An interpretable mortality prediction model for COVID-19 patients

Design of an artificial neural network to predict mortality among COVID-19 patients

Introduction

The fast pandemic of coronavirus disease 2019 (COVID-19) has challenged clinicians with many uncertainties and ambiguities regarding disease outcomes and complications. To deal with these uncertainties, our study aimed to develop and evaluate several artificial neural networks (ANNs) to predict the mortality risk in hospitalized COVID-19 patients.

Material and methods

The data of 1710 hospitalized COVID-19 patients were used in this retrospective and developmental study. First, a Chi-square test (P < 0.05), Eta coefficient (η > 0.4), and binary logistics regression (BLR) analysis were performed to determine the factors affecting COVID-19 mortality. Then, using the selected variables, two types of feed-forward (FF) models, including the back-propagation (BP) and distributed time delay (DTD) were trained. The models' performance was assessed using mean squared error (MSE), error histogram (EH), and area under the ROC curve (AUC-ROC) metrics.

Results

After applying the univariate and multivariate analysis, 13 variables were selected as important features in predicting COVID-19 mortality at P < 0.05. A comparison of the two ANN architectures using the MSE showed that the BP-ANN (validation error: 0.067, most of the classified samples having 0.049 and 0.05 error rates, and AUC-ROC: 0.888) was the best model.

Conclusions

Our findings show the acceptable performance of ANN for predicting the risk of mortality in hospitalized COVID-19 patients. Application of the developed ANN-based CDSS in a real clinical environment will improve patient safety and reduce disease severity and mortality.

Gut Microbiota Disruption in COVID-19 or Post-COVID Illness Association with severity biomarkers: A Possible Role of Pre / Pro-biotics in manipulating microflora

Coronavirus disease (COVID-19), a coronavirus-induced illness attributed to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission, is thought to have first emerged on November 17, 2019. According to World Health Organization (WHO). COVID-19 has been linked to 379,223,560 documented occurrences and 5,693,245 fatalities globally as of 1st Feb 2022. Influenza A virus that has also been discovered diarrhea and gastrointestinal discomfort was found in the infected person, highlighting the need of monitoring them for gastro intestinal tract (GIT) symptoms regardless of whether the sickness is respiration related. The majority of the microbiome in the intestines is Firmicutes and Bacteroidetes, while Bacteroidetes, Proteobacteria, and Firmicutes are found in the lungs. Although most people overcome SARS-CoV-2 infections, many people continue to have symptoms months after the original sickness, called Long-COVID or Post COVID. The term "post-COVID-19 symptoms" refers to those that occur with or after COVID-19 and last for more than 12 weeks (long-COVID-19). The possible understanding of biological components such as inflammatory, immunological, metabolic activity biomarkers in peripheral blood is needed to evaluate the study. Therefore, this article aims to review the informative data that supports the idea underlying the disruption mechanisms of the microbiome of the gastrointestinal tract in the acute COVID-19 or post-COVID-mediated elevation of severity biomarkers.

Validation of Machine Learning Models to Predict Adverse Outcomes in Patients with COVID-19: A Prospective Pilot Study

PURPOSE

We previously developed learning models for predicting the need for intensive care and oxygen among patients with coronavirus disease (COVID-19). Here, we aimed to prospectively validate the accuracy of these models.

MATERIALS AND METHODS

Probabilities of the need for intensive care [intensive care unit (ICU) score] and oxygen (oxygen score) were calculated from information provided by hospitalized COVID-19 patients (n=44) via a web-based application. The performance of baseline scores to predict 30-day outcomes was assessed.

RESULTS

Among 44 patients, 5 and 15 patients needed intensive care and oxygen, respectively. The area under the curve of ICU score and oxygen score to predict 30-day outcomes were 0.774 [95% confidence interval (CI): 0.614-0.934] and 0.728 (95% CI: 0.559-0.898), respectively. The ICU scores of patients needing intensive care increased daily by 0.71 points (95% CI: 0.20-1.22) after hospitalization and by 0.85 points (95% CI: 0.36-1.35) after symptom onset, which were significantly different from those in individuals not needing intensive care (p=0.002 and <0.001, respectively). Trends in daily oxygen scores overall were not markedly different; however, when the scores were evaluated within <7 days after symptom onset, the patients needing oxygen showed a higher daily increase in oxygen scores [1.81 (95% CI: 0.48-3.14) vs. -0.28 (95% CI: 1.00-0.43), p=0.007].

CONCLUSION

Our machine learning models showed good performance for predicting the outcomes of COVID-19 patients and could thus be useful for patient triage and monitoring.

Feature Importance Analysis by Nowcasting Perspective to Predict COVID-19

The present work raises an investigation about prediction and the feature importance to estimate the COVID-19 infection, using Machine Learning approach. Our work analyzed the inclusion of climatic features, mobility, government actions and the number of cases per health sub-territory from an existing model. The Random Forest with Permutation Importance method was used to assess the importance and list the thirty most relevant that represent the probability of infection of the disease. Among all features, the most important were: i) the variables per region health stand out, ii) period comprised between the date of notification and symptom onset, iii) symptoms features as fever, cough and sore throat, iv) variables of the traffic flow and mobility, and also v) wheathers features. The model was validated and reached an accuracy average of 81.82%, whereas the sensitivity and specificity achieved 87.52% and the 78.67% respectively in the infection estimate. Therefore, the proposed investigation represents an alternative to guide authorities in understanding aspects related to the disease.

Smart pooling: AI-powered COVID-19 informative group testing

Massive molecular testing for COVID-19 has been pointed out as fundamental to moderate the spread of the pandemic. Pooling methods can enhance testing efficiency, but they are viable only at low incidences of the disease. We propose Smart Pooling, a machine learning method that uses clinical and sociodemographic data from patients to increase the efficiency of informed Dorfman testing for COVID-19 by arranging samples into all-negative pools. To do this, we ran an automated method to train numerous machine learning models on a retrospective dataset from more than 8000 patients tested for SARS-CoV-2 from April to July 2020 in Bogotá, Colombia. We estimated the efficiency gains of using the predictor to support Dorfman testing by simulating the outcome of tests. We also computed the attainable efficiency gains of non-adaptive pooling schemes mathematically. Moreover, we measured the false-negative error rates in detecting the ORF1ab and N genes of the virus in RT-qPCR dilutions. Finally, we presented the efficiency gains of using our proposed pooling scheme on proof-of-concept pooled tests. We believe Smart Pooling will be efficient for optimizing massive testing of SARS-CoV-2.

Statistical Analysis and Machine Learning Prediction of Disease Outcomes for COVID-19 and Pneumonia Patients

The Coronavirus Disease 2019 (COVID-19) has spread all over the world and impacted many people’s lives. The characteristics of COVID-19 and other types of pneumonia have both similarities and differences, which confused doctors initially to separate and understand them. Here we presented a retrospective analysis for both COVID-19 and other types of pneumonia by combining the COVID-19 clinical data, eICU and MIMIC-III databases. Machine learning models, including logistic regression, random forest, XGBoost and deep learning neural networks, were developed to predict the severity of COVID-19 infections as well as the mortality of pneumonia patients in intensive care units (ICU). Statistical analysis and feature interpretation, including the analysis of two-level attention mechanisms on both temporal and non-temporal features, were utilized to understand the associations between different clinical variables and disease outcomes. For the COVID-19 data, the XGBoost model obtained the best performance on the test set (AUROC = 1.000 and AUPRC = 0.833). On the MIMIC-III and eICU pneumonia datasets, our deep learning model (Bi-LSTM_Attn) was able to identify clinical variables associated with death of pneumonia patients (AUROC = 0.924 and AUPRC = 0.802 for 24-hour observation window and 12-hour prediction window). The results highlighted clinical indicators, such as the lymphocyte counts, that may help the doctors to predict the disease progression and outcomes for both COVID-19 and other types of pneumonia.

