceptionally critical to saving the lives of human beings. The need for an effective, rapid, and precise way to reduce consultants' workload in diagnosing suspected cases has emerged. This paper presents a proposed model that aims to design and implement an automated model to predict COVID-19 with high accuracy in the early stages. The dataset used in this study considers an imbalanced dataset and converted to a balanced one using Synthetic Minority Over Sampling Technique (SMOTE). Filter-based feature selection method and many machine learning algorithms such as K-Nearest Neighbor, Support Vector Machine, Decision Tree, Logistic Regression, and Random Forest (RF) is used in this model. Since the best classification result was achieved by using the RF algorithm, and this algorithm was optimized by tuning the hyperparameters. The optimized RF enhanced the accuracy from 98.0 to 99.5.

Sociodemographic and Clinical Characteristics Associated with Early Detection of COVID-19 in Kinshasa: Democratic Republic of Congo

Objective: COVID-19 is a disease that, as of 2020, has affected the whole world. Its spread being rapid, early detection would contribute to its control. This study aims to determine the sociodemographic and clinical characteristics associated with this detection fast in Kinshasa. Material and methods: A cross-sectional, descriptive study with an analytical aim is carried out on 713 people suspected of COVID-19 upon their admission to the Covid Treatment Center of the University Clinics of Kinshasa (CTC / CUK) between 2020 and 2021 through the exploitation of the database registering these patients. Data are analyzed using jamovi software version 2.3.18. Frequencies, Fisher's Exact test then logistic regression with α = 0.05 are used. Results: In total, we recorded 713 cases, 459 or 64.4% tested positive at the first screening. The median age is 59.0 years. The sex ratio is 1.7 in favor of men. The following characteristics are associated with early detection of COVID-19: advanced age (OR = 2.9 *1.03 – 8.29+); arterial hypertension (OR = 1.7 *1.15 – 2.52]); diabetes mellitus (OR = 3.66 [1.92 – 6.98]); body aches (OR = 0.41 [0.20 – 0.83]) as well as signs of respiratory distress (OR = 2.4 [1.44 – 3.87]). Conclusion: This study shows that elderly patients, those with a history of hypertension, diabetes and signs of respiratory distress tested positive at the first screening upon arrival at the CTC/CUK, unlike those with body aches. These cases would therefore require special attention from all staff of the COVID-19 response team for appropriate care.

Potential for Early Noninvasive COVID-19 Detection Using Electronic-Nose Technologies and Disease-Specific VOC Metabolic Biomarkers.

The established efficacy of electronic volatile organic compound (VOC) detection technologies as diagnostic tools for noninvasive early detection of COVID-19 and related coronaviruses has been demonstrated from multiple studies using a variety of experimental and commercial electronic devices capable of detecting precise mixtures of VOC emissions in human breath. The activities of numerous global research teams, developing novel electronic-nose (e-nose) devices and diagnostic methods, have generated empirical laboratory and clinical trial test results based on the detection of different types of host VOC-biomarker metabolites from specific chemical classes. COVID-19-specific volatile biomarkers are derived from disease-induced changes in host metabolic pathways by SARS-CoV-2 viral pathogenesis. The unique mechanisms proposed from recent researchers to explain how COVID-19 causes damage to multiple organ systems throughout the body are associated with unique symptom combinations, cytokine storms and physiological cascades that disrupt normal biochemical processes through gene dysregulation to generate disease-specific VOC metabolites targeted for e-nose detection. This paper reviewed recent methods and applications of e-nose and related VOC-detection devices for early, noninvasive diagnosis of SARS-CoV-2 infections. In addition, metabolomic (quantitative) COVID-19 disease-specific chemical biomarkers, consisting of host-derived VOCs identified from exhaled breath of patients, were summarized as possible sources of volatile metabolic biomarkers useful for confirming and supporting e-nose diagnoses.