Automatic Detection of Severely and Mildly Infected COVID-19 Patients with Supervised Machine Learning Models

The external validity of machine learning-based prediction scores from hematological parameters of COVID-19: A study using hospital records from Brazil, Italy, and Western Europe

The unprecedented worldwide pandemic caused by COVID-19 has motivated several research groups to develop machine-learning based approaches that aim to automate the diagnosis or screening of COVID-19, in large-scale. The gold standard for COVID-19 detection, quantitative-Real-Time-Polymerase-Chain-Reaction (qRT-PCR), is expensive and time-consuming. Alternatively, haematology-based detections were fast and near-accurate, although those were less explored. The external-validity of the haematology-based COVID-19-predictions on diverse populations are yet to be fully investigated. Here we report external-validity of machine learning-based prediction scores from haematological parameters recorded in different hospitals of Brazil, Italy, and Western Europe (raw sample size, 195554). The XGBoost classifier performed consistently better (out of seven ML classifiers) on all the datasets. The working models include a set of either four or fourteen haematological parameters. The internal performances of the XGBoost models (AUC scores range from 84% to 97%) were superior to ML models reported in the literature for some of these datasets (AUC scores range from 84% to 87%). The meta-validation on the external performances revealed the reliability of the performance (AUC score 86%) along with good accuracy of the probabilistic prediction (Brier score 14%), particularly when the model was trained and tested on fourteen haematological parameters from the same country (Brazil). The external performance was reduced when the model was trained on datasets from Italy and tested on Brazil (AUC score 69%) and Western Europe (AUC score 65%); presumably affected by factors, like, ethnicity, phenotype, immunity, reference ranges, across the populations. The state-of-the-art in the present study is the development of a COVID-19 prediction tool that is reliable and parsimonious, using a fewer number of hematological features, in comparison to the earlier study with meta-validation, based on sufficient sample size (n = 195554). Thus, current models can be applied at other demographic locations, preferably, with prior training of the model on the same population. Availability: https://covipred.bits-hyderabad.ac.in/home; https://github.com/debashreebanerjee/CoviPred.

Arteriolar Elasticity Measurement in the Fingertip Based on Photoplethysmographic Volume-Oscillometry: A New Approach to the Assessment of Vasomotor Functions in the Microvasculature

PURPOSE

Dysfunction of vasomotor reactions due to arteriolar smooth muscle causes serious adverse events, such as loss of hemodynamic coherence. This in turn can increase risks of cardiovascular-related diseases. A noninvasive and quantitative evaluation of microvascular disorder is therefore very important for early diagnosis and treatment. This paper describes a new approach to the assessment of vasomotor functions using the arteriolar elasticity measurement technique in the fingertip.

METHODS

A recently developed device, modified to detect a photoplethysmogram with green light (gPPG) in arteriolar regions, allowed the measurement of arteriolar blood pressure (BPca.) and gPPG from a left index fingertip placed on an occlusive cuff of the device. Arteriolar stiffness and distensibility were analyzed as effective elasticity indices, as a function of arteriolar distending pressure derived by volume-oscillometry. Cold pressor tests to induce vasoconstriction were carried out whether appropriate elasticity changes could be obtained.

RESULTS

Experiments using 6 healthy subjects were successfully made to obtain arteriolar elastic properties before and while immersing a right hand in cold water. The index-values of stiffness and distensibility showed, respectively, a considerable increase and decrease, clearly demonstrating the appropriate elasticity changes with vasoconstrictive reactions.

CONCLUSION

Although a further study using many subjects is needed, the results so far suggest that this method could easily provide important features to acquire quantitatively arteriolar elasticity together with BPca. and to assess vasomotor functions in the microvasculature. This convenient method appears useful for clinical practices and health management and promising also for screening cardiovascular-related diseases. (242/250 words).