A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system

Starting from December 2019, the COVID-19 pandemic has globally strained medical resources and caused significant mortality. It is commonly recognized that the severity of SARS-CoV-2 disease depends on both the comorbidity and the state of the patient's immune system, which is reflected in several biomarkers. The development of early diagnosis and disease severity prediction methods can reduce the burden on the health care system and increase the effectiveness of treatment and rehabilitation of patients with severe cases. This study aims to develop and validate an ensemble machine-learning model based on clinical and immunological features for severity risk assessment and post-COVID rehabilitation duration for SARS-CoV-2 patients. The dataset consisting of 35 features and 122 instances was collected from Lviv regional rehabilitation center. The dataset contains age, gender, weight, height, BMI, CAT, 6-minute walking test, pulse, external respiration function, oxygen saturation, and 15 immunological markers used to predict the relationship between disease duration and biomarkers using the machine learning approach. The predictions are assessed through an area under the receiver-operating curve, classification accuracy, precision, recall, and F1 score performance metrics. A new hybrid ensemble feature selection model for a post-COVID prediction system is proposed as an automatic feature cut-off rank identifier. A three-layer high accuracy stacking ensemble classification model for intelligent analysis of short medical datasets is presented. Together with weak predictors, the associative rules allowed improving the classification quality. The proposed ensemble allows using a random forest model as an aggregator for weak repressors' results generalization. The performance of the three-layer stacking ensemble classification model (AUC 0.978; CA 0.920; F1 score 0.921; precision 0.924; recall 0.920) was higher than five machine learning models, viz. tree algorithm with forward pruning; Naïve Bayes classifier; support vector machine with RBF kernel; logistic regression, and a calibrated learner with sigmoid function and decision threshold optimization. Aging-related biomarkers, viz. CD3+, CD4+, CD8+, CD22+ were examined to predict post-COVID rehabilitation duration. The best accuracy was reached in the case of the support vector machine with the linear kernel (MAPE = 0.0787) and random forest classifier (RMSE = 1.822). The proposed three-layer stacking ensemble classification model predicted SARS-CoV-2 disease severity based on the cytokines and physiological biomarkers. The results point out that changes in studied biomarkers associated with the severity of the disease can be used to monitor the severity and forecast the rehabilitation duration.

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

Background and Aims

The aim of this study was to apply machine learning models and a nomogram to differentiate critically ill from non-critically ill COVID-19 pneumonia patients.

Methods

Clinical symptoms and signs, laboratory parameters, cytokine profile, and immune cellular data of 63 COVID-19 pneumonia patients were retrospectively reviewed. Outcomes were followed up until Mar 12, 2020. A logistic regression function (LR model), Random Forest, and XGBoost models were developed. The performance of these models was measured by area under receiver operating characteristic curve (AUC) analysis.

Results

Univariate analysis revealed that there was a difference between critically and non-critically ill patients with respect to levels of interleukin-6, interleukin-10, T cells, CD4+ T, and CD8+ T cells. Interleukin-10 with an AUC of 0.86 was most useful predictor of critically ill patients with COVID-19 pneumonia. Ten variables (respiratory rate, neutrophil counts, aspartate transaminase, albumin, serum procalcitonin, D-dimer and B-type natriuretic peptide, CD4+ T cells, interleukin-6 and interleukin-10) were used as candidate predictors for LR model, Random Forest (RF) and XGBoost model application. The coefficients from LR model were utilized to build a nomogram. RF and XGBoost methods suggested that Interleukin-10 and interleukin-6 were the most important variables for severity of illness prediction. The mean AUC for LR, RF, and XGBoost model were 0.91, 0.89, and 0.93 respectively (in two-fold cross-validation). Individualized prediction by XGBoost model was explained by local interpretable model-agnostic explanations (LIME) plot.

Conclusions

XGBoost exhibited the highest discriminatory performance for prediction of critically ill patients with COVID-19 pneumonia. It is inferred that the nomogram and visualized interpretation with LIME plot could be useful in the clinical setting. Additionally, interleukin-10 could serve as a useful predictor of critically ill patients with COVID-19 pneumonia.

Deep Learning-Based Automatic CT Quantification of Coronavirus Disease 2019 Pneumonia: An International Collaborative Study

OBJECTIVE

We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images.

METHODS

This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115).

RESULTS

In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035).

CONCLUSIONS

Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.

Machine learning model from a Spanish cohort for prediction of SARS-COV-2 mortality risk and critical patients

Patients affected by SARS-COV-2 have collapsed healthcare systems around the world. Consequently, different challenges arise regarding the prediction of hospital needs, optimization of resources, diagnostic triage tools and patient evolution, as well as tools that allow us to analyze which are the factors that determine the severity of patients. Currently, it is widely accepted that one of the problems since the pandemic appeared was to detect (i) who patients were about to need Intensive Care Unit (ICU) and (ii) who ones were about not overcome the disease. These critical patients collapsed Hospitals to the point that many surgeries around the world had to be cancelled. Therefore, the aim of this paper is to provide a Machine Learning (ML) model that helps us to prevent when a patient is about to be critical. Although we are in the era of data, regarding the SARS-COV-2 patients, there are currently few tools and solutions that help medical professionals to predict the evolution of patients in order to improve their treatment and the needs of critical resources at hospitals. Moreover, most of these tools have been created from small populations and/or Chinese populations, which carries a high risk of bias. In this paper, we present a model, based on ML techniques, based on 5378 Spanish patients’ data from which a quality cohort of 1201 was extracted to train the model. Our model is capable of predicting the probability of death of patients with SARS-COV-2 based on age, sex and comorbidities of the patient. It also allows what-if analysis, with the inclusion of comorbidities that the patient may develop during the SARS-COV-2 infection. For the training of the model, we have followed an agnostic approach. We explored all the active comorbidities during the SARS-COV-2 infection of the patients with the objective that the model weights the effect of each comorbidity on the patient’s evolution according to the data available. The model has been validated by using stratified cross-validation with k = 5 to prevent class imbalance. We obtained robust results, presenting a high hit rate, with 84.16% accuracy, 83.33% sensitivity, and an Area Under the Curve (AUC) of 0.871. The main advantage of our model, in addition to its high success rate, is that it can be used with medical records in order to predict their diagnosis, allowing the critical population to be identified in advance. Furthermore, it uses the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD 9-CM) standard. In this sense, we should also emphasize that those hospitals using other encodings can add an intermediate layer business to business (B2B) with the aim of making transformations to the same international format.

An approach to forecast impact of Covid-19 using supervised machine learning model

The Covid-19 pandemic has emerged as one of the most disquieting worldwide public health emergencies of the 21st century and has thrown into sharp relief, among other factors, the dire need for robust forecasting techniques for disease detection, alleviation as well as prevention. Forecasting has been one of the most powerful statistical methods employed the world over in various disciplines for detecting and analyzing trends and predicting future outcomes based on which timely and mitigating actions can be undertaken. To that end, several statistical methods and machine learning techniques have been harnessed depending upon the analysis desired and the availability of data. Historically speaking, most predictions thus arrived at have been short term and country-specific in nature. In this work, multimodel machine learning technique is called EAMA for forecasting Covid-19 related parameters in the long-term both within India and on a global scale have been proposed. This proposed EAMA hybrid model is well-suited to predictions based on past and present data. For this study, two datasets from the Ministry of Health & Family Welfare of India and Worldometers, respectively, have been exploited. Using these two datasets, long-term data predictions for both India and the world have been outlined, and observed that predicted data being very similar to real-time values. The experiment also conducted for statewise predictions of India and the countrywise predictions across the world and it has been included in the Appendix.

