Machine learning approaches in Covid-19 severity risk prediction in Morocco

Machine learning-aided algorithm design for prediction of severity from clinical, demographic, biochemical and immunological parameters: Our COVID-19 experience from the pandemic

Background

The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID-19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters-based machine learning algorithms for severity indexing in COVID-19.

Methods

Laboratory biochemical results of 5715 COVID-19 patients were mined from electronic records including 509 admitted in COVID-19 ICU. Random Forest Classifier (RFC), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and K-Nearest Neighbours (KNN) classifier models were used. Lasso regression helped in identifying the most influential parameter. A decision tree was made for subdivided data set, based on randomization.

Results

Accuracy of SVM was highest with 94.18% and RFC with 94.04%. SVM had highest PPV (1.00), and NBC had highest NPV (0.95). QUEST modelling ignored age, urea and total protein, and only C-reactive protein and lactate dehydrogenase were considered to be a part of decision-tree algorithm. The overall percentage of correct classification was 78.31% in the overall algorithm with a sensitivity of 87.95% and an AUC of 0.747.

Conclusion

C-reactive protein and lactate dehydrogenase being routinely performed tests in clinical laboratories in peripheral setups, this algorithm could be an effective predictive tool. SVM and RFC models showed significant accuracy in predicting COVID-19 severity and could be useful for future pandemics.

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.

Excess of body weight is associated with accelerated T-cell senescence in hospitalized COVID-19 patients

BACKGROUND

Several risk factors have been involved in the poor clinical progression of coronavirus disease-19 (COVID-19), including ageing, and obesity. SARS-CoV-2 may compromise lung function through cell damage and paracrine inflammation; and obesity has been associated with premature immunosenescence, microbial translocation, and dysfunctional innate immune responses leading to poor immune response against a range of viruses and bacterial infections. Here, we have comprehensively characterized the immunosenescence, microbial translocation, and immune dysregulation established in hospitalized COVID-19 patients with different degrees of body weight.

RESULTS

Hospitalised COVID-19 patients with overweight and obesity had similarly higher plasma LPS and sCD14 levels than controls (all p < 0.01). Patients with obesity had higher leptin levels than controls. Obesity and overweight patients had similarly higher expansions of classical monocytes and immature natural killer (NK) cells (CD56+CD16-) than controls. In contrast, reduced proportions of intermediate monocytes, mature NK cells (CD56+CD16+), and NKT were found in both groups of patients than controls. As expected, COVID-19 patients had a robust expansion of plasmablasts, contrasting to lower proportions of major T-cell subsets (CD4 + and CD8+) than controls. Concerning T-cell activation, overweight and obese patients had lower proportions of CD4+CD38+ cells than controls. Contrasting changes were reported in CD25+CD127low/neg regulatory T cells, with increased and decreased proportions found in CD4+ and CD8+ T cells, respectively. There were similar proportions of T cells expressing checkpoint inhibitors across all groups. We also investigated distinct stages of T-cell differentiation (early, intermediate, and late-differentiated - TEMRA). The intermediate-differentiated CD4 + T cells and TEMRA cells (CD4+ and CD8+) were expanded in patients compared to controls. Senescent T cells can also express NK receptors (NKG2A/D), and patients had a robust expansion of CD8+CD57+NKG2A+ cells than controls. Unbiased immune profiling further confirmed the expansions of senescent T cells in COVID-19.

CONCLUSIONS

These findings suggest that dysregulated immune cells, microbial translocation, and T-cell senescence may partially explain the increased vulnerability to COVID-19 in subjects with excess of body weight.

Clinical Features Predicting COVID-19 Severity Risk at the Time of Hospitalization

The global spread of COVID-19 has led to significant mortality and morbidity worldwide. Early identification of COVID-19 patients who are at high risk of developing severe disease can help in improved patient management, care, and treatment, as well as in the effective allocation of hospital resources. The severity prediction at the time of hospitalization can be extremely helpful in deciding the treatment of COVID-19 patients. To this end, this study presents an interpretable artificial intelligence (AI) model, named COVID-19 severity predictor (CoSP) that predicts COVID-19 severity using the clinical features at the time of hospital admission. We utilized a dataset comprising 64 demographic and laboratory features of 7,416 confirmed COVID-19 patients that were collected at the time of hospital admission. The proposed hierarchical CoSP model performs four-class COVID severity risk prediction into asymptomatic, mild, moderate, and severe categories. CoSP yielded better performance with good interpretability, as observed via Shapley analysis on COVID severity prediction compared to the other popular ML methods, with an area under the received operating characteristic curve (AUC-ROC) of 0.95, an area under the precision-recall curve (AUPRC) of 0.91, and a weighted F1-score of 0.83. Out of 64 initial features, 19 features were inferred as predictive of the severity of COVID-19 disease by the CoSP model. Therefore, an AI model predicting COVID-19 severity may be helpful for early intervention, optimizing resource allocation, and guiding personalized treatments, potentially enabling healthcare professionals to save lives and allocate resources effectively in the fight against the pandemic.