Machine learning approaches to predict the need for intensive care unit admission among Iranian COVID-19 patients based on ICD-10: A cross-sectional study

Background & Aim

Timely identification of the patients requiring intensive care unit admission (ICU) could be life-saving. We aimed to compare different machine learning algorithms to predict the requirements for ICU admission in COVID-19 patients.

Methods

We screened all patients with COVID-19 at six academic hospitals in Tehran comprising our study population. A total of 44,112 COVID-19 patients (≥18 years old) were included, among which 7722 patients were hospitalized. We used a Random Forest algorithm to select significant variables. Then, prediction models were developed using the Support Vector Machine, Naıve Bayes, logistic regression, lightGBM, decision tree, and K-Nearest Neighbor algorithms. Sensitivity, specificity, accuracy, F1 score, and receiver operating characteristic-Area Under the Curve (AUC) were used to compare the prediction performance of different models.

Results

Based on random Forest, the following predictors were selected: age, cardiac disease, cough, hypertension, diabetes, influenza & pneumonia, malignancy, and nervous system disease. Age was found to have the strongest association with ICU admission among COVID-19 patients. All six models achieved an AUC greater than 0.60. Naıve Bayes achieved the best predictive performance (AUC = 0.71).

Conclusion

Naïve Bayes and lightGBM demonstrated promising results in predicting ICU admission needs in COVID-19 patients. Machine learning models could help quickly identify high-risk patients upon entry and reduce mortality and morbidity among COVID-19 patients.

A stochastic scale conjugate neural network procedure for the SIRC epidemic delay differential system

In this study, a stochastic computing structure is provided for the numerical solutions of the SIRC epidemic delay differential model, i.e. SIRC-EDDM using the dynamics of the COVID-19. The design of the scale conjugate gradient (CG) neural networks (SCGNNs) is presented for the numerical treatment of SIRC-EDDM. The mathematical model is divided into susceptible S ( ρ ) , recovered R ( ρ ) , infected I ( ρ ) , and cross-immune C ( ρ ) , while the numerical performances have been provided into three different cases. The exactitude of the SCGNNs is perceived through the comparison of the accomplished and reference outcomes (Runge-Kutta scheme) and the negligible absolute error (AE) that are performed around 10-06 to 10-08 for each case of the SIRC-EDDM. The obtained results have been presented to reduce the mean square error (MSE) using the performances of train, validation, and test data. The neuron analysis is also performed that shows the AE by taking 14 neurons provide more accurateness as compared to 4 numbers of neurons. To check the proficiency of SCGNNs, the comprehensive studies are accessible using the error histograms (EHs) investigations, state transitions (STs) values, MSE performances, regression measures, and correlation.

Development of Biomarkers and Prognosis Model of Mortality Risk in Patients with COVID-19

Background

As of 30 April 2023, the COVID-19 pandemic has resulted in over 6.9 million deaths worldwide. The virus continues to spread and mutate, leading to continuously evolving pathological and physiological processes. It is imperative to reevaluate predictive factors for identifying the risk of early disease progression.

Methods

A retrospective study was conducted on a cohort of 1379 COVID-19 patients who were discharged from Xin Hua Hospital affiliated with Shanghai Jiao Tong University School of Medicine between 15 December 2022 and 15 February 2023. Patient symptoms, comorbidities, demographics, vital signs, and laboratory test results were systematically documented. The dataset was split into testing and training sets, and 15 different machine learning algorithms were employed to construct prediction models. These models were assessed for accuracy and area under the receiver operating characteristic curve (AUROC), and the best-performing model was selected for further analysis.

Results

AUROC for models generated by 15 machine learning algorithms all exceeded 90%, and the accuracy of 10 of them also surpassed 90%. Light Gradient Boosting model emerged as the optimal choice, with accuracy of 0.928 ± 0.0006 and an AUROC of 0.976 ± 0.0028. Notably, the factors with the greatest impact on in-hospital mortality were growth stimulation expressed gene 2 (ST2,19.3%), interleukin-8 (IL-8,17.2%), interleukin-6 (IL-6,6.4%), age (6.1%), NT-proBNP (5.1%), interleukin-2 receptor (IL-2R, 5%), troponin I (TNI,4.6%), congestive heart failure (3.3%) in Light Gradient Boosting model.

