Diagnosis and prediction of COVID-19 severity: can biochemical tests and machine learning be used as prognostic indicators?

Can the number of confirmed COVID-19 cases be predicted more accurately by including lifestyle data? An exploratory study for data-driven prediction of COVID-19 cases in metropolitan cities using deep learning models

Objective

The COVID-19 outbreak has significantly impacted human lifestyles and life patterns. Therefore, data related to human social life may tell us the increase or decrease in the number of confirmed COVID-19 cases. However, although the number of confirmed cases is affected by social life, it is difficult to find studies that attempt to predict the number of confirmed cases using various lifestyle data. This paper attempted an exploratory data analysis to see if the number of confirmed cases could be predicted more accurately by including various lifestyle data.

Methods

We included taking public transportation, watching a movie at the cinema, and accommodation at a motel in the lifestyle data. Finally, a 'lifestyle addition' set was constructed that added lifestyle data to the number of past confirmed cases and search term frequency data. The deep learning algorithms used in the analysis are deep neural networks (DNNs) and recurrent neural networks (RNNs). Performance differences across data sets and between deep learning models were tested to be statistically significant.

Results

Among metropolitan cities in South Korea, Seoul (9.6 million) with the largest population and Busan (3.4 million) with the second largest population had the lowest error rate in 'lifestyle addition' set. When predicting with the 'lifestyle addition' set, in Seoul, the error rate was reduced to 20.1%, and in Busan, the graph of the actual number of confirmed cases and the predicted graph were almost identical.

Conclusions

Through this study, we were able to identify three notable results that could contribute to predicting the number of patients infected with epidemic in the future.

Diagnosis, Severity, and Prognosis from Potential Biomarkers of COVID-19 in Urine: A Review of Clinical and Omics Results

The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has spurred an extraordinary scientific effort to better understand the disease's pathophysiology and develop diagnostic and prognostic tools to guide more precise and effective clinical management. Among the biological samples analyzed for biomarker identification, urine stands out due to its low risk of infection, non-invasive collection, and suitability for frequent, large-volume sampling. Integrating data from omics studies with standard biochemical analyses offers a deeper and more comprehensive understanding of COVID-19. This review aims to provide a detailed summary of studies published to date that have applied omics and clinical analyses on urine samples to identify potential biomarkers for COVID-19. In July 2024, an advanced search was conducted in Web of Science using the query: "covid* (Topic) AND urine (Topic) AND metabol* (Topic)". The search included results published up to 14 October 2024. The studies retrieved from this digital search were evaluated through a two-step screening process: first by reviewing titles and abstracts for eligibility, and then by retrieving and assessing the full texts of articles that met the specific criteria. The initial search retrieved 913 studies, of which 45 articles were ultimately included in this review. The most robust biomarkers identified include kynurenine, neopterin, total proteins, red blood cells, ACE2, citric acid, ketone bodies, hypoxanthine, amino acids, and glucose. The biological causes underlying these alterations reflect the multisystemic impact of COVID-19, highlighting key processes such as systemic inflammation, renal dysfunction, critical hypoxia, and metabolic stress.

Back to Basics: The Diagnostic Value of a Complete Blood Count in the Clinical Management of COVID-19

Since the beginning of the COVID-19 pandemic, scientists have struggled significantly to understand the complexity of COVID-19 pathophysiology. COVID-19 has demonstrated a notoriously unpredictable clinical course. This unpredictability constituted a significant obstacle to clinicians in predicting the disease course among COVID-19 patients, more specifically, in predicting who would develop severe cases and possibly die from the infection. This brief report aims to assess the diagnostic value of using a complete blood count (CBC) and applying high-dimensional analysis, i.e., principal component analysis (PCA), on it to differentiate between patients with mild and severe COVID-19 infection. The data of 855 patients were retrieved from multiple centres in Saudi Arabia. Descriptive statistics, such as counts, percentages, and medians (interquartile ranges) were used to describe patients' characteristics and CBC parameters. Analytical statistics, such as the Mann-Whitney U test, were used to compare between survivors and non-survivors. PCA was applied using the CBC parameters, and the results were compared between survivors and non-survivors. Patients in this study had a median age of 41, with an almost equal ratio of men to women. Most participants were Saudis, and non-survivors were 13.22% of the total cohort. The median values of all CBC indices were within reference ranges; however, some statistically significant differences were observed between survivors and non-survivors. Non-survivors had lower hemoglobin levels and lower hematocrit, lymphocyte, and eosinophil counts but higher WBC and neutrophil counts compared to survivors. PCA on the CBC results of survivors yielded a significantly different profile than non-survivors, indicating the possibility of its use in the context of COVID-19. The diagnostic value of CBC in the clinical management of COVID-19 should be utilized in clinical guidelines for managing COVID-19 cases.