Research on Design of Emergency Science Popularization Information Visualization for Public Health Events-Taking “COVID-19”as an Example

This study explores the optimization method of emergency popular science information design elements in public health events, breaks through the traditional design with the designer as the subjective consciousness and proposes an emergency popular science information design method oriented by perceptual narrative. First, relevant research on public health events was carried out to screen out and analyze relevant narrative information elements and image elements, and narrative element divergence tree was established to show evaluation indicators. Second, relevant personnel were invited to evaluate the importance and kansei engineering, factor analysis and other methods were used to establish the correlation evaluation indicators of narrative elements. Finally, the optimization narrative elements of popular science information design were calculated with the fuzzy evaluation method to provide an effective auxiliary role for the visualization design of emergency popular science information. Taking “COVID-19 Event” as an example, the narrative design practice of emergency popular science elements was carried out. According to 313 effective questionnaires, the satisfaction of “COVID-19 event” popular science information elements that adopt the optimization method is relatively high, which verifies the feasibility of this method. The conclusion proves that the perceptual narrative design method can obtain the perceptual identity from the audience and plays a positive role in disseminating emergency popular science information.

Development of a Machine Learning Based Web Application for Early Diagnosis of COVID-19 Based on Symptoms

Detecting the presence of a disease requires laboratory tests, testing kits, and devices; however, these were not always available on hand. This study proposes a new approach in disease detection using machine learning algorithms by analyzing symptoms experienced by a person without requiring laboratory tests. Six supervised machine learning algorithms such as J48 decision tree, random forest, support vector machine, k-nearest neighbors, naïve Bayes algorithms, and artificial neural networks were applied in the “COVID-19 Symptoms and Presence Dataset” from Kaggle. Through hyperparameter optimization and 10-fold cross validation, we attained the highest possible performance of each algorithm. A comparative analysis was performed according to accuracy, sensitivity, specificity, and area under the ROC curve. Results show that random forest, support vector machine, k-nearest neighbors, and artificial neural networks outweighed other algorithms by attaining 98.84% accuracy, 100% sensitivity, 98.79% specificity, and 98.84% area under the ROC curve. Finally, we developed a web application that will allow users to select symptoms currently being experienced, and use it to predict the presence of COVID-19 through the developed prediction model. Based on this mechanism, the proposed method can effectively predict the presence or absence of COVID-19 in a person immediately without using laboratory tests, kits, and devices in a real-time manner.

COVID-19 Risk Stratification and Mortality Prediction in Hospitalized Indian Patients: Harnessing clinical data for public health benefits

The variability of clinical course and prognosis of COVID-19 highlights the necessity of patient sub-group risk stratification based on clinical data. In this study, clinical data from a cohort of Indian COVID-19 hospitalized patients is used to develop risk stratification and mortality prediction models. We analyzed a set of 70 clinical parameters including physiological and hematological for developing machine learning models to identify biomarkers. We also compared the Indian and Wuhan cohort, and analyzed the role of steroids. A bootstrap averaged ensemble of Bayesian networks was also learned to construct an explainable model for discovering actionable influences on mortality and days to outcome. We discovered blood parameters, diabetes, co-morbidity and SpO2 levels as important risk stratification features, whereas mortality prediction is dependent only on blood parameters. XGboost and logistic regression model yielded the best performance on risk stratification and mortality prediction, respectively (AUC score 0.83, AUC score 0.92). Blood coagulation parameters (ferritin, D-Dimer and INR), immune and inflammation parameters IL6, LDH and Neutrophil (%) are common features for both risk and mortality prediction. Compared with Wuhan patients, Indian patients with extreme blood parameters indicated higher survival rate. Analyses of medications suggest that a higher proportion of survivors and mild patients who were administered steroids had extreme neutrophil and lymphocyte percentages. The ensemble averaged Bayesian network structure revealed serum ferritin to be the most important predictor for mortality and Vitamin D to influence severity independent of days to outcome. The findings are important for effective triage during strains on healthcare infrastructure.

Ethnicity-Specific Features of COVID-19 Among Arabs, Africans, South Asians, East Asians, and Caucasians in the United Arab Emirates

Background

Dubai (United Arab Emirates; UAE) has a multi-national population which makes it exceptionally interesting study sample because of its unique demographic factors.

Objective

To stratify the risk factors for the multinational society of the UAE.

Methods

A retrospective chart review of 560 patients sequentially admitted to inpatient care with laboratory confirmed COVID-19 was conducted. We studied patients’ demographics, clinical features, laboratory results, disease severity, and outcomes. The parameters were compared across different ethnic groups using tree-based estimators to rank the ethnicity-specific disease features. We trained ML classification algorithms to build a model of ethnic specificity of COVID-19 based on clinical presentation and laboratory findings on admission.

Results

Out of 560 patients, 43.6% were South Asians, 26.4% Middle Easterns, 16.8% East Asians, 10.7% Caucasians, and 2.5% are under others. UAE nationals represented half of the Middle Eastern patients, and 13% of the entire cohort. Hypertension was the most common comorbidity in COVID-19 patients. Subjective complaint of fever and cough were the chief presenting symptoms. Two-thirds of the patients had either a mild disease or were asymptomatic. Only 20% of the entire cohort needed oxygen therapy, and 12% needed ICU admission. Forty patients (~7%) needed invasive ventilation and fifteen patients died (2.7%). We observed differences in disease severity among different ethnic groups. Caucasian or East-Asian COVID-19 patients tended to have a more severe disease despite a lower risk profile. In contrast to this, Middle Eastern COVID-19 patients had a higher risk factor profile, but they did not differ markedly in disease severity from the other ethnic groups. There was no noticeable difference between the Middle Eastern subethnicities—Arabs and Africans—in disease severity (p = 0.81). However, there were disparities in the SOFA score, D-dimer (p = 0.015), fibrinogen (p = 0.007), and background diseases (hypertension, p = 0.003; diabetes and smoking, p = 0.045) between the subethnicities.

Conclusion

We observed variations in disease severity among different ethnic groups. The high accuracy (average AUC = 0.9586) of the ethnicity classification model based on the laboratory and clinical findings suggests the presence of ethnic-specific disease features. Larger studies are needed to explore the role of ethnicity in COVID-19 disease features.

Severity and mortality prediction models to triage Indian COVID-19 patients

As the second wave in India mitigates, COVID-19 has now infected about 29 million patients countrywide, leading to more than 350 thousand people dead. As the infections surged, the strain on the medical infrastructure in the country became apparent. While the country vaccinates its population, opening up the economy may lead to an increase in infection rates. In this scenario, it is essential to effectively utilize the limited hospital resources by an informed patient triaging system based on clinical parameters. Here, we present two interpretable machine learning models predicting the clinical outcomes, severity, and mortality, of the patients based on routine non-invasive surveillance of blood parameters from one of the largest cohorts of Indian patients at the day of admission. Patient severity and mortality prediction models achieved 86.3% and 88.06% accuracy, respectively, with an AUC-ROC of 0.91 and 0.92. We have integrated both the models in a user-friendly web app calculator, https://triage-COVID-19.herokuapp.com/, to showcase the potential deployment of such efforts at scale.