Conclusion

ST-2, IL-8, IL-6, NT-proBNP, IL-2R, TNI, age and congestive heart failure were significant predictors of in-hospital mortality among COVID-19 patients.

Association of Coagulopathy and Inflammatory Biomarkers with Severity in SARS-CoV-2-Infected Individuals of the Al-Qunfudhah Region of Saudi Arabia

BACKGROUND

Identifying prognosticators/predictors of COVID-19 severity is the principal focus for early prediction and effective management of the disease in a time-bound and cost-effective manner. We aimed to evaluate COVID-19 severity-dependent alteration in inflammatory and coagulopathy biomarkers.

METHODS

A hospital-dependent retrospective observational study (total: n = 377; male, n = 213; and female, n = 164 participants) was undertaken. COVID-19 exposure was assessed by performing real-time PCR on nasopharyngeal (NP) swabs. Descriptive and inferential statistics were applied for both continuous and categorical variables using Rstudio-version-4.0.2. Pearson correlation and regression were executed with a cut-off of p < 0.05 for evaluating significance. Data representation by R-packages and ggplot2.

RESULTS

A significant variation in the mean ± SD (highly-sever (HS)/moderately severe (MS)) of CRP (HS/MS: 102.4 ± 22.9/21.3 ± 6.9, p-value < 0.001), D-dimer (HS/MS: 661.1 ± 80.6/348.7 ± 42.9, p-value < 0.001), and ferritin (HS/MS: 875.8 ± 126.8/593.4 ± 67.3, p-value < 0.001) were observed. Thrombocytopenia, high PT, and PTT exhibited an association with the HS individuals (p < 0.001). CRP was correlated with neutrophil (r = 0.77), ferritin (r = 0.74), and WBC (r = 0.8). D-dimer correlated with platelets (r = -0.82), PT (r = 0.22), and PTT (r = 0.37). The adjusted odds ratios (Ad-OR) of CRP, ferritin, D-dimer, platelet, PT, and PTT for HS compared to MS were 1.30 (95% CI -1.137, 1.50; p < 0.001), 1.048 (95% CI -1.03, 1.066; p < 0.001), 1.3 (95% CI -1.24, 1.49, p > 0.05), -0.813 (95% CI -0.734, 0.899, p < 0.001), 1.347 (95% CI -1.15, 1.57, p < 0.001), and 1.234 (95% CI -1.16, 1.314, p < 0.001), respectively.

CONCLUSION

SARS-CoV-2 caused alterations in vital laboratory parameters and raised ferritin, CRP, and D-dimer presented an association with disease severity at a significant level.

Detection of Severe Lung Infection on Chest Radiographs of COVID-19 Patients: Robustness of AI Models across Multi-Institutional Data

The diagnosis of severe COVID-19 lung infection is important because it carries a higher risk for the patient and requires prompt treatment with oxygen therapy and hospitalization while those with less severe lung infection often stay on observation. Also, severe infections are more likely to have long-standing residual changes in their lungs and may need follow-up imaging. We have developed deep learning neural network models for classifying severe vs. non-severe lung infections in COVID-19 patients on chest radiographs (CXR). A deep learning U-Net model was developed to segment the lungs. Inception-v1 and Inception-v4 models were trained for the classification of severe vs. non-severe COVID-19 infection. Four CXR datasets from multi-country and multi-institutional sources were used to develop and evaluate the models. The combined dataset consisted of 5748 cases and 6193 CXR images with physicians' severity ratings as reference standard. The area under the receiver operating characteristic curve (AUC) was used to evaluate model performance. We studied the reproducibility of classification performance using the different combinations of training and validation data sets. We also evaluated the generalizability of the trained deep learning models using both independent internal and external test sets. The Inception-v1 based models achieved AUC ranging between 0.81 ± 0.02 and 0.84 ± 0.0, while the Inception-v4 models achieved AUC in the range of 0.85 ± 0.06 and 0.89 ± 0.01, on the independent test sets, respectively. These results demonstrate the promise of using deep learning models in differentiating COVID-19 patients with severe from non-severe lung infection on chest radiographs.

Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers

The COVID-19 influenza emerged and proved to be fatal, causing millions of deaths worldwide. Vaccines were eventually discovered, effectively preventing the severe symptoms caused by the disease. However, some of the population (elderly and patients with comorbidities) are still vulnerable to severe symptoms such as breathlessness and chest pain. Identifying these patients in advance is imperative to prevent a bad prognosis. Hence, machine learning and deep learning algorithms have been used for early COVID-19 severity prediction using clinical and laboratory markers. The COVID-19 data was collected from two Manipal hospitals after obtaining ethical clearance. Multiple nature-inspired feature selection algorithms are used to choose the most crucial markers. A maximum testing accuracy of 95% was achieved by the classifiers. The predictions obtained by the classifiers have been demystified using five explainable artificial intelligence techniques (XAI). According to XAI, the most important markers are c-reactive protein, basophils, lymphocytes, albumin, D-Dimer and neutrophils. The models could be deployed in various healthcare facilities to predict COVID-19 severity in advance so that appropriate treatments could be provided to mitigate a severe prognosis. The computer aided diagnostic method can also aid the healthcare professionals and ease the burden on already suffering healthcare infrastructure.

Developing an interpretable machine learning model for predicting COVID-19 patients deteriorating prior to intensive care unit admission using laboratory markers

Coronavirus disease (COVID-19) remains a significant global health challenge, prompting a transition from emergency response to comprehensive management strategies. Furthermore, the emergence of new variants of concern, such as BA.2.286, underscores the need for early detection and response to new variants, which continues to be a crucial strategy for mitigating the impact of COVID-19, especially among the vulnerable population. This study aims to anticipate patients requiring intensive care or facing elevated mortality risk throughout their COVID-19 infection while also identifying laboratory predictive markers for early diagnosis of patients. Therefore, haematological, biochemical, and demographic variables were retrospectively evaluated in 8,844 blood samples obtained from 2,935 patients before intensive care unit admission using an interpretable machine learning model. Feature selection techniques were applied using precision-recall measures to address data imbalance and evaluate the suitability of the different variables. The model was trained using stratified cross-validation with k=5 and internally validated, achieving an accuracy of 77.27%, sensitivity of 78.55%, and area under the receiver operating characteristic (AUC) of 0.85; successfully identifying patients at increased risk of severe progression. From a medical perspective, the most important features of the progression or severity of patients with COVID-19 were lactate dehydrogenase, age, red blood cell distribution standard deviation, neutrophils, and platelets, which align with findings from several prior investigations. In light of these insights, diagnostic processes can be significantly expedited through the use of laboratory tests, with a greater focus on key indicators. This strategic approach not only improves diagnostic efficiency but also extends its reach to a broader spectrum of patients. In addition, it allows healthcare professionals to take early preventive measures for those most at risk of adverse outcomes, thereby optimising patient care and prognosis.

The Diagnostic Value of Inflammatory Markers (CRP, IL6, CRP/IL6, CRP/L, LCR) for Assessing the Severity of COVID-19 Symptoms Based on the MEWS and Predicting the Risk of Mortality

Introduction

Various diagnostic tools are used to assess the severity of COVID-19 symptoms and the risk of mortality, including laboratory tests and scoring indices such as the Modified Early Warning Score (MEWS). The diagnostic value of inflammatory markers for assessing patients with different severity of COVID-19 symptoms according to the MEWS was evaluated in this study.

Materials and Methods

The concentrations of CRP (C-reactive protein) (immunoassay) and IL6 (interleukin 6) (electrochemiluminescence assay) were determined, and CRP/IL6, CRP/L, and LCR ratios were calculated in blood serum samples collected from 374 COVID-19 patients.