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.

Long- and Short-Term Memory Model of Cotton Price Index Volatility Risk Based on Explainable Artificial Intelligence

Market uncertainty greatly interferes with the decisions and plans of market participants, thus increasing the risk of decision-making, leading to compromised interests of decision-makers. Cotton price index (hereinafter referred to as cotton price) volatility is highly noisy, nonlinear, and stochastic and is susceptible to supply and demand, climate, substitutes, and other policy factors, which are subject to large uncertainties. To reduce decision risk and provide decision support for policymakers, this article integrates 13 factors affecting cotton price index volatility based on existing research and further divides them into transaction data and interaction data. A long- and short-term memory (LSTM) model is constructed, and a comparison experiment is implemented to analyze the cotton price index volatility. To make the constructed model explainable, we use explainable artificial intelligence (XAI) techniques to perform statistical analysis of the input features. The experimental results show that the LSTM model can accurately analyze the cotton price index fluctuation trend but cannot accurately predict the actual price of cotton; the transaction data plus interaction data are more sensitive than the transaction data in analyzing the cotton price fluctuation trend and can have a positive effect on the cotton price fluctuation analysis. This study can accurately reflect the fluctuation trend of the cotton market, provide reference to the state, enterprises, and cotton farmers for decision-making, and reduce the risk caused by frequent fluctuation of cotton prices. The analysis of the model using XAI techniques builds the confidence of decision-makers in the model.

Assessing risk factors for malnutrition among women in Bangladesh and forecasting malnutrition using machine learning approaches

BACKGROUND

This paper presents an in-depth examination of malnutrition in women in Bangladesh. Malnutrition in women is a major public health issue related to different diseases and has negative repercussions for children, such as premature birth, decreased infection resistance, and an increased risk of death. Moreover, malnutrition is a severe problem in Bangladesh. Data from the Bangladesh Demographic Health Survey (BDHS) conducted in 2017-18 was used to identify risk factors for malnourished women and to create a machine learning-based strategy to detect their nutritional status.

METHODS

A total of 17022 women participants are taken to conduct the research. All the participants are from different regions and different ages. A chi-square test with a five percent significance level is used to identify possible risk variables for malnutrition in women and six machine learning-based classifiers (Naïve Bayes, two types of Decision Tree, Logistic Regression, Random Forest, and Gradient Boosting Machine) were used to predict the malnutrition of women. The models are being evaluated using different parameters like accuracy, sensitivity, specificity, positive predictive value, negative predictive value, [Formula: see text] score, and area under the curve (AUC).

RESULTS

Descriptive data showed that 45% of the population studied were malnourished women, and the chi-square test illustrated that all fourteen variables are significantly associated with malnutrition in women and among them, age and wealth index had the most influence on their nutritional status, while water source had the least impact. Random Forest had an accuracy of 60% and 60.2% for training and test data sets, respectively. CART and Gradient Boosting Machine also had close accuracy like Random Forest but based on other performance metrics such as kappa and [Formula: see text] scores Random Forest got the highest rank among others. Also, it had the highest accuracy and [Formula: see text] scores in k-fold validation along with the highest AUC (0.604).

CONCLUSION

The Random Forest (RF) approach is a reasonably superior machine learning-based algorithm for forecasting women's nutritional status in Bangladesh in comparison to other ML algorithms investigated in this work. The suggested approach will aid in forecasting which women are at high susceptibility to malnutrition, hence decreasing the strain on the healthcare system.

Application of Machine Learning to Predict COVID-19 Spread via an Optimized BPSO Model

During the pandemic of the coronavirus disease (COVID-19), statistics showed that the number of affected cases differed from one country to another and also from one city to another. Therefore, in this paper, we provide an enhanced model for predicting COVID-19 samples in different regions of Saudi Arabia (high-altitude and sea-level areas). The model is developed using several stages and was successfully trained and tested using two datasets that were collected from Taif city (high-altitude area) and Jeddah city (sea-level area) in Saudi Arabia. Binary particle swarm optimization (BPSO) is used in this study for making feature selections using three different machine learning models, i.e., the random forest model, gradient boosting model, and naive Bayes model. A number of predicting evaluation metrics including accuracy, training score, testing score, F-measure, recall, precision, and receiver operating characteristic (ROC) curve were calculated to verify the performance of the three machine learning models on these datasets. The experimental results demonstrated that the gradient boosting model gives better results than the random forest and naive Bayes models with an accuracy of 94.6% using the Taif city dataset. For the dataset of Jeddah city, the results demonstrated that the random forest model outperforms the gradient boosting and naive Bayes models with an accuracy of 95.5%. The dataset of Jeddah city achieved better results than the dataset of Taif city in Saudi Arabia using the enhanced model for the term of accuracy.