Novel COVID-19 biomarkers identified through multi-omics data analysis: N-acetyl-4-O-acetylneuraminic acid, N-acetyl-L-alanine, N-acetyltriptophan, palmitoylcarnitine, and glycerol 1-myristate

This study aims to apply machine learning models to identify new biomarkers associated with the early diagnosis and prognosis of SARS-CoV-2 infection.Plasma and serum samples from COVID-19 patients (mild, moderate, and severe), patients with other pneumonia (but with negative COVID-19 RT-PCR), and healthy volunteers (control) from hospitals in four different countries (China, Spain, France, and Italy) were analyzed by GC-MS, LC-MS, and NMR. Machine learning models (PCA and PLS-DA) were developed to predict the diagnosis and prognosis of COVID-19 and identify biomarkers associated with these outcomes.A total of 1410 patient samples were analyzed. The PLS-DA model presented a diagnostic and prognostic accuracy of around 95% of all analyzed data. A total of 23 biomarkers (e.g., spermidine, taurine, L-aspartic, L-glutamic, L-phenylalanine and xanthine, ornithine, and ribothimidine) have been identified as being associated with the diagnosis and prognosis of COVID-19. Additionally, we also identified for the first time five new biomarkers (N-Acetyl-4-O-acetylneuraminic acid, N-Acetyl-L-Alanine, N-Acetyltriptophan, palmitoylcarnitine, and glycerol 1-myristate) that are also associated with the severity and diagnosis of COVID-19. These five new biomarkers were elevated in severe COVID-19 patients compared to patients with mild disease or healthy volunteers.The PLS-DA model was able to predict the diagnosis and prognosis of COVID-19 around 95%. Additionally, our investigation pinpointed five novel potential biomarkers linked to the diagnosis and prognosis of COVID-19: N-Acetyl-4-O-acetylneuraminic acid, N-Acetyl-L-Alanine, N-Acetyltriptophan, palmitoylcarnitine, and glycerol 1-myristate. These biomarkers exhibited heightened levels in severe COVID-19 patients compared to those with mild COVID-19 or healthy volunteers.

A prognostic model for SARS-CoV-2 breakthrough infection: Analyzing a prospective cellular immunity cohort

BACKGROUND

Following the COVID-19 pandemic, studies have identified several prevalent characteristics, especially related to lymphocyte subsets. However, limited research is available on the focus of this study, namely, the specific memory cell subsets among individuals who received COVID-19 vaccine boosters and subsequently experienced a SARS-CoV-2 breakthrough infection.

METHODS

Flow cytometry (FCM) was employed to investigate the early and longitudinal pattern changes of cellular immunity in patients with SARS-CoV-2 breakthrough infections following COVID-19 vaccine boosters. XGBoost (a machine learning algorithm) was employed to analyze cellular immunity prior to SARS-CoV-2 breakthrough, aiming to establish a prognostic model for SARS-CoV-2 breakthrough infections.

RESULTS

Following SARS-CoV-2 breakthrough infection, naïve T cells and TEMRA subsets increased while the percentage of TCM and TEM cells decreased. Naïve and non-switched memory B cells increased while switched and double-negative memory B cells decreased. The XGBoost model achieved an area under the curve (AUC) of 0.78, with an accuracy rate of 81.8 %, a sensitivity of 75 %, and specificity of 85.7 %. TNF-α, CD27-CD19+cells, and TEMRA subsets were identified as high predictors. An increase in TNF-α, cTfh, double-negative memory B cells, IL-6, IL-10, and IFN-γ prior to SARS-CoV-2 infection was associated with enduring clinical symptoms; conversely, an increase in CD3+ T cells, CD4+ T cells, and IL-2 was associated with clinical with non-enduring clinical symptoms.

CONCLUSION

SARS-CoV-2 breakthrough infection leads to disturbances in cellular immunity. Assessing cellular immunity prior to breakthrough infection serves as a valuable prognostic tool for SARS-CoV-2 infection, which facilitates clinical decision-making.

[Prevention and treatment of COVID-19 based on post-genomic pharmacological analysis: Systematic computer analysis of 290,000 scientific articles on COVID-19]

The COVID-19 pandemic has highlighted pressing challenges in biomedical research methodology. It has become obvious that the rapid and effective development of treatments for "new" viral infections is impossible without the coordination of interdisciplinary research and in-depth analysis of data obtained within the framework of the post-genomic paradigm. Presents the results of a systematic computer analysis of 290,000 scientific articles on COVID-19, with an emphasis on the results of post-genomic studies of SARS-CoV-2. The futility of the overly simplified approach, which considers only one "most important receptor protein", only one "key virus gene", etc., is shown. It is shown how post-genomic technologies will make it possible to find informative biomarkers of severe coronavirus infection, including those based on complex immune disorders associated with COVID-19.