Digital technologies, healthcare and Covid-19: insights from developing and emerging nations

COVID-19 pandemic created a global health crisis affecting every nation. The essential smart medical devices/accessories, quarantine facilities, surveillance systems, and related digital technologies are in huge demand. Healthcare, manufacturing industries, and educational institutions need technologies that allow working from a safe location. Digital technologies and Industry 4.0 tools have the potential to fulfil these customized requirements during and post COVID-19 crisis. The purpose of this research is to provide understanding to healthcare professionals, government policymakers, researchers, industry professionals, academics, and students/learners of the paradigm of different Digital technologies, Industry 4.0 tools, and their applications during the COVID-19 pandemic. Digital technologies, Industry 4.0 tools and their current and potential applications have been reviewed. The use of different Digital technologies and Industry 4.0 tools is identified. Digital technologies and Industry 4.0 tools (3D Printing, Artificial Intelligence, Cloud Computing, Autonomous Robot, Biosensor, Telemedicine service, Internet of Things (IoT), Virtual reality, and holography) offer opportunities for effective delivery of healthcare service(s), online education, and Work from Home (WFH) environment. The article emphasises the usefulness, most recent development, and implementation of Digital technologies, Industry 4.0 techniques, and tools in fighting the COVID-19 pandemic worldwide.

Data-Driven Prediction for COVID-19 Severity in Hospitalized Patients

Clinicians urgently need reliable and stable tools to predict the severity of COVID-19 infection for hospitalized patients to enhance the utilization of hospital resources and supplies. Published COVID-19 related guidelines are frequently being updated, which impacts its utilization as a stable go-to resource for informing clinical and operational decision-making processes. In addition, many COVID-19 patient-level severity prediction tools that were developed during the early stages of the pandemic failed to perform well in the hospital setting due to many challenges including data availability, model generalization, and clinical validation. This study describes the experience of a large tertiary hospital system network in the Middle East in developing a real-time severity prediction tool that can assist clinicians in matching patients with appropriate levels of needed care for better management of limited health care resources during COVID-19 surges. It also provides a new perspective for predicting patients’ COVID-19 severity levels at the time of hospital admission using comprehensive data collected during the first year of the pandemic in the hospital. Unlike many previous studies for a similar population in the region, this study evaluated 4 machine learning models using a large training data set of 1386 patients collected between March 2020 and April 2021. The study uses comprehensive COVID-19 patient-level clinical data from the hospital electronic medical records (EMR), vital sign monitoring devices, and Polymerase Chain Reaction (PCR) machines. The data were collected, prepared, and leveraged by a panel of clinical and data experts to develop a multi-class data-driven framework to predict severity levels for COVID-19 infections at admission time. Finally, this study provides results from a prospective validation test conducted by clinical experts in the hospital. The proposed prediction framework shows excellent performance in concurrent validation (n=462 patients, March 2020–April 2021) with highest discrimination obtained with the random forest classification model, achieving a macro- and micro-average area under receiver operating characteristics curve (AUC) of 0.83 and 0.87, respectively. The prospective validation conducted by clinical experts (n=185 patients, April–May 2021) showed a promising overall prediction performance with a recall of 78.4–90.0% and a precision of 75.0–97.8% for different severity classes.

In hospital risk factors for acute kidney injury and its burden in patients with Sars-Cov-2 infection: a longitudinal multinational study

Acute kidney injury (AKI) is associated with increased mortality in most critical settings. However, it is unclear whether its mild form (i.e. AKI stage 1) is associated with increased mortality also in non-critical settings. Here we conducted an international study in patients hospitalized with SARS-CoV-2 infection aiming 1. to estimate the incidence of AKI at each stage and its impact on mortality 2. to identify AKI risk factors at admission (susceptibility) and during hospitalization (exposures) and factors contributing to AKI-associated mortality. We included 939 patients from medical departments in Moscow (Russia) and Padua (Italy). In-hospital AKI onset was identified in 140 (14.9%) patients, mainly with stage 1 (65%). Mortality was remarkably higher in patients with AKI compared to those without AKI (55 [39.3%] vs. 34 [4.3%], respectively). Such association remained significant after adjustment for other clinical conditions at admission (relative risk [RR] 5.6; CI 3.5- 8.8) or restricting to AKI stage 1 (RR 3.2; CI 1.8-5.5) or to subjects with AKI onset preceding deterioration of clinical conditions. After hospital admission, worsening of hypoxic damage, inflammation, hyperglycemia, and coagulopathy were identified as hospital-acquired risk factors predicting AKI onset. Following AKI onset, the AKI-associated worsening of respiratory function was identified as the main contributor to AKI-induced increase in mortality risk. In conclusion, AKI is a common complication of Sars-CoV2 infection in non-intensive care settings where it markedly increases mortality risk also at stage 1. The identification of hospital-acquired risk factors and exposures might help prevention of AKI onset and of its complications.

Risk Factors Associated with In-Hospital Mortality in Iranian Patients with COVID-19: Application of Machine Learning

Introduction: Predicting the mortality risk of COVID-19 patients based on patient’s physiological conditions and demographic characteristics can help optimize resource consumption along with the provision of effective medical services for patients. In the current study, we aimed to develop several machine learning models to forecast the mortality risk in COVID-19 patients, evaluate their performance, and select the model with the highest predictive power.

Material and methods: We conducted a retrospective analysis of the records belonging to COVID-19 patients admitted to one of the main hospitals of Qazvin located in the northwest of Iran over 12 months period. We selected 29 variables for developing machine learning models incorporating demographic factors, physical symptoms, comorbidities, and laboratory test results. The outcome variable was mortality as a binary variable. Logistic regression analysis was conducted to identify risk factors of in-hospital death.

Results: In prediction of mortality, Ensemble demonstrated the maximum values of accuracy (0.8071, 95%CI: 0.7787, 0.8356), F1-score (0.8121 95%CI: 0.7900, 0.8341), and AUROC (0.8079, 95%CI: 0.7800, 0.8358). Including fourteen top-scored features identified by maximum relevance minimum redundancy algorithm into the subset of predictors of ensemble classifier such as BUN level, shortness of breath, seizure, disease history, fever, gender, body pain, WBC, diarrhea, sore throat, blood oxygen level, muscular pain, lack of taste and history of drug (medication) use are sufficient for this classifier to reach to its best predictive power for prediction of mortality risk of COVID-19 patients.

Conclusions: Study findings revealed that old age, lower oxygen saturation level, underlying medical conditions, shortness of breath, seizure, fever, sore throat, and body pain, besides serum BUN, WBC, and CRP levels, were significantly associated with increased mortality risk of COVID-19 patients. Machine learning algorithms can help healthcare systems by predicting and reduction of the mortality risk of COVID-19 patients.

Feature selection reveal peripheral blood parameter's changes between COVID-19 infections patients from Brazil and Ecuador

The investigation of conventional complete blood-count (CBC) data for classifying the SARS-CoV-2 infection status became a topic of interest, particularly as a complementary laboratory tool in developing and third-world countries that financially struggled to test their population. Although hematological parameters in COVID-19-affected individuals from Asian and USA populations are available, there are no descriptions of comparative analyses of CBC findings between COVID-19 positive and negative cases from Latin American countries. In this sense, machine learning techniques have been employed to examine CBC data and aid in screening patients suspected of SARS-CoV-2 infection. In this work, we used machine learning to compare CBC data between two highly genetically distinguished Latin American countries: Brazil and Ecuador. We notice a clear distribution pattern of positive and negative cases between the two countries. Interestingly, almost all red blood cell count parameters were divergent. For males, neutrophils and lymphocytes are distinct between Brazil and Ecuador, while eosinophils are distinguished for females. Finally, neutrophils, lymphocytes, and monocytes displayed a particular distribution for both genders. Therefore, our findings demonstrate that the same set of CBC features relevant to one population is unlikely to apply to another. This is the first study to compare CBC data from two genetically distinct Latin American countries.