Results

We demonstrated that CRP, IL6, CRP/IL6, CRP/L, LCR inflammatory markers increase significantly with disease progression assessed based on the MEWS in COVID-19 patients and may be used to differentiating patients with severe and non-severe COVID-19 and to assess the mortality.

Conclusion

The diagnostic value of inflammatory markers for assessing the risk of mortality and differentiating between patients with mild and severe COVID-19 was confirmed.

Prognostic Value of C-Reactive Protein in SARS-CoV-2 Infection: A Simplified Biomarker of COVID-19 Severity in Northern Ethiopia

Purpose

To evaluate the role of C-reactive protein (CRP) in predicting severe COVID-19 patients.

Methods

A prospective observational cohort study was conducted from July 15 to October 28, 2020, at Kuyha COVID-19 isolation and treatment center hospital, Mekelle City, Northern Ethiopia. A total of 670 blood samples were collected serially. SARS-CoV-2 infection was confirmed by RT-PCR from nasopharyngeal swabs and CRP concentration was determined using Cobas Integra 400 Plus (Roche). Data were analyzed using STATA version 14. P-value <0.05 was considered statistically significant.

Results

Overall, COVID-19 patients had significantly elevated CRP at baseline when compared to PCR-negative controls [median 11.1 (IQR: 2.0-127.8) mg/L vs 0.9 (IQR: 0.5-1.9) mg/L; p=0.0004)]. Those with severe COVID-19 clinical presentation had significantly higher median CRP levels compared to those with non-severe cases [166.1 (IQR: 48.6-332.5) mg/L vs 2.4 (IQR: 1.2-7.6) mg/L; p<0.00001)]. Moreover, COVID-19 patients exhibited higher median CRP levels at baseline [58 (IQR: 2.0-127.8) mg/L] that decreased significantly to 2.4 (IQR: 1.4-3.9) mg/L after 40 days after symptom onset (p<0.0001). Performance of CRP levels determined using ROC analysis distinguished severe from non-severe COVID-19 patients, with an AUC value of 0.83 (95% CI: 0.73-0.91; p=0.001; 77.4% sensitivity and 89.4% specificity). In multivariable analysis, CRP levels above 30 mg/L were significantly associated with an increased risk of developing severe COVID-19 for those who have higher ages and comorbidities (ARR 3.99, 95% CI: 1.35-11.82; p=0.013).

Conclusion

CRP was found to be an independent determinant factor for severe COVID-19 patients. Therefore, CRP levels in COVID-19 patients in African settings may provide a simple, prompt, and inexpensive assessment of the severity status at baseline and monitoring of treatment outcomes.

LogNNet model as a fast, simple and economical AI instrument in the diagnosis and prognosis of COVID-19

Rapid and effective detection of the diagnosis and prognosis of COVID-19 disease is important in terms of reducing the mortality of the disease and reducing the pressure on health systems. Methods such as PCR testing and computed tomography used for this purpose in current health systems are costly, require an expert team and take time. This study offers a fast, economical and reliable approach for the early diagnosis and prognosis of infectious diseases, especially COVID-19. For this purpose, characteristics of a large population of COVID-19 patients were determined (51 different routine blood values) and calibrated. In order to determine the diagnosis and prognosis of the disease, the calibrated features were run with the LogNNet model. LogNNet has a simple algorithm and performance indicators comparable to the most efficient algorithms available.This approach pointed out that routine blood values contain important information, especially in the detection of COVID-19, and showed that the LogNNet model can be used as an economical, safe and fast alternative tool in the diagnosis of this disease.-In the LogNNet feedforward neural network, a feature vector is passed through a specially designed reservoir matrix and transformed into a new feature vector of a different size, increasing the classification accuracy.-The presented network architecture can achieve 80%-99% classification accuracy using a range of weightings on devices with a total memory size of 1 to 29 kB constrained.-Due to the chaotic mapping procedures, the RAM usage in the LogNNet neural network processing process is greatly reduced. Hence, optimization of chaotic map parameters has an important function in LogNNet neural network application.