Difference in mortality risk predicted by leukocyte and lymphocyte levels in COVID-19 patients infected with the Wild-type, Delta, and Omicron strains

This study aimed to investigate the changing trends, level differences, and prognostic performance of the leukocyte and lymphocyte levels of patients infected with the Wild strains, Delta strains and Omicron strains to provide a reference for prognostic assessment. In the current study, we conducted a retrospective cross-sectional study to evaluate the changing trends, level differences, and prognostic performance of leukocyte and lymphocyte of different strains at admission and discharge may already exist in patients with coronavirus disease-2019 (COVID-19) infected with the Wild type, Delta, and Omicron strains. A retrospective cross-sectional study was conducted. We recruited and screened the 243 cases infected with the Wild-type strains in Wuhan, the 629 cases infected with the Delta and 116 cases infected strains with the Omicron strains in Xi'an. The leukocyte and lymphocyte levels were compared the cohort of Wild-type infection with the cohort of Delta and the Omicron. The changes in the levels of leukocytes and lymphocytes exhibit a completely opposite trend in patients with COVID-19 infected with the different strains. The lymphocyte level at admission and discharge in patients with COVID-19 infected with Omicron strains (area under curve [AUC] receiver operating characteristic curve [ROC] 72.8-90.2%, 82.8-97.2%) presented better performance compared patients with COVID-19 infected with Wild type strains (AUC ROC 60.9-80.7%, 82.3-97.2%) and Delta strains (AUC ROC 56.1-84.7%, 40.3-93.3%). Kaplan-Meier curves showed that the leukocyte levels above newly established cutoff values and the lymphocyte levels below newly established cutoff values had a significantly higher risk of in-hospital mortality in COVID-19 patients with Wild-type and Omicron strains (P < .01). The levels of leukocyte and lymphocyte at admission and discharge in patients with COVID-19 infected with the Wild type, Delta, and Omicron strains may be differences among strains, which indicates different death risks. Our research may help clinicians identify patients with a poor prognosis for severe acute respiratory syndrome coronavirus 2 infection.

Feature selection for effective prediction of SARS-COV-2 using machine learning

BACKGROUND

With rise in variants of SARS-CoV-2, it is necessary to classify the emerging SARS-CoV-2 for early detection and thereby reduce human transmission. Genomic and proteomic information have less frequently been used for classifying in a machine learning (ML) approach for detection of SARS-CoV-2.

OBJECTIVE

With this aim we used nucleoprotein and viral proteomic evolutionary information of SARS-CoV-2 along with the charge and basicity distribution of amino acids from various strains of SARS-CoV-2 to generate a disease severity model based on ML.

METHODS

All sequence and clinical data were obtained from GISAID. Proteomic level calculations were added to comprise the dataset. The training set was used for feature selection. Select K- Best feature selection method was employed which was cross validated with testing set and performance evaluated. Delong's test was also done. We also employed BIRCH clustering on SARS-CoV-2 for clustering the strains.

RESULTS

Out of six ML models four were successful in training and testing. Extra Trees algorithm generated a micro-averaged F1-score of 74.2% and a weighted averaged area under the receiver operating characteristic curve (AUC-ROC) score of 73.7% with multi-class option. The feature selection set to 5, enhanced the ROC AUC from 73.7 to 76.4%. Accuracy of the selected model of 86.9% was achieved.

CONCLUSION

The unique features identified in the ML approach was able to classify disease severity into classes and had potential for predicting risk in newer variants.

Urine Parameters in Patients with COVID-19 Infection

A urine test permits the measure of several urinary markers. This is a non-invasive method for early monitoring of potential kidney damage. In COVID-19 patients, alterations of urinary markers were observed. This review aims to evaluate the utility of urinalysis in predicting the severity of COVID-19. A total of 68 articles obtained from PubMed studies reported that (i) the severity of disease was related to haematuria and proteinuria and that (ii) typical alterations of the urinary sediment were noticed in COVID-19-associated AKI patients. This review emphasizes that urinalysis and microscopic examination support clinicians in diagnosing and predicting COVID-19 severity.

Association between SUMF1 polymorphisms and COVID-19 severity

BACKGROUND

Evidence shows that genetic factors play important roles in the severity of coronavirus disease 2019 (COVID-19). Sulfatase modifying factor 1 (SUMF1) gene is involved in alveolar damage and systemic inflammatory response. Therefore, we speculate that it may play a key role in COVID-19.

RESULTS

We found that rs794185 was significantly associated with COVID-19 severity in Chinese population, under the additive model after adjusting for gender and age (for C allele = 0.62, 95% CI = 0.44-0.88, P = 0.0073, logistic regression). And this association was consistent with this in European population Genetics Of Mortality In Critical Care (GenOMICC: OR for C allele = 0.94, 95% CI = 0.90-0.98, P = 0.0037). Additionally, we also revealed a remarkable association between rs794185 and the prothrombin activity (PTA) in subjects (P = 0.015, Generalized Linear Model).

CONCLUSIONS

In conclusion, our study for the first time identified that rs794185 in SUMF1 gene was associated with the severity of COVID-19.

Automatic COVID-19 prediction using explainable machine learning techniques

The coronavirus is considered this century's most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person's body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms.