Fulfilling the Promise of Artificial Intelligence in the Health Sector: Let's Get Real

OBJECTIVES

This study aimed to showcase the potential and key concerns and risks of artificial intelligence (AI) in the health sector, illustrating its application with current examples, and to provide policy guidance for the development, assessment, and adoption of AI technologies to advance policy objectives.

METHODS

Nonsystematic scan and analysis of peer-reviewed and gray literature on AI in the health sector, focusing on key insights for policy and governance.

RESULTS

The application of AI in the health sector is currently in the early stages. Most applications have not been scaled beyond the research setting. The use in real-world clinical settings is especially nascent, with more evidence in public health, biomedical research, and "back office" administration. Deploying AI in the health sector carries risks and hazards that must be managed proactively by policy makers. For AI to produce positive health and policy outcomes, 5 key areas for policy are proposed, including health data governance, operationalizing AI principles, flexible regulation, skills among health workers and patients, and strategic public investment.

CONCLUSIONS

AI is not a panacea, but a tool to address specific problems. Its successful development and adoption require data governance that ensures high-quality data are available and secure; relevant actors can access technical infrastructure and resources; regulatory frameworks promote trustworthy AI products; and health workers and patients have the information and skills to use AI products and services safely, effectively, and efficiently. All of this requires considerable investment and international collaboration.

QTc interval prolongation, inflammation, and mortality in patients with COVID-19

PURPOSE

Systemic inflammation has been associated with corrected QT (QTc) interval prolongation. The role of inflammation on QTc prolongation in COVID-19 patients was investigated.

METHODS

Patients with a laboratory-confirmed SARS-CoV-2 infection admitted to IRCCS San Raffaele Scientific Institute (Milan, Italy) between March 14, 2020, and March 30, 2020 were included. QTc-I was defined as the QTc interval by Bazett formula in the first ECG performed during the hospitalization, before any new drug treatment; QTc-II was the QTc in the ECG performed after the initiation of hydroxychloroquine drug treatment.

RESULTS

QTc-I was long in 45 patients (45%) and normal in 55 patients (55%). Patients with long QTc-I were older and more frequently males. C-Reactive protein (CRP) and white blood cell (WBC) count at hospitalization were higher in patients with long QTc-I and long QTc-II. QTc-I was significantly correlated with CRP levels at hospitalization. After a median follow-up of 83 days, 14 patients (14%) died. There were no deaths attributed to ventricular arrhythmias. Patients with long QTc-I and long QTc-II had a shorter survival, compared with normal QTc-I and QTc-II patients, respectively. In Cox multivariate analysis, independent predictors of mortality were age (HR = 1.1, CI 95% 1.04-1.18, p = 0.002) and CRP at ECG II (HR 1.1, CI 95% 1.0-1.1, p = 0.02).

CONCLUSIONS

QTc at hospitalization is a simple risk marker of mortality risk in COVID-19 patients and reflects the myocardial inflammatory status.

Machine learning based prognostic model and mobile application software platform for predicting infection susceptibility of COVID-19 using healthcare data

Introduction

Methods

Results

Conclusion

A CNN based coronavirus disease prediction system for chest X-rays

Coronavirus disease (COVID-19) proliferated globally in early 2020, causing existential dread in the whole world. Radiography is crucial in the clinical staging and diagnosis of COVID-19 and offers high potential to improve healthcare plans for tackling the pandemic. However high variations in infection characteristics and low contrast between normal and infected regions pose great challenges in preparing radiological reports. To address these challenges, this study presents CODISC-CNN (CNN based Coronavirus DIsease Prediction System for Chest X-rays) that can automatically extract the features from chest X-ray images for the disease prediction. However, to get the infected region of X-ray, edges of the images are detected by applying image preprocessing. Furthermore, to attenuate the shortage of labeled datasets data augmentation has been adapted. Extensive experiments have been performed to classify X-ray images into two classes (Normal and COVID), three classes (Normal, COVID, and Virus Bacteria), and four classes (Normal, COVID, and Virus Bacteria, and Virus Pneumonia) with the accuracy of 97%, 89%, and 84% respectively. The proposed CNN-based model outperforms many cutting-edge classification models and boosts state-of-the-art performance.

Machine learning methods to predict presence of residual cancer following hysterectomy

Surgical management for gynecologic malignancies often involves hysterectomy, often constituting the most common gynecologic surgery worldwide. Despite maximal surgical and medical care, gynecologic malignancies have a high rate of recurrence following surgery. Current machine learning models use advanced pathology data that is often inaccessible within low-resource settings and are specific to singular cancer types. There is currently a need for machine learning models to predict non-clinically evident residual disease using only clinically available health data. Here we developed and tested multiple machine learning models to assess the risk of residual disease post-hysterectomy based on clinical and operative parameters. Data from 3656 hysterectomy patients from the NSQIP dataset over 14 years were used to develop models with a training set of 2925 patients and a validation set of 731 patients. Our models revealed the top postoperative predictors of residual disease were the initial presence of gross abdominal disease on the diaphragm, disease located on the bowel mesentery, located on the bowel serosa, and disease located within the adjacent pelvis prior to resection. There were no statistically significant differences in performances of the top three models. Extreme gradient Boosting, Random Forest, and Logistic Regression models had comparable AUC ROC (0.90) and accuracy metrics (87–88%). Using these models, physicians can identify gynecologic cancer patients post-hysterectomy that may benefit from additional treatment. For patients at high risk for disease recurrence despite adequate surgical intervention, machine learning models may lay the basis for potential prospective trials with prophylactic/adjuvant therapy for non-clinically evident residual disease, particularly in under-resourced settings.

Fungi population metabolomics and molecular network study reveal novel biomarkers for early detection of aflatoxigenic Aspergillus species

Mycotoxins threaten global food safety, public health and cause huge socioeconomic losses. Early detection is an effective preventive strategy, yet efficient biomarkers for early detection of aflatoxigenic Aspergillus species are lacking. Here, we proposed to use untargeted metabolomics and machine learning to mine biomarkers of aflatoxigenic Aspergillus species. We systematically delineated metabolic differences across 568 extensive field sampling A. flavus and performed biomarker analysis. Versicolorin B, 11-hydroxy-O-methylsterigmatocystin et.al metabolites shown a high correlation (from 0.71 to 0.95) with strains aflatoxin-producing capacity. Molecular networking analysis deciphered the connection of aflatoxins and biomarkers as well as potential emerging mycotoxins. We then developed a model using the biomarkers as variables to discern aflatoxigenic Aspergillus species with 97.8% accuracy. A validation dataset and metabolome from other 16 fungal isolates confirmed the robustness and specificity of these biomarkers. We further demonstrated the solution feasibility in agricultural products by early detection of biomarkers, which predicted aflatoxin contamination risk 35-47 days in advance. A developed operable decision rule by the XGBoost algorithm help regulators to intuitively assess the risk prioritization with 87.2% accuracy. Our research provides novel insights into global food safety risk assessment which will be crucial for early prevention and control of mycotoxins.