Investigating the performance of machine learning algorithms in predicting the survival of COVID-19 patients: A cross section study of Iran

Background and Aims

Like early diagnosis, predicting the survival of patients with Coronavirus Disease 2019 (COVID-19) is of great importance. Survival prediction models help doctors be more cautious to treat the patients who are at high risk of dying because of medical conditions. This study aims to predict the survival of hospitalized patients with COVID-19 by comparing the accuracy of machine learning (ML) models.

Methods

It is a cross-sectional study which was performed in 2022 in Fasa city in Iran country. The research data set was extracted from the period February 18, 2020 to February 10, 2021, and contains 2442 hospitalized patients' records with 84 features. A comparison was made between the efficiency of five ML algorithms to predict survival, includes Naive Bayes (NB), K-nearest neighbors (KNN), random forest (RF), decision tree (DT), and multilayer perceptron (MLP). Modeling steps were done with Python language in the Anaconda Navigator 3 environment.

Results

Our findings show that NB algorithm had better performance than others with accuracy, precision, recall, F-score, and area under receiver operating characteristic curve of 97%, 96%, 96%, 96%, and 97%, respectively. Based on the analysis of factors affecting survival, heart disease, pulmonary diseases and blood related disease were the most important disease related to death.

Conclusion

The development of software systems based on NB will be effective to predict the survival of COVID-19 patients.

Effect of ferritin, INR, and D-dimer immunological parameters levels as predictors of COVID-19 mortality: A strong prediction with the decision trees

Background and objective

A hyperinflammatory environment is thought to be the distinctive characteristic of COVID-19 infection and an important mediator of morbidity. This study aimed to determine the effect of other immunological parameter levels, especially ferritin, as a predictor of COVID-19 mortality via decision-trees analysis.

Material and method

This is a retrospective study evaluating a total of 2568 patients who died (n = 232) and recovered (n = 2336) from COVID-19 in August and December 2021. Immunological laboratory data were compared between two groups that died and recovered from patients with COVID-19. In addition, decision trees from machine learning models were used to evaluate the performance of immunological parameters in the mortality of the COVID-19 disease.

Results

Non-surviving from COVID-19 had 1.75 times higher ferritin, 10.7 times higher CRP, 2.4 times higher D-dimer, 1.14 times higher international-normalized-ratio (INR), 1.1 times higher Fibrinogen, 22.9 times higher procalcitonin, 3.35 times higher troponin, 2.77 mm/h times higher erythrocyte-sedimentation-rate (ESR), 1.13sec times longer prothrombin time (PT) when compared surviving patients. In addition, our interpretable decision tree, which was constructed with only the cut-off values of ferritin, INR, and D-dimer, correctly predicted 99.7% of surviving patients and 92.7% of non-surviving patients.

Conclusions

This study perfectly predicted the mortality of COVID-19 with our interpretable decision tree constructed with INR and D-dimer, especially ferritin. For this reason, we think that it may be important to include ferritin, INR, and D-dimer parameters and their cut-off values in the scoring systems to be planned for COVID-19 mortality.

Hematological, Inflammatory, Coagulation, and Oxidative/Antioxidant Biomarkers as Predictors for Severity and Mortality in COVID-19: A Prospective Cohort-Study

Purpose

Oxidative stress (OS) and inflammation are pivotal points in the pathophysiology of coronavirus disease-2019 (COVID-19). This study aims to use routine laboratory and oxidative stress/antioxidative biomarkers as predictors for the mortality of the disease.

Patients and Methods

This prospective cohort study, made up of 120 COVID-19 patients from emergency units in Erbil, Duhok, Kirkuk, and Sulaymaniyah cities in Iraq, from May the 1st to May the 30th, 2021, and 60 healthy controls (HCs) (n = 60). The patients were re-categorized into mild (n = 54), severe (n = 40), and critical (n = 26) groups based on the clinical criteria. Following admission to the hospital, blood was directly collected for measuring routine laboratory biomarkers.