Predicting intubation risk among COVID-19 hospitalized patients using artificial neural networks

BACKGROUND

Accurately predicting the intubation risk in COVID-19 patients at the admission time is critical to optimal use of limited hospital resources, providing customized and evidence-based treatments, and improving the quality of delivered medical care services. This study aimed to design a statistical algorithm to select the best features influencing intubation prediction in coronavirus disease 2019 (COVID-19) hospitalized patients. Then, using selected features, multiple artificial neural network (ANN) configurations were developed to predict intubation risk.

MATERIAL AND METHODS

In this retrospective single-center study, a dataset containing 482 COVID-19 patients who were hospitalized between February 9, 2020 and July 20, 2021 was used. First, the Phi correlation coefficient method was performed for selecting the most important features affecting COVID-19 patients' intubation. Then, the different configurations of ANN were developed. Finally, the performance of ANN configurations was assessed using several evaluation metrics, and the best structure was determined for predicting intubation requirements among hospitalized COVID-19 patients.

RESULTS

The ANN models were developed based on 18 validated features. The results indicated that the best performance belongs to the 18-20-1 ANN configuration with positive predictive value (PPV) = 0.907, negative predictive value (NPV) = 0.941, sensitivity = 0.898, specificity = 0.951, and area under curve (AUC) = 0.906.

CONCLUSIONS

The results demonstrate the effectiveness of the ANN models for timely and reliable prediction of intubation risk in COVID-19 hospitalized patients. Our models can inform clinicians and those involved in policymaking and decision making for prioritizing restricted mechanical ventilation and other related resources for critically COVID-19 patients.

Machine Learning Successfully Detects Patients with COVID-19 Prior to PCR Results and Predicts Their Survival Based on Standard Laboratory Parameters in an Observational Study

INTRODUCTION

In the current COVID-19 pandemic, clinicians require a manageable set of decisive parameters that can be used to (i) rapidly identify SARS-CoV-2 positive patients, (ii) identify patients with a high risk of a fatal outcome on hospital admission, and (iii) recognize longitudinal warning signs of a possible fatal outcome.

METHODS

This comparative study was performed in 515 patients in the Maria Skłodowska-Curie Specialty Voivodeship Hospital in Zgierz, Poland. The study groups comprised 314 patients with COVID-like symptoms who tested negative and 201 patients who tested positive for SARS-CoV-2 infection; of the latter, 72 patients with COVID-19 died and 129 were released from hospital. Data on which we trained several machine learning (ML) models included clinical findings on admission and during hospitalization, symptoms, epidemiological risk, and reported comorbidities and medications.

RESULTS

We identified a set of eight on-admission parameters: white blood cells, antibody-synthesizing lymphocytes, ratios of basophils/lymphocytes, platelets/neutrophils, and monocytes/lymphocytes, procalcitonin, creatinine, and C-reactive protein. The medical decision tree built using these parameters differentiated between SARS-CoV-2 positive and negative patients with up to 90-100% accuracy. Patients with COVID-19 who on hospital admission were older, had higher procalcitonin, C-reactive protein, and troponin I levels together with lower hemoglobin and platelets/neutrophils ratio were found to be at highest risk of death from COVID-19. Furthermore, we identified longitudinal patterns in C-reactive protein, white blood cells, and D dimer that predicted the disease outcome.

CONCLUSIONS

Our study provides sets of easily obtainable parameters that allow one to assess the status of a patient with SARS-CoV-2 infection, and the risk of a fatal disease outcome on hospital admission and during the course of the disease.

Predicting Risk of Mortality in COVID-19 Hospitalized Patients using Hybrid Machine Learning Algorithms

BACKGROUND

Since hospitalized patients with COVID-19 are considered at high risk of death, the patients with the sever clinical condition should be identified. Despite the potential of machine learning (ML) techniques to predict the mortality of COVID-19 patients, high-dimensional data is considered a challenge, which can be addressed by metaheuristic and nature-inspired algorithms, such as genetic algorithm (GA).

OBJECTIVE

This paper aimed to compare the efficiency of the GA with several ML techniques to predict COVID-19 in-hospital mortality.

MATERIAL AND METHODS

In this retrospective study, 1353 COVID-19 in-hospital patients were examined from February 9 to December 20, 2020. The GA technique was applied to select the important features, then using selected features several ML algorithms such as K-nearest-neighbor (K-NN), Decision Tree (DT), Support Vector Machines (SVM), and Artificial Neural Network (ANN) were trained to design predictive models. Finally, some evaluation metrics were used for the comparison of developed models.

RESULTS

A total of 10 features out of 56 were selected, including length of stay (LOS), age, cough, respiratory intubation, dyspnea, cardiovascular diseases, leukocytosis, blood urea nitrogen (BUN), C-reactive protein, and pleural effusion by 10-independent execution of GA. The GA-SVM had the best performance with the accuracy and specificity of 9.5147e+01 and 9.5112e+01, respectively.