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.

Multidimensional analysis of immune cells from COVID-19 patients identified cell subsets associated with the severity at hospital admission

BACKGROUND

SARS-CoV-2 emerged as a new coronavirus causing COVID-19, and it has been responsible for more than 760 million cases and 6.8 million deaths worldwide until March 2023. Although infected individuals could be asymptomatic, other patients presented heterogeneity and a wide range of symptoms. Therefore, identifying those infected individuals and being able to classify them according to their expected severity could help target health efforts more effectively.

METHODOLOGY/PRINCIPAL FINDINGS

Therefore, we wanted to develop a machine learning model to predict those who will develop severe disease at the moment of hospital admission. We recruited 75 individuals and analysed innate and adaptive immune system subsets by flow cytometry. Also, we collected clinical and biochemical information. The objective of the study was to leverage machine learning techniques to identify clinical features associated with disease severity progression. Additionally, the study sought to elucidate the specific cellular subsets involved in the disease following the onset of symptoms. Among the several machine learning models tested, we found that the Elastic Net model was the better to predict the severity score according to a modified WHO classification. This model was able to predict the severity score of 72 out of 75 individuals. Besides, all the machine learning models revealed that CD38+ Treg and CD16+ CD56neg HLA-DR+ NK cells were highly correlated with the severity.

CONCLUSIONS/SIGNIFICANCE

The Elastic Net model could stratify the uninfected individuals and the COVID-19 patients from asymptomatic to severe COVID-19 patients. On the other hand, these cellular subsets presented here could help to understand better the induction and progression of the symptoms in COVID-19 individuals.

Explanatory predictive model for COVID-19 severity risk employing machine learning, shapley addition, and LIME

The rapid spread of SARS-CoV-2 threatens global public health and impedes the operation of healthcare systems. Several studies have been conducted to confirm SARS-CoV-2 infection and examine its risk factors. To produce more effective treatment options and vaccines, it is still necessary to investigate biomarkers and immune responses in order to gain a deeper understanding of disease pathophysiology. This study aims to determine how cytokines influence the severity of SARS-CoV-2 infection. We measured the plasma levels of 48 cytokines in the blood of 87 participants in the COVID-19 study. Several Classifiers were trained and evaluated using Machine Learning and Deep Learning to complete missing data, generate synthetic data, and fill in any gaps. To examine the relationship between cytokine storm and COVID-19 severity in patients, the Shapley additive explanation (SHAP) and the LIME (Local Interpretable Model-agnostic Explanations) model were applied. Individuals with severe SARS-CoV-2 infection had elevated plasma levels of VEGF-A, MIP-1b, and IL-17. RANTES and TNF were associated with healthy individuals, whereas IL-27, IL-9, IL-12p40, and MCP-3 were associated with non-Severity. These findings suggest that these cytokines may promote the development of novel preventive and therapeutic pathways for disease management. In this study, the use of artificial intelligence is intended to support clinical diagnoses of patients to determine how each cytokine may be responsible for the severity of COVID-19, which could lead to the identification of several cytokines that could aid in treatment decision-making and vaccine development.

Generalizable machine learning approach for COVID-19 mortality risk prediction using on-admission clinical and laboratory features

We aimed to propose a mortality risk prediction model using on-admission clinical and laboratory predictors. We used a dataset of confirmed COVID-19 patients admitted to three general hospitals in Tehran. Clinical and laboratory values were gathered on admission. Six different machine learning models and two feature selection methods were used to assess the risk of in-hospital mortality. The proposed model was selected using the area under the receiver operator curve (AUC). Furthermore, a dataset from an additional hospital was used for external validation. 5320 hospitalized COVID-19 patients were enrolled in the study, with a mortality rate of 17.24% (N = 917). Among 82 features, ten laboratories and 27 clinical features were selected by LASSO. All methods showed acceptable performance (AUC > 80%), except for K-nearest neighbor. Our proposed deep neural network on features selected by LASSO showed AUC scores of 83.4% and 82.8% in internal and external validation, respectively. Furthermore, our imputer worked efficiently when two out of ten laboratory parameters were missing (AUC = 81.8%). We worked intimately with healthcare professionals to provide a tool that can solve real-world needs. Our model confirmed the potential of machine learning methods for use in clinical practice as a decision-support system.