Cell specific peripheral immune responses predict survival in critical COVID-19 patients

SARS-CoV-2 triggers a complex systemic immune response in circulating blood mononuclear cells. The relationship between immune cell activation of the peripheral compartment and survival in critical COVID-19 remains to be established. Here we use single-cell RNA sequencing and Cellular Indexing of Transcriptomes and Epitomes by sequence mapping to elucidate cell type specific transcriptional signatures that associate with and predict survival in critical COVID-19. Patients who survive infection display activation of antibody processing, early activation response, and cell cycle regulation pathways most prominent within B-, T-, and NK-cell subsets. We further leverage cell specific differential gene expression and machine learning to predict mortality using single cell transcriptomes. We identify interferon signaling and antigen presentation pathways within cDC2 cells, CD14 monocytes, and CD16 monocytes as predictors of mortality with 90% accuracy. Finally, we validate our findings in an independent transcriptomics dataset and provide a framework to elucidate mechanisms that promote survival in critically ill COVID-19 patients. Identifying prognostic indicators among critical COVID-19 patients holds tremendous value in risk stratification and clinical management.

Development and validation of a simple web-based tool for early prediction of COVID-19-associated death in kidney transplant recipients

This analysis, using data from the Brazilian kidney transplant (KT) COVID-19 study, seeks to develop a prediction score to assist in COVID-19 risk stratification in KT recipients. In this study, 1379 patients (35 sites) were enrolled, and a machine learning approach was used to fit models in a derivation cohort. A reduced Elastic Net model was selected, and the accuracy to predict the 28-day fatality after the COVID-19 diagnosis, assessed by the area under the ROC curve (AUC-ROC), was confirmed in a validation cohort. The better calibration values were used to build the applicable ImAgeS score. The 28-day fatality rate was 17% (n = 235), which was associated with increasing age, hypertension and cardiovascular disease, higher body mass index, dyspnea, and use of mycophenolate acid or azathioprine. Higher kidney graft function, longer time of symptoms until COVID-19 diagnosis, presence of anosmia or coryza, and use of mTOR inhibitor were associated with reduced risk of death. The coefficients of the best model were used to build the predictive score, which achieved an AUC-ROC of 0.767 (95% CI 0.698-0.834) in the validation cohort. In conclusion, the easily applicable predictive model could assist health care practitioners in identifying non-hospitalized kidney transplant patients that may require more intensive monitoring. Trial registration: ClinicalTrials.gov NCT04494776.

Prospective predictive performance comparison between clinical gestalt and validated COVID-19 mortality scores

Most COVID-19 mortality scores were developed at the beginning of the pandemic and clinicians now have more experience and evidence-based interventions. Therefore, we hypothesized that the predictive performance of COVID-19 mortality scores is now lower than originally reported. We aimed to prospectively evaluate the current predictive accuracy of six COVID-19 scores and compared it with the accuracy of clinical gestalt predictions. 200 patients with COVID-19 were enrolled in a tertiary hospital in Mexico City between September and December 2020. The area under the curve (AUC) of the LOW-HARM, qSOFA, MSL-COVID-19, NUTRI-CoV, and NEWS2 scores and the AUC of clinical gestalt predictions of death (as a percentage) were determined. In total, 166 patients (106 men and 60 women aged 56±9 years) with confirmed COVID-19 were included in the analysis. The AUC of all scores was significantly lower than originally reported: LOW-HARM 0.76 (95% CI 0.69 to 0.84) vs 0.96 (95% CI 0.94 to 0.98), qSOFA 0.61 (95% CI 0.53 to 0.69) vs 0.74 (95% CI 0.65 to 0.81), MSL-COVID-19 0.64 (95% CI 0.55 to 0.73) vs 0.72 (95% CI 0.69 to 0.75), NUTRI-CoV 0.60 (95% CI 0.51 to 0.69) vs 0.79 (95% CI 0.76 to 0.82), NEWS2 0.65 (95% CI 0.56 to 0.75) vs 0.84 (95% CI 0.79 to 0.90), and neutrophil to lymphocyte ratio 0.65 (95% CI 0.57 to 0.73) vs 0.74 (95% CI 0.62 to 0.85). Clinical gestalt predictions were non-inferior to mortality scores, with an AUC of 0.68 (95% CI 0.59 to 0.77). Adjusting scores with locally derived likelihood ratios did not improve their performance; however, some scores outperformed clinical gestalt predictions when clinicians' confidence of prediction was <80%. Despite its subjective nature, clinical gestalt has relevant advantages in predicting COVID-19 clinical outcomes. The need and performance of most COVID-19 mortality scores need to be evaluated regularly.

COVID 19 Pandemic, Socio-Economic Behaviour and Infection Characteristics: An Inter-Country Predictive Study Using Deep Learning

This work aims to develop a data driven multi-horizon incidence forecasting model considering the inter-country variability in static socio-economic factors. The specific objectives of this study are to predict the future country-wise COVID 19 incidences, to locate the influences of individual socio-economic factors on the predictions, to analyze the clusters of countries on the basis of influential explanatory variables and thus to search for intra-cluster and inter-cluster characteristics. To that respect this study has used the deep neural network based temporal fusion transformer for the predictions, Pearson correlation to understand the influence of socio-economic variables on incidence and hierarchical clustering for cluster-analysis. The findings conclude that the inter-country infection related predictions vary widely over spatio-temporal variability and different socio-economic variables have different influences over this inter-country variability. It is observed that greater the population size, stronger the global connectedness, larger the social cohesion, higher the population density and meaningful the gender based discrimination higher will be the future spread. On the other hand greater the development level, higher the nutritional status, greater the access to quality health services, greater the urban population and greater the material poverty lesser will be the future spread. Definite spatial pattern of influence of the explanatory variables emerged from cluster analysis. To minimize the vulnerability towards unforeseen biological calamities modern and sustainable development policies are needed; affluence may not guarantee less infection. But these policies should vary between economies due to the variation in socio-economic status of the countries worldwide.

5-Hydroxymethylcytosine Signatures in Circulating Cell-Free DNA as Early Warning Biomarkers for COVID-19 Progression and Myocardial Injury

Background: The symptoms of coronavirus disease 2019 (COVID-19) range from moderate to critical conditions, leading to death in some patients, and the early warning indicators of the COVID-19 progression and the occurrence of its serious complications such as myocardial injury are limited.

Methods: We carried out a multi-center, prospective cohort study in three hospitals in Wuhan. Genome-wide 5-hydroxymethylcytosine (5hmC) profiles in plasma cell-free DNA (cfDNA) was used to identify risk factors for COVID-19 pneumonia and develop a machine learning model using samples from 53 healthy volunteers, 66 patients with moderate COVID-19, 99 patients with severe COVID-19, and 38 patients with critical COVID-19.

Results: Our warning model demonstrated that an area under the curve (AUC) for 5hmC warning moderate patients developed into severe status was 0.81 (95% CI 0.77–0.85) and for severe patients developed into critical status was 0.92 (95% CI 0.89–0.96). We further built a warning model on patients with and without myocardial injury with the AUC of 0.89 (95% CI 0.84–0.95).

Conclusion: This is the first study showing the utility of 5hmC as an accurate early warning marker for disease progression and myocardial injury in patients with COVID-19. Our results show that phosphodiesterase 4D and ten-eleven translocation 2 may be important markers in the progression of COVID-19 disease.

Prognostic Value of Serum/Plasma Neurofilament Light Chain for COVID-19 Associated Mortality.. [PMID: 35075461 PMCID: PMC8786234 DOI: 10.1101/2022.01.13.22269244]

Given the continued spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), early predictors of coronavirus disease 19 (COVID-19) mortality might improve patients’ outcomes. Increased levels of circulating neurofilament light chain (NfL), a biomarker of neuro-axonal injury, have been observed in patients with severe COVID-19. We investigated whether NfL provides non-redundant clinical value to previously identified predictors of COVID-19 mortality.