CONCLUSION

The hybrid ML models, especially the GA-SVM, can improve the treatment of COVID-19 patients, predict severe disease and mortality, and optimize the utilization of health resources based on the improvement of input features and the adaption of the structure of the models.

Predictive models for COVID-19 detection using routine blood tests and machine learning

The problem of accurate, fast, and inexpensive COVID-19 tests has been urgent till now. Standard COVID-19 tests need high-cost reagents and specialized laboratories with high safety requirements, are time-consuming. Data of routine blood tests as a base of SARS-CoV-2 invasion detection allows using the most practical medicine facilities. But blood tests give general information about a patient's state, which is not directly associated with COVID-19. COVID-19-specific features should be selected from the list of standard blood characteristics, and decision-making software based on appropriate clinical data should be created. This review describes the abilities to develop predictive models for COVID-19 detection using routine blood tests and machine learning.

Comparison of clinical characteristics in adult patients under 65 years of age with and without Covid-19 pneumonia

Background

Coronavirus disease 2019 (COVID-19) can cause asymptomatic, mild upper respiratory tract symptoms and pneumonia in young persons. How the disease will progress in each patient is still unknown. Therefore, we aimed to investigate the prognostic markers of the development of pneumonia and the clinical characteristics of patients under 65 years with COVID-19 confirmed by a positive reverse transcriptase polymerase chain reaction test.

Methods

In this retrospective study, a total of 271 patients admitted in our unit were included. The patients were divided into two groups, those who did and those who did not develop pneumonia. Their clinical features, treatment protocols, and laboratory parameters were recorded retrospectively.

Results

Pneumonia developed in 67.9% (n = 184) of the cases. The age in the pneumonia group was higher than that in the non-pneumonia group (p < 0.001). In the logistic regression analysis, the symptom and co-morbidity status were examined according to the presence of pneumonia; hypertension (HT) (OR: 4525, 95% CL: 1,494-13,708) was the most important risk factor for pneumonia. When age and laboratory values were examined according to the presence of pneumonia, advanced age (OR: 1.042, 95% CL: 1.01-1.073), low albumin (OR: 0.917, 95% CL: 0.854-0.986), and high troponin (OR: 1.291, 95% CL: 1.044-1.596) were identified as risk factors for pneumonia.

Conclusion

In this article, HT (22.3%, P < 0.001) has been considered as an important risk factor, whereas association of diabetes mellitus (21.2%, P 0.029) and smoking (25.0%, P 0.038) was also significant. The median age of the group was 51 (41.5-58) in the group developing pneumonia and 41 (30-48) in the non-developing group. Young patients with these predictive factors should be more carefully evaluated by further diagnostic procedures, such as thoracic computed tomography.

Predicting the Need for Intubation among COVID-19 Patients Using Machine Learning Algorithms: A Single-Center Study

Background: Owing to the shortage of ventilators, there is a crucial demand for an objective and accurate prognosis for 2019 coronavirus disease (COVID-19) critical patients, which may necessitate a mechanical ventilator (MV). This study aimed to construct a predictive model using machine learning (ML) algorithms for frontline clinicians to better triage endangered patients and priorities who would need MV.

Methods: In this retrospective single-center study, the data of 482 COVID-19 patients from February 9, 2020, to December 20, 2020, were analyzed by several ML algorithms including, multi-layer perception (MLP), logistic regression (LR), J-48 decision tree, and Naïve Bayes (NB). First, the most important clinical variables were identified using the Chi-square test at P < 0.01. Then, by comparing the ML algorithms' performance using some evaluation criteria, including TP-Rate, FP-Rate, precision, recall, F-Score, MCC, and Kappa, the best performing one was identified.

Results: Predictive models were trained using 15 validated features, including cough, contusion, oxygen therapy, dyspnea, loss of taste, rhinorrhea, blood pressure, absolute lymphocyte count, pleural fluid, activated partial thromboplastin time, blood glucose, white cell count, cardiac diseases, length of hospitalization, and other underline diseases. The results indicated the J-48 with F-score = 0.868 and AUC = 0.892 yielded the best performance for predicting intubation requirement.

Conclusion: ML algorithms are potentials to improve traditional clinical criteria to forecast the necessity for intubation in COVID-19 in-hospital patients. Such ML-based prediction models may help physicians with optimizing the timing of intubation, better sharing of MV resources and personnel, and increase patient clinical status.

Machine Learning-Based COVID-19 Classification Using E-Adopted CT Scans

In recent years, several machine learning models were successfully deployed in various fields. However, a huge quantity of data is required for training good machine learning. Data are distributivity stored across multiple sources and centralizing those data leads to privacy and security issues. To solve this problem, the proposed federated-based method works by exchanging the parameters of three locally trained machine learning models without compromising privacy. Each machine learning model uses the e-adoption of CT scans for improving their training knowledge. The CT scans are electronically transferred between various medical centers. Proper care is taken to prevent identify loss from the e-adopted data. To normalize the parameters, a novel weighting scheme is also exchanged along with the parameters. Thus, the global model is trained with more heterogeneous samples to increase performance. Based on the experiment, the proposed algorithm has obtained 89% of accuracy, which is 32% more than the existing machine learning models.

Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model

Due to the COVID-19 pandemic, computerized COVID-19 diagnosis studies are proliferating. The diversity of COVID-19 models raises the questions of which COVID-19 diagnostic model should be selected and which decision-makers of healthcare organizations should consider performance criteria. Because of this, a selection scheme is necessary to address all the above issues. This study proposes an integrated method for selecting the optimal deep learning model based on a novel crow swarm optimization algorithm for COVID-19 diagnosis. The crow swarm optimization is employed to find an optimal set of coefficients using a designed fitness function for evaluating the performance of the deep learning models. The crow swarm optimization is modified to obtain a good selected coefficient distribution by considering the best average fitness. We have utilized two datasets: the first dataset includes 746 computed tomography images, 349 of them are of confirmed COVID-19 cases and the other 397 are of healthy individuals, and the second dataset are composed of unimproved computed tomography images of the lung for 632 positive cases of COVID-19 with 15 trained and pretrained deep learning models with nine evaluation metrics are used to evaluate the developed methodology. Among the pretrained CNN and deep models using the first dataset, ResNet50 has an accuracy of 91.46% and a F1-score of 90.49%. For the first dataset, the ResNet50 algorithm is the optimal deep learning model selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5715.988 for COVID-19 computed tomography lung images case considered differential advancement. In contrast, the VGG16 algorithm is the optimal deep learning model is selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5758.791 for the second dataset. Overall, InceptionV3 had the lowest performance for both datasets. The proposed evaluation methodology is a helpful tool to assist healthcare managers in selecting and evaluating the optimal COVID-19 diagnosis models based on deep learning.

Development of neural network models for prediction of the outcome of COVID-19 hospitalized patients based on initial laboratory findings, demographics, and comorbidities

Background

During the process of the treatment of COVID-19 hospitalized patients, physicians still face a lot of unknowns and problems. Despite the application of the treatment protocol, it is still unknown why the medical status of a certain number of patients worsens and ends with death. Many factors were analyzed for the prediction of the clinical outcome of the patients using different methods. The aim of this paper was to develop a prediction model based on initial laboratory blood test results, accompanying comorbidities, and demographics to help physicians to better understand the medical state of patients with respect to possible clinical outcomes using neural networks, hypothesis testing, and confidence intervals.

Methods

The research had retrospective-prospective, descriptive, and analytical character. As inputs for this research, 12 components of laboratory blood test results, six accompanying comorbidities, and demographics (age and gender) data were collected from hospital information system in Sarajevo for each patient from a sample of 634 hospitalized patients. Clinical outcome of the hospitalized patients, survival or death, was recorded 30 days after admission to the hospital. The prediction model was designed using a neural network. In addition, formal hypothesis tests were performed to investigate whether there were significant differences in laboratory blood test results and age between patients who died and those who survived, including the construction of 95% confidence intervals.

Results

In this paper, 11 neural networks were developed with different threshold values to determine the optimal neural network with the highest prediction performance. The performances of the neural networks were evaluated by accuracy, precision, sensitivity, and specificity. Optimal neural network model evaluation metrics are: accuracy = 87.78%, precision = 96.37%, sensitivity = 90.07%, and specificity = 62.16%. Significantly higher values (P < 0.05) of blood laboratory result components and age were detected in patients who died.

Conclusion

Optimal neural network model, results of hypothesis tests, and confidence intervals could help to predict, analyze, and better understand the medical state of COVID-19 hospitalized patients and thus reduce the mortality rate.

Diagnosis and prognosis of COVID-19 employing analysis of patients' plasma and serum via LC-MS and machine learning

OBJECTIVE

To implement and evaluate machine learning (ML) algorithms for the prediction of COVID-19 diagnosis, severity, and fatality and to assess biomarkers potentially associated with these outcomes.

MATERIAL AND METHODS

Serum (n = 96) and plasma (n = 96) samples from patients with COVID-19 (acute, severe and fatal illness) from two independent hospitals in China were analyzed by LC-MS. Samples from healthy volunteers and from patients with pneumonia caused by other viruses (i.e. negative RT-PCR for COVID-19) were used as controls. Seven different ML-based models were built: PLS-DA, ANNDA, XGBoostDA, SIMCA, SVM, LREG and KNN.

RESULTS

The PLS-DA model presented the best performance for both datasets, with accuracy rates to predict the diagnosis, severity and fatality of COVID-19 of 93%, 94% and 97%, respectively. Low levels of the metabolites ribothymidine, 4-hydroxyphenylacetoylcarnitine and uridine were associated with COVID-19 positivity, whereas high levels of N-acetyl-glucosamine-1-phosphate, cysteinylglycine, methyl isobutyrate, l-ornithine and 5,6-dihydro-5-methyluracil were significantly related to greater severity and fatality from COVID-19.

