Development of Machine-Learning Model to Predict COVID-19 Mortality: Application of Ensemble Model and Regarding Feature Impacts

Impact of nutrition-related laboratory tests on mortality of patients who are critically ill using artificial intelligence: A focus on trace elements, vitamins, and cholesterol

BACKGROUND

This study aimed to understand the collective impact of trace elements, vitamins, cholesterol, and prealbumin on patient outcomes in the intensive care unit (ICU) using an advanced artificial intelligence (AI) model for mortality prediction.

METHODS

Data from ICU patients (December 2016 to December 2021), including serum levels of trace elements, vitamins, cholesterol, and prealbumin, were retrospectively analyzed using AI models. Models employed included category boosting (CatBoost), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and multilayer perceptron (MLP). Performance was evaluated using area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, and F1-score. The performance was evaluated using 10-fold crossvalidation. The SHapley Additive exPlanations (SHAP) method provided interpretability.

RESULTS

CatBoost emerged as the top-performing individual AI model with an AUROC of 0.756, closely followed by LGBM, MLP, and XGBoost. Furthermore, the ensemble model combining these four models achieved the highest AUROC of 0.776 and more balanced metrics, outperforming all models. SHAP analysis indicated significant influences of prealbumin, Acute Physiology and Chronic Health Evaluation II score, and age on predictions. Notably, the ratios of selenium to age and low-density lipoprotein to total cholesterol also had a notable impact on the models' output.

CONCLUSION

The study underscores the critical role of nutrition-related parameters in ICU patient outcomes. Advanced AI models, particularly in an ensemble approach, demonstrated improved predictive accuracy. SHAP analysis offered insights into specific factors influencing patient survival, highlighting the need for broader consideration of these biomarkers in critical care management.

Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage

BACKGROUND

Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage.

METHODS

This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets.

RESULTS

A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively.

CONCLUSIONS

The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.

A brief review and scientometric analysis on ensemble learning methods for handling COVID-19

Numerous efforts and research have been conducted worldwide to combat the coronavirus disease 2019 (COVID-19) pandemic. In this regard, some researchers have focused on deep and machine-learning approaches to discover more about this disease. There have been many articles on using ensemble learning methods for COVID-19 detection. Still, there seems to be no scientometric analysis or a brief review of these researches. Hence, a combined method of scientometric analysis and brief review was used to study the published articles that employed an ensemble learning approach to detect COVID-19. This research used both methods to overcome their limitations, leading to enhanced and reliable outcomes. The related articles were retrieved from the Scopus database. Then a two-step procedure was employed. A concise review of the collected articles was conducted. Then they underwent scientometric and bibliometric analyses. The findings revealed that convolutional neural network (CNN) is the mostly employed algorithm, while support vector machine (SVM), random forest, Resnet, DenseNet, and visual geometry group (VGG) were also frequently used. Additionally, China has had a significant presence in the numerous top-ranking categories of this field of research. Both study phases yielded valuable results and rankings.

Development of blood demand prediction model using artificial intelligence based on national public big data

Objective

Modern healthcare systems face challenges related to the stable and sufficient blood supply of blood due to shortages. This study aimed to predict the monthly blood transfusion requirements in medical institutions using an artificial intelligence model based on national open big data related to transfusion.

Methods

Data regarding blood types and components in Korea from January 2010 to December 2021 were obtained from the Health Insurance Review and Assessment Service and Statistics Korea. The data were collected from a single medical institution. Using the obtained information, predictive models were developed, including eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and category boosting (CatBoost). An ensemble model was created using these three models.

Results

The prediction performance of XGBoost, LGBM, and CatBoost demonstrated a mean absolute error ranging from 14.6657 for AB+ red blood cells (RBCs) to 84.0433 for A+ platelet concentrate (PC) and a root mean squared error ranging from 18.5374 for AB+ RBCs to 118.6245 for B+ PC. The error range was further improved by creating ensemble models, wherein the department requesting blood was the most influential parameter affecting transfusion prediction performance for different blood products and types. Except for the department, the features that affected the prediction performance varied for each product and blood type, including the number of RBC antibody screens, crossmatch, nationwide blood donations, and surgeries.

Conclusion

Based on blood-related open big data, the developed blood-demand prediction algorithm can efficiently provide medical facilities with an appropriate volume of blood ahead of time.

Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review

Aim

To perform a systematic review on the use of Artificial Intelligence (AI) techniques for predicting COVID-19 hospitalization and mortality using primary and secondary data sources.

Study eligibility criteria

Cohort, clinical trials, meta-analyses, and observational studies investigating COVID-19 hospitalization or mortality using artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data sources

Articles recorded in Ovid MEDLINE from 01/01/2019 to 22/08/2022 were screened.

Data extraction

We extracted information on data sources, AI models, and epidemiological aspects of retrieved studies.

Bias assessment

A bias assessment of AI models was done using PROBAST.

Participants

Patients tested positive for COVID-19.