We measured serum or plasma NfL concentrations in a blinded fashion in 3 cohorts totaling 338 COVID-19 patients. In cohort 1, we found significantly elevated NfL levels only in critically ill COVID-19 patients compared to healthy controls. Longitudinal cohort 2 data showed that NfL is elevated late in the course of the disease, following two other prognostic markers of COVID-19: decrease in absolute lymphocyte count (ALC) and increase in lactate dehydrogenase (LDH). Significant correlations between LDH and ALC abnormalities and subsequent rise of NfL implicate multi-organ failure as a likely cause of neuronal injury at the later stages of COVID-19. Addition of NfL to age and gender in cohort 1 significantly improved the accuracy of mortality prediction and these improvements were validated in cohorts 2 and 3.

In conclusion, although substantial increase in serum/plasma NfL reproducibly enhances COVID-19 mortality prediction, NfL has clinically meaningful prognostic value only close to death, which may be too late to alter medical management. When combined with other prognostic biomarkers, rising longitudinal NfL measurements triggered by LDH and ALC abnormalities would identify patients at risk of COVID-19 associated mortality who might still benefit from escalated care.

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies. Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission. Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP). Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset. Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

A new COVID-19 intubation prediction strategy using an intelligent feature selection and K-NN method

Background

Predicting severe respiratory failure due to COVID-19 can help triage patients to higher levels of care, resource allocation and decrease morbidity and mortality. The need for this research derives from the increasing demand for innovative technologies to overcome complex data analysis and decision-making tasks in critical care units. Hence the aim of our paper is to present a new algorithm for selecting the best features from the dataset and developing Machine Learning(ML) based models to predict the intubation risk of hospitalized COVID-19 patients.

Methods

In this retrospective single-center study, the data of 1225 COVID-19 patients from February 9, 2020, to July 20, 2021, were analyzed by several ML algorithms which included, Decision Tree(DT), Support Vector Machine (SVM), Multilayer perceptron (MLP), and K-Nearest Neighbors(K-NN). First, the most important predictors were identified using the Horse herd Optimization Algorithm (HOA). Then, by comparing the ML algorithms' performance using some evaluation criteria, the best performing one was identified.

Results

Predictive models were trained using 12 validated features. Also, it found that proposed DT-based predictive model enables a reasonable level of accuracy (=93%) in predicting the risk of intubation among hospitalized COVID-19 patients.

Conclusions

The experimental results demonstrate the effectiveness of the proposed meta-heuristic feature selection technique in combining with DT model in predicting intubation risk for hospitalized patients with COVID-19. The proposed model have the potential to inform frontline clinicians with quantitative and non-invasive tool to assess illness severity and to identify high risk patients.

Comparing machine learning algorithms for predicting COVID-19 mortality

BACKGROUND

The coronavirus disease (COVID-19) hospitalized patients are always at risk of death. Machine learning (ML) algorithms can be used as a potential solution for predicting mortality in COVID-19 hospitalized patients. So, our study aimed to compare several ML algorithms to predict the COVID-19 mortality using the patient's data at the first time of admission and choose the best performing algorithm as a predictive tool for decision-making.

METHODS

In this study, after feature selection, based on the confirmed predictors, information about 1500 eligible patients (1386 survivors and 144 deaths) obtained from the registry of Ayatollah Taleghani Hospital, Abadan city, Iran, was extracted. Afterwards, several ML algorithms were trained to predict COVID-19 mortality. Finally, to assess the models' performance, the metrics derived from the confusion matrix were calculated.

RESULTS

The study participants were 1500 patients; the number of men was found to be higher than that of women (836 vs. 664) and the median age was 57.25 years old (interquartile 18-100). After performing the feature selection, out of 38 features, dyspnea, ICU admission, and oxygen therapy were found as the top three predictors. Smoking, alanine aminotransferase, and platelet count were found to be the three lowest predictors of COVID-19 mortality. Experimental results demonstrated that random forest (RF) had better performance than other ML algorithms with accuracy, sensitivity, precision, specificity, and receiver operating characteristic (ROC) of 95.03%, 90.70%, 94.23%, 95.10%, and 99.02%, respectively.

CONCLUSION

It was found that ML enables a reasonable level of accuracy in predicting the COVID-19 mortality. Therefore, ML-based predictive models, particularly the RF algorithm, potentially facilitate identifying the patients who are at high risk of mortality and inform proper interventions by the clinicians.

Accuracy comparison of ARIMA and XGBoost forecasting models in predicting the incidence of COVID-19 in Bangladesh

Accurate predictive time series modelling is important in public health planning and response during the emergence of a novel pandemic. Therefore, the aims of the study are three-fold: (a) to model the overall trend of COVID-19 confirmed cases and deaths in Bangladesh; (b) to generate a short-term forecast of 8 weeks of COVID-19 cases and deaths; (c) to compare the predictive accuracy of the Autoregressive Integrated Moving Average (ARIMA) and eXtreme Gradient Boosting (XGBoost) for precise modelling of non-linear features and seasonal trends of the time series. The data were collected from the onset of the epidemic in Bangladesh from the Directorate General of Health Service (DGHS) and Institute of Epidemiology, Disease Control and Research (IEDCR). The daily confirmed cases and deaths of COVID-19 of 633 days in Bangladesh were divided into several training and test sets. The ARIMA and XGBoost models were established using those training data, and the test sets were used to evaluate each model's ability to forecast and finally averaged all the predictive performances to choose the best model. The predictive accuracy of the models was assessed using the mean absolute error (MAE), mean percentage error (MPE), root mean square error (RMSE) and mean absolute percentage error (MAPE). The findings reveal the existence of a nonlinear trend and weekly seasonality in the dataset. The average error measures of the ARIMA model for both COVID-19 confirmed cases and deaths were lower than XGBoost model. Hence, in our study, the ARIMA model performed better than the XGBoost model in predicting COVID-19 confirmed cases and deaths in Bangladesh. The suggested prediction model might play a critical role in estimating the spread of a novel pandemic in Bangladesh and similar countries.

Comparative Study of Government Response Measures and Epidemic Trends for COVID-19 Global Pandemic

The ongoing novel coronavirus (COVID-19) epidemic has evolved into a full range of challenges that the world is facing. Health and economic threats caused governments to take preventive measures against the spread of the disease. This study aims to provide a correlation analysis of the response measures adopted by countries and epidemic trends since the COVID-19 outbreak. This analysis picks 13 countries for quantitative assessment. We select a trusted model to fit the epidemic trend curves in segments and catch the characteristics based on which we explore the key factors of COVID-19 spread. This review generates a score table of government response measures according to the Likert scale. We use the Delphi method to obtain expert judgments about the government response in the Likert scale. Furthermore, we find a significant negative correlation between the epidemic trend characteristics and the government response measure scores given by experts through correlation analysis. More stringent government response measures correlate with fewer infections and fewer waves in the infection curves. Stringent government response measures curb the spread of COVID-19, limit the number of total infectious cases, and reduce the time to peak of total cases. The clusters of the results categorize the countries into two specific groups. This study will improve our understanding of the prevention of COVID-19 spread and government response.

Machine Learning Models for Predicting Short-Long Length of Stay of COVID-19 Patients

During 2020 and 2021, managing limited healthcare resources and hospital beds has been a fundamental aspect of the fight against the COVID-19 pandemic. Predicting in advance the length of stay, and in particular identifying whether a patient is going to stay in the hospital longer or less than a week, can provide important support in handling resources allocation. However, there have been significant changes in terms of containment measures, virus diffusion, new treatments, vaccines, and new variants of SARS-CoV-2 during the last period. These changes pose several conceptual drift issues that can limit the usefulness of machine learning in this context. In this work, we present a machine learning system trained and tested using data from more than 6000 hospitalised patients in northern Italy, distributed over almost two years of pandemic. We show how machine learning can be effective even by analysing data over this long period of time, also exploiting a model that predicts the patient's outcome in terms of discharge or death. Furthermore, learning from data that also consider deceased patients is a common issue in predicting the length of stay because they have severe conditions similar to patients with a long stay period, but may actually have a very short duration of hospitalisation. For this purpose, we present a method for handling data from alive and deceased patients, exploiting more patient records, increasing the robustness of the model and its performance in this task. Finally, we investigate the features that are most relevant to the prediction of the simplified length of stay.