CONCLUSION

The PLS-DA model can help to predict SARS-CoV-2 diagnosis, severity and fatality in daily practice. Some biomarkers typically increased in COVID-19 patients' serum or plasma (i.e. ribothymidine, N-acetyl-glucosamine-1-phosphate, l-ornithine, 5,6-dihydro-5-methyluracil) should be further evaluated as prognostic indicators of the disease.

Predicting COVID-19 outcomes from clinical and laboratory parameters in an intensive care facility during the second wave of the pandemic in South Africa

Background

The second wave of coronavirus disease 2019 (COVID-19) in South Africa was caused by the Beta variant of severe acute respiratory syndrome coronavirurus-2. This study aimed to explore clinical and biochemical parameters that could predict outcome in patients with COVID-19.

Methods

A prospective study was conducted between 5 November 2020 and 30 April 2021 among patients with confirmed COVID-19 admitted to the intensive care unit (ICU) of a tertiary hospital. The Cox proportional hazards model in Stata 16 was used to assess risk factors associated with survival or death. Factors with P<0.05 were considered significant.

Results

Patients who died were found to have significantly lower median pH (P<0.001), higher median arterial partial pressure of carbon dioxide (P<0.001), higher D-dimer levels (P=0.001), higher troponin T levels (P=0.001), higher N-terminal-prohormone B-type natriuretic peptide levels (P=0.007) and higher C-reactive protein levels (P=0.010) compared with patients who survived. Increased standard bicarbonate (HCO3std) was associated with lower risk of death (hazard ratio 0.96, 95% confidence interval 0.93-0.99).

Conclusions

The mortality of patients with COVID-19 admitted to the ICU was associated with elevated D-dimer and a low HCO3std level. Large studies are warranted to increase the identification of patients at risk of poor prognosis, and to improve the clinical approach.

CT-based severity assessment for COVID-19 using weakly supervised non-local CNN

Evaluating patient criticality is the foremost step in administering appropriate COVID-19 treatment protocols. Learning an Artificial Intelligence (AI) model from clinical data for automatic risk-stratification enables accelerated response to patients displaying critical indicators. Chest CT manifestations including ground-glass opacities and consolidations are a reliable indicator for prognostic studies and show variability with patient condition. To this end, we propose a novel attention framework to estimate COVID-19 severity as a regression score from a weakly annotated CT scan dataset. It takes a non-locality approach that correlates features across different parts and spatial scales of the 3D scan. An explicit guidance mechanism from limited infection labeling drives attention refinement and feature modulation. The resulting encoded representation is further enriched through cross-channel attention. The attention model also infuses global contextual awareness into the deep voxel features by querying the base CT scan to mine relevant features. Consequently, it learns to effectively localize its focus region and chisel out the infection precisely. Experimental validation on the MosMed dataset shows that the proposed architecture has significant potential in augmenting existing methods as it achieved a 0.84 R-squared score and 0.133 mean absolute difference.

Predicting Severe Disease and Critical Illness on Initial Diagnosis of COVID-19: Simple Triage Tools

Rationale

This study was conducted to develop, validate, and compare prediction models for severe disease and critical illness among symptomatic patients with confirmed COVID-19.

Methods

For development cohort, 433 symptomatic patients diagnosed with COVID-19 between April 15th 2020 and June 30th, 2020 presented to Tawam Public Hospital, Abu Dhabi, United Arab Emirates were included in this study. Our cohort included both severe and non-severe patients as all cases were admitted for purpose of isolation as per hospital policy. We examined 19 potential predictors of severe disease and critical illness that were recorded at the time of initial assessment. Univariate and multivariate logistic regression analyses were used to construct predictive models. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC). Calibration and goodness of fit of the models were assessed. A cohort of 213 patients assessed at another public hospital in the country during the same period was used to validate the models.

Results

One hundred and eighty-six patients were classified as severe while the remaining 247 were categorized as non-severe. For prediction of progression to severe disease, the three independent predictive factors were age, serum lactate dehydrogenase (LDH) and serum albumin (ALA model). For progression to critical illness, the four independent predictive factors were age, serum LDH, kidney function (eGFR), and serum albumin (ALKA model). The AUC for the ALA and ALKA models were 0.88 (95% CI, 0.86–0.89) and 0.85 (95% CI, 0.83–0.86), respectively. Calibration of the two models showed good fit and the validation cohort showed excellent discrimination, with an AUC of 0.91 (95% CI, 0.83–0.99) for the ALA model and 0.89 (95% CI, 0.80–0.99) for the ALKA model. A free web-based risk calculator was developed.

Conclusions

The ALA and ALKA predictive models were developed and validated based on simple, readily available clinical and laboratory tests assessed at presentation. These models may help frontline clinicians to triage patients for admission or discharge, as well as for early identification of patients at risk of developing critical illness.