Results

Neutrophils and neutrophil/lymphocyte ratio (NLR) were higher in the critical group, while lymphocytes were lower in the severe and critical groups compared to the mild group. The CRP, ferritin, and D-dimer values were more elevated in severe and critical cases than in mild COVID-19 cases. The levels of malondialdehyde (MDA), nitric oxide (NO), and copper were elevated, while the superoxide dismutase (SOD) activity level and total antioxidant capacity (TAC) level were lower. However, vitamin C, glutathione peroxidase (GPx), and catalase activity levels were not changed in the COVID-19 groups compared to the HCs. NO and ferritin were predictors of ICU hospitalization; D-dimer, MDA, and NLR were predictors of mortality. NO, and NLR were predictors of SpO2 depression. Moreover, NO, and copper have both good diagnostic values, their cutoffs were 39.01 and 11.93, respectively.

Conclusion

There is an association between immune dysregulation and oxidative imbalance. The biomarkers, that could be considered as predictors for the severity and mortality of COVID-19, are the NLR, NO, ferritin, and D-dimer. The age equal to and older than 50 has a poor prognosis in the Kurdish population.

Ct, IL-18 polymorphism, and laboratory biomarkers for predicting chemosensory dysfunctions and mortality in COVID-19

Aim

Patients with COVID-19 often experience chemosensory dysfunction. This research intends to uncover the association of RT-PCR Ct value with chemosensory dysfunctions and SpO2. This study also aims to investigate Ct, SpO2, CRP, D-dimer, and -607 IL-18 T/G polymorphism in order to find out predictors of chemosensory dysfunctions and mortality.

Materials & methods

This study included 120 COVID-19 patients, of which 54 were mild, 40 were severe and 26 were critical. CRP, D-dimer, RT-PCR, and IL-18 polymorphism were evaluated. Results & conclusion: Low Ct was associated with SpO2 dropping and chemosensory dysfunctions. IL-18 T/G polymorphism did not show an association with COVID-19 mortality; conversely, age, BMI, D-dimer and Ct values did.

Biomarkers: Promising and valuable tools towards diagnosis, prognosis and treatment of Covid-19 and other diseases

The use of biomarkers as early warning systems in the evaluation of disease risk has increased markedly in the last decade. Biomarkers are indicators of typical biological processes, pathogenic processes, or pharmacological reactions to therapy. The application and identification of biomarkers in the medical and clinical fields have an enormous impact on society. In this review, we discuss the history, various definitions, classifications, characteristics, and discovery of biomarkers. Furthermore, the potential application of biomarkers in the diagnosis, prognosis, and treatment of various diseases over the last decade are reviewed. The present review aims to inspire readers to explore new avenues in biomarker research and development.

Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application

Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.

Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network

Since February 2020, the world has been engaged in an intense struggle with the COVID-19 disease, and health systems have come under tragic pressure as the disease turned into a pandemic. The aim of this study is to obtain the most effective routine blood values (RBV) in the diagnosis and prognosis of COVID-19 using a backward feature elimination algorithm for the LogNNet reservoir neural network. The first dataset in the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 tests. The LogNNet-model achieved the accuracy rate of 99.5% in the diagnosis of the disease with 46 features and the accuracy of 99.17% with only mean corpuscular hemoglobin concentration, mean corpuscular hemoglobin, and activated partial prothrombin time. The second dataset consists of a total of 3899 patients with a diagnosis of COVID-19 who were treated in hospital, of which 203 were severe patients and 3696 were mild patients. The model reached the accuracy rate of 94.4% in determining the prognosis of the disease with 48 features and the accuracy of 82.7% with only erythrocyte sedimentation rate, neutrophil count, and C reactive protein features. Our method will reduce the negative pressures on the health sector and help doctors to understand the pathogenesis of COVID-19 using the key features. The method is promising to create mobile health monitoring systems in the Internet of Things.