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

Baik, Seung Min; Lee, Mi-Ae; Hong, Kyung-Sook; Park, Dong-Jin

doi:10.3390/diagnostics12061464

Cited by 10 publications

(11 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to this, the ANFISE boosted the performance of FFNN, ANFIS, SVM, and MLR by 13, 6.1, 13.9, and 19.3 per cent, respectively. These numbers show that the capacity for the prediction of COVID-19 was increased in the case of the ensemble models rather than the single models, and these findings were compared to the findings of studies conducted in different fields using AI ensemble models [ 6 , 14 , 35 , 37 ]. Hence, these findings showed that ensemble models can be applied to the prediction of COVID-19 in the eastern Africa region more effectively than the single AI-driven models.…”

Section: Resultsmentioning

confidence: 85%

“…In addition to this, the big question, then, is “when will things go back to normal, or whether we should prepare for new waves of coronavirus or not?” Though no one has a final answer to this question, through data analyses, we can understand how it happened and what the situation will look like in the future. The results of these analyses, including those using artificial intelligence (AI)-driven models, will be actionable knowledge that can help us to manage a similar crisis in the future [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Abegaz

Etikan

2022

Diagnostics

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

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

Abegaz

Etikan

2022

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Two studies had a prospective study design [45,53], whilst the remaining 22 were retrospective [30][31][32][33][34][46][47][48][49][50][51][52][54][55][56][57][58][59][60][61][62][63]. The clinical endpoints assessed included mortality (15 studies) [30][31][32][33][34][46][47][48][50][51][52][54][55][56]62] and the following measures of severe disease: clinical severity based on existing guidelines (8 studies) [33,45,49,53,[56][57][58][59], transfer to the ICU (two studies) [56,62], persistent viral positivity (one study) [6...…”

Section: Results Of Individual Studies and Synthesesmentioning

confidence: 99%

“…Of them, 4757 were either duplicates or irrelevant and, therefore, excluded. After a full review of the remaining 27 articles, three were excluded because they did not meet the inclusion criteria, leaving 24 articles for analysis (Figure 1) [30][31][32][33][34][45][46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62][63]. Two studies had a prospective study design [45,53], whilst the remaining 22 were retrospective [30][31][32][33][34][46][47][48][49][50][51][52][54][55][56][57][58][59][60][61][62][63].…”

Section: Selection Of Studiesmentioning

confidence: 99%

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

Mangoni

Zinellu

2023

Life

View full text Add to dashboard Cite

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).

show abstract

“…Finally, an ensemble model, model 4, was developed using a weighted soft-voting strategy that predicts based on the calculated probability from the individual models. 17 Models with better performance contributed more significantly. Here, the voting weights were assigned based on the area under the curve (AUC) of each model on the training data set.…”

Section: Feature Selection and Model Constructionmentioning

confidence: 99%

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

Zhang,

Zhu,

Cao

et al. 2024

Stroke

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 10 publications

References 57 publications

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

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

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

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

Contact Info

Product

Resources

About