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Several Artificial Intelligence-based models have been developed for COVID-19 disease diagnosis. In spite of the promise of artificial intelligence, there are very few models which bridge the gap between traditional human-centered diagnosis and the potential future of machine-centered disease diagnosis. Under the concept of human-computer interaction design, this study proposes a new explainable artificial intelligence method that exploits graph analysis for feature visualization and optimization for the purpose of COVID-19 diagnosis from blood test samples. In this developed model, an explainable decision forest classifier is employed to COVID-19 classification based on routinely available patient blood test data. The approach enables the clinician to use the decision tree and feature visualization to guide the explainability and interpretability of the prediction model. By utilizing this novel feature selection phase, the proposed diagnosis model will not only improve diagnosis accuracy but decrease the execution time as well.

Does COVID-19 Clinical Status Associate with Outcome Severity? An Unsupervised Machine Learning Approach for Knowledge Extraction

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial intelligence (AI) and machine learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classifications which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying a principal component analysis (PCA) on the numerical part of the dataset and a multiple correspondence analysis (MCA) on the categorical part of the dataset. Then, the Bayesian information criterion (BIC) was applied to Gaussian mixture models (GMM) in order to identify the optimal number of clusters under which the best grouping of patients occurs. The proposed methodology identified four clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and the patient's mortality.

A novel combined dynamic ensemble selection model for imbalanced data to detect COVID-19 from complete blood count

BACKGROUND

As blood testing is radiation-free, low-cost and simple to operate, some researchers use machine learning to detect COVID-19 from blood test data. However, few studies take into consideration the imbalanced data distribution, which can impair the performance of a classifier.

METHOD

A novel combined dynamic ensemble selection (DES) method is proposed for imbalanced data to detect COVID-19 from complete blood count. This method combines data preprocessing and improved DES. Firstly, we use the hybrid synthetic minority over-sampling technique and edited nearest neighbor (SMOTE-ENN) to balance data and remove noise. Secondly, in order to improve the performance of DES, a novel hybrid multiple clustering and bagging classifier generation (HMCBCG) method is proposed to reinforce the diversity and local regional competence of candidate classifiers.

RESULTS

The experimental results based on three popular DES methods show that the performance of HMCBCG is better than only use bagging. HMCBCG+KNE obtains the best performance for COVID-19 screening with 99.81% accuracy, 99.86% F1, 99.78% G-mean and 99.81% AUC.

CONCLUSION

Compared to other advanced methods, our combined DES model can improve accuracy, G-mean, F1 and AUC of COVID-19 screening.

A machine-learning parsimonious multivariable predictive model of mortality risk in patients with Covid-19

The COVID-19 pandemic is impressively challenging the healthcare system. Several prognostic models have been validated but few of them are implemented in daily practice. The objective of the study was to validate a machine-learning risk prediction model using easy-to-obtain parameters to help to identify patients with COVID-19 who are at higher risk of death. The training cohort included all patients admitted to Fondazione Policlinico Gemelli with COVID-19 from March 5, 2020, to November 5, 2020. Afterward, the model was tested on all patients admitted to the same hospital with COVID-19 from November 6, 2020, to February 5, 2021. The primary outcome was in-hospital case-fatality risk. The out-of-sample performance of the model was estimated from the training set in terms of Area under the Receiving Operator Curve (AUROC) and classification matrix statistics by averaging the results of fivefold cross validation repeated 3-times and comparing the results with those obtained on the test set. An explanation analysis of the model, based on the SHapley Additive exPlanations (SHAP), is also presented. To assess the subsequent time evolution, the change in paO2/FiO2 (P/F) at 48 h after the baseline measurement was plotted against its baseline value. Among the 921 patients included in the training cohort, 120 died (13%). Variables selected for the model were age, platelet count, SpO2, blood urea nitrogen (BUN), hemoglobin, C-reactive protein, neutrophil count, and sodium. The results of the fivefold cross-validation repeated 3-times gave AUROC of 0.87, and statistics of the classification matrix to the Youden index as follows: sensitivity 0.840, specificity 0.774, negative predictive value 0.971. Then, the model was tested on a new population (n = 1463) in which the case-fatality rate was 22.6%. The test model showed AUROC 0.818, sensitivity 0.813, specificity 0.650, negative predictive value 0.922. Considering the first quartile of the predicted risk score (low-risk score group), the case-fatality rate was 1.6%, 17.8% in the second and third quartile (high-risk score group) and 53.5% in the fourth quartile (very high-risk score group). The three risk score groups showed good discrimination for the P/F value at admission, and a positive correlation was found for the low-risk class to P/F at 48 h after admission (adjusted R-squared = 0.48). We developed a predictive model of death for people with SARS-CoV-2 infection by including only easy-to-obtain variables (abnormal blood count, BUN, C-reactive protein, sodium and lower SpO2). It demonstrated good accuracy and high power of discrimination. The simplicity of the model makes the risk prediction applicable for patients in the Emergency Department, or during hospitalization. Although it is reasonable to assume that the model is also applicable in not-hospitalized persons, only appropriate studies can assess the accuracy of the model also for persons at home.