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

The purpose of this study is to develop and test machine learning-based models for COVID-19 severity prediction. COVID-19 test samples from 337 COVID-19 positive patients at Cheikh Zaid Hospital were grouped according to the severity of their illness. Ours is the first study to estimate illness severity by combining biological and non-biological data from patients with COVID-19. Moreover the use of ML for therapeutic purposes in Morocco is currently restricted, and ours is the first study to investigate the severity of COVID-19. When data analysis approaches were used to uncover patterns and essential characteristics in the data, C-reactive protein, platelets, and D-dimers were determined to be the most associated to COVID-19 severity prediction. In this research, many data reduction algorithms were used, and Machine Learning models were trained to predict the severity of sickness using patient data. A new feature engineering method based on topological data analysis called Uniform Manifold Approximation and Projection (UMAP) shown that it achieves better results. It has 100% accuracy, specificity, sensitivity, and ROC curve in conducting a prognostic prediction using different machine learning classifiers such as X_GBoost, AdaBoost, Random Forest, and ExtraTrees. The proposed approach aims to assist hospitals and medical facilities in determining who should be seen first and who has a higher priority for admission to the hospital.

Longitudinal prediction of hospital-acquired acute kidney injury in COVID-19: a two-center study

BACKGROUND

To investigate the temporal characteristics of clinical variables of hospital-acquired acute kidney injury (AKI) in COVID-19 patients and to longitudinally predict AKI onset.

METHODS

There were 308 hospital-acquired AKI and 721 non-AKI (NAKI) COVID-19 patients from Stony Brook Hospital (New York, USA) data, and 72 hospital-acquired AKI and 303 NAKI COVID-19 patients from Tongji Hospital (Wuhan, China). Demographic, comorbidities, and longitudinal (3 days before and 3 days after AKI onset) clinical variables were used to compute odds ratios for and longitudinally predict hospital-acquired AKI onset.

RESULTS

COVID-19 patients with AKI were more likely to die than NAKI patients (31.5% vs 6.9%, adjusted p < 0.001, OR = 4.67 [95% CI 3.1, 7.0], Stony Brook data). AKI developed on average 3.3 days after hospitalization. Procalcitonin was elevated prior to AKI onset (p < 0.05), peaked, and remained elevated (p < 0.05). Alanine aminotransferase, aspartate transaminase, ferritin, and lactate dehydrogenase peaked the same time as creatinine, whereas D-dimer and brain natriuretic peptide peaked a day later. C-reactive protein, white blood cell and lymphocyte showed group differences - 2 days prior (p < 0.05). Top predictors were creatinine, procalcitonin, white blood cells, lactate dehydrogenase, and lymphocytes. They predicted AKI onset with areas under curves (AUCs) of 0.78, 0.66, and 0.56 at 0, - 1, and - 2 days prior, respectively. When tested on the Tongji Hospital data, the AUCs were 0.80, 0.79, and 0.77, respectively.

CONCLUSIONS

Time-locked longitudinal data provide insight into AKI progression. Commonly clinical variables reasonably predict AKI onset a few days prior. This work may lead to earlier recognition of AKI and treatment to improve clinical outcomes.

Role of artificial intelligence in fast-track drug discovery and vaccine development for COVID-19

COVID-19 is a global pandemic spread across more than 200 countries and several measures are being taken to control it. Researchers in pharmaceutical academia/industry are incessantly targeting this disease through vaccine and drug development protocols. Artificial intelligence is being extensively explored for surveillance, diagnostics, contact tracing, and for clinical management of COVID-19. The most common application has been for repurposing of existing drugs through various AI tools. Successful training of artificial neural networks based on identification of specific patterns in binding of known antiviral drugs with protein sequences from diverse virus species have generated models giving good predictions for molecules against SARS-CoV-2 virus, in sync with clinical studies. ML tools have also been used to investigate immunogenic components of the virus to be exploited as vaccine candidates. In this chapter, the utilization of artificial intelligence to accelerate drug-design and vaccine design research for COVID-19 has been reviewed.

Developing and validating a chronic obstructive pulmonary disease quick screening questionnaire using statistical learning models

BACKGROUND

Active targeted case-finding is a cost-effective way to identify individuals with high-risk for early diagnosis and interventions of chronic obstructive pulmonary disease (COPD). A precise and practical COPD screening instrument is needed in health care settings.

METHODS

We created four statistical learning models to predict the risk of COPD using a multi-center randomized cross-sectional survey database (n = 5281). The minimal set of predictors and the best statistical learning model in identifying individuals with airway obstruction were selected to construct a new case-finding questionnaire. We validated its performance in a prospective cohort (n = 958) and compared it with three previously reported case-finding instruments.

RESULTS

A set of seven predictors was selected from 643 variables, including age, morning productive cough, wheeze, years of smoking cessation, gender, job, and pack-year of smoking. In four statistical learning models, generalized additive model model had the highest area under curve (AUC) value both on the developing cross-sectional data set (AUC = 0.813) and the prospective validation data set (AUC = 0.880). Our questionnaire outperforms the other three tools on the cross-sectional validation data set.

CONCLUSIONS

We developed a COPD case-finding questionnaire, which is an efficient and cost-effective tool for identifying high-risk population of COPD.

Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes

The clinical outcome of SARS-CoV-2 infection varies widely between individuals. Machine learning models can support decision making in healthcare by assessing fatality risk in patients that do not yet show severe signs of COVID-19. Most predictive models rely on static demographic features and clinical values obtained upon hospitalization. However, time-dependent biomarkers associated with COVID-19 severity, such as antibody titers, can substantially contribute to the development of more accurate outcome models. Here we show that models trained on immune biomarkers, longitudinally monitored throughout hospitalization, predicted mortality and were more accurate than models based on demographic and clinical data upon hospital admission. Our best-performing predictive models were based on the temporal analysis of anti-SARS-CoV-2 Spike IgG titers, white blood cell (WBC), neutrophil and lymphocyte counts. These biomarkers, together with C-reactive protein and blood urea nitrogen levels, were found to correlate with severity of disease and mortality in a time-dependent manner. Shapley additive explanations of our model revealed the higher predictive value of day post-symptom onset (PSO) as hospitalization progresses and showed how immune biomarkers contribute to predict mortality. In sum, we demonstrate that the kinetics of immune biomarkers can inform clinical models to serve as a powerful monitoring tool for predicting fatality risk in hospitalized COVID-19 patients, underscoring the importance of contextualizing clinical parameters according to their time post-symptom onset.

A Knowledge Distillation Ensemble Framework for Predicting Short- and Long-Term Hospitalization Outcomes From Electronic Health Records Data

The ability to perform accurate prognosis is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission and readmission from time-series of vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked ensemble platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction by incorporating static features. The model is used to assess a patient's risk of adversity and provides visual justifications of its prediction. Results of three case studies show that the model outperforms existing platforms in ICU and general ward settings, achieving average Precision-Recall Areas Under the Curve (PR-AUCs) of 0.891 (95% CI: 0.878-0.939) for mortality and 0.908 (95% CI: 0.870-0.935) in predicting ICU admission and readmission.