Mortality Analysis of Patients with COVID-19 in Mexico Based on Risk Factors Applying Machine Learning Techniques

The new pandemic caused by the COVID-19 virus has generated an overload in the quality of medical care in clinical centers around the world. Causes that originate this fact include lack of medical personnel, infrastructure, medicines, among others. The rapid and exponential increase in the number of patients infected by COVID-19 has required an efficient and speedy prediction of possible infections and their consequences with the purpose of reducing the health care quality overload. Therefore, intelligent models are developed and employed to support medical personnel, allowing them to give a more effective diagnosis about the health status of patients infected by COVID-19. This paper aims to propose an alternative algorithmic analysis for predicting the health status of patients infected with COVID-19 in Mexico. Different prediction models such as KNN, logistic regression, random forests, ANN and majority vote were evaluated and compared. The models use risk factors as variables to predict the mortality of patients from COVID-19. The most successful scheme is the proposed ANN-based model, which obtained an accuracy of 90% and an F1 score of 89.64%. Data analysis reveals that pneumonia, advanced age and intubation requirement are the risk factors with the greatest influence on death caused by virus in Mexico.

Time-Dependent Changes of Laboratory Parameters as Independent Predictors of All-Cause Mortality in COVID-19 Patients

Independent predictors of mortality for COVID-19 patients have been identified upon hospital admission; however, how they behave after hospitalization remains unknown. The aim of this study is to identify clinical and laboratory parameters from admission to discharge or death that distinguish survivors and non-survivors of COVID-19, including those with independent ability to predict mortality. In a cohort of 266 adult patients, clinical and laboratory data were analyzed from admission and throughout hospital stay until discharge or death. Upon admission, non-survivors had significantly increased C reactive protein (CRP), neutrophil count, neutrophil to lymphocyte ratio (NLR) (p < 0.0001, each), ferritin (p < 0.001), and AST (aspartate transaminase) (p = 0.009) compared to survivors. During the hospital stay, deceased patients maintained elevated CRP (21.7 mg/dL [admission] vs. 19.3 [hospitalization], p = 0.060), ferritin, neutrophil count and NLR. Conversely, survivors showed significant reductions in CRP (15.8 mg/dL [admission] vs. 9.3 [hospitalization], p < 0.0001], ferritin, neutrophil count and NLR during hospital stay. Upon admission, elevated CRP, ferritin, and diabetes were independent predictors of mortality, as were persistently high CRP, neutrophilia, and the requirement of invasive mechanical ventilation during hospital stay. Inflammatory and clinical parameters distinguishing survivors from non-survivors upon admission changed significantly during hospital stay. These markers warrant close evaluation to monitor and predict patients’ outcome once hospitalized.

Predicting COVID-19 future trends for different European countries using Pearson correlation

The ability to accurately forecast the number of COVID-19 cases and future case trends would certainly assist governments and various organisations in strategising and preparing for the newly infected cases well in advance. Many predictions have failed to foresee future COVID-19 cases due to the lack of reliable data; however, such data are now widely available for predicting future trends in COVID-19 after more than one and a half years of the pandemic. Also, various countries are closely monitoring other countries that are experiencing a surge in COVID-19 cases in the expectation of similar scenarios, but this does not always produce correct results, as no research has identified specific correlations between different countries in terms of COVID-19 cases. During the past 18 months, many nations have watched countries whose COVID-19 cases have risen sharply, in anticipation of handling the situation themselves. However, this did not provide accurate results, as no research was conducted that compared countries to determine if their COVID-19 case trends were correlated. As official data on COVID-19 cases has become increasingly available, using the Pearson correlation technique to pinpoint the countries that should be closely monitored will help governments plan and prepare for the number of infections that are expected in the future at an early stage. In this study, a simple and real-time prediction of COVID-19 cases incorporating existing variables of coronavirus variants was used to explore the correlation among different European countries in terms of the number of COVID-19 cases officially recorded on a daily basis. Data from selected countries over the past 76 weeks were analysed using a Pearson correlation technique to determine if there were correlations between case trends and geographical position. The correlation coefficient (r) was employed for identifying whether the different countries in Europe were interrelated, with r > 0.85 indicating they were very strongly correlated, 0.85 > r > 0.8 indicating that they were strongly correlated, 0.8 > r > 0.7 indicating that they were moderately correlated, and r < 0.7 indicating that the examined countries were either weakly correlated or that a correlation did not exist. The results showed that although some neighbouring countries are strongly correlated, other countries that are not geographically close are also correlated. In addition, some countries on opposite sides of Europe (Belgium and Armenia) are also correlated. Other countries (France, Iceland, Israel, Kosovo, San Marino, Spain, Sweden and Turkey) were either weakly correlated or had no relationship at all.