Results

We included 39 studies related to AI-based prediction of hospitalization and death related to COVID-19. The articles were published in the period 2019-2022, and mostly used Random Forest as the model with the best performance. AI models were trained using cohorts of individuals sampled from populations of European and non-European countries, mostly with cohort sample size <5,000. Data collection generally included information on demographics, clinical records, laboratory results, and pharmacological treatments (i.e., high-dimensional datasets). In most studies, the models were internally validated with cross-validation, but the majority of studies lacked external validation and calibration. Covariates were not prioritized using ensemble approaches in most of the studies, however, models still showed moderately good performances with Area under the Receiver operating characteristic Curve (AUC) values >0.7. According to the assessment with PROBAST, all models had a high risk of bias and/or concern regarding applicability.

Conclusions

A broad range of AI techniques have been used to predict COVID-19 hospitalization and mortality. The studies reported good prediction performance of AI models, however, high risk of bias and/or concern regarding applicability were detected.

An Updated Systematic Review and Meta-Analysis of the Association between the De Ritis Ratio and Disease Severity and Mortality in Patients with COVID-19

Patients with Coronavirus disease 2019 (COVID-19) often have elevations in markers of liver injury, particularly serum aspartate transaminase (AST) and alanine transaminase (ALT). Such alterations may affect the AST/ALT ratio (De Ritis ratio) and, potentially, clinical outcomes. We conducted an updated systematic review and meta-analysis of the association between the De Ritis ratio and COVID-19 severity and mortality in hospitalized patients. PubMed, Web of Science, and Scopus were searched between 1 December 2019 and 15 February 2023. The Joanna Briggs Institute Critical Appraisal Checklist and the Grading of Recommendations, Assessment, Development, and Evaluation were used to assess the risk of bias and the certainty of the evidence, respectively. Twenty-four studies were identified. The De Ritis ratio on admission was significantly higher in patients with severe disease and non-survivors vs. patients with non-severe disease and survivors (15 studies, weighted mean difference = 0.36, 95% CI 0.24 to 0.49, p < 0.001). The De Ritis ratio was also associated with severe disease and/or mortality using odds ratios (1.83, 95% CI 1.40 to 2.39, p ˂ 0.001; nine studies). Similar results were observed using hazard ratios (2.36, 95% CI 1.17 to 4.79, p = 0.017; five studies). In six studies, the pooled area under the receiver operating characteristic curve was 0.677 (95% CI 0.612 to 0.743). In our systematic review and meta-analysis, higher De Ritis ratios were significantly associated with severe disease and mortality in COVID-19 patients. Therefore, the De Ritis ratio can be useful for early risk stratification and management in this patient group (PROSPERO registration number: CRD42023406916).

Boosting the Performance of Artificial Intelligence-Driven Models in Predicting COVID-19 Mortality in Ethiopia

Like other nations around the world, Ethiopia has suffered negative effects from COVID-19. The objective of this study was to predict COVID-19 mortality using Artificial Intelligence (AI)-driven models. Two-year daily recorded data related to COVID-19 were trained and tested to predict mortality using machine learning algorithms. Normalization of features, sensitivity analysis for feature selection, modelling of AI-driven models, and comparing the boosting model with single AI-driven models were the main activities performed in this study. Prediction of COVID-19 mortality was conducted using a combination of four dominant feature variables, and hence, the best determination of coefficient (DC) of AdaBoost, KNN, ANN-6, and SVM in the prediction process were 0.9422, 0.8618, 0.8629, and 0.7171, respectively. The Boosting model improved the performance of the individual AI-driven models KNN, SVM, and ANN-6 by 7.94, 22.51, and 8.02 percent, respectively, at the verification stage using the testing dataset. This suggests that the boosting model has the best performance for prediction of COVID-19 mortality in Ethiopia. As a result, it suggests a promising potential performance of boosting ensemble model to be applied in predicting mortality and cases from similarly recorded daily data to predict mortality due to COVID-19 in other parts of the world.

Artificial Intelligence-Driven Ensemble Model for Predicting Mortality Due to COVID-19 in East Africa

East Africa was not exempt from the devastating effects of COVID-19, which led to the nearly complete cessation of social and economic activities worldwide. The objective of this study was to predict mortality due to COVID-19 using an artificial intelligence-driven ensemble model in East Africa. The dataset, which spans two years, was divided into training and verification datasets. To predict the mortality, three steps were conducted, which included a sensitivity analysis, the modelling of four single AI-driven models, and development of four ensemble models. Four dominant input variables were selected to conduct the single models. Hence, the coefficients of determination of ANFIS, FFNN, SVM, and MLR were 0.9273, 0.8586, 0.8490, and 0.7956, respectively. The non-linear ensemble approaches performed better than the linear approaches, and the ANFIS ensemble was the best-performing ensemble approach that boosted the predicting performance of the single AI-driven models. This fact revealed the promising capability of ensemble models for predicting the daily mortality due to COVID-19 in other parts of the globe.