Dataset Information

Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China.

ABSTRACT:

Background

Persistence of long-term COVID-19 pandemic is putting high pressure on healthcare services worldwide for several years. This article aims to establish models to predict infection levels and mortality of COVID-19 patients in China.

Methods

Machine learning models and deep learning models have been built based on the clinical features of COVID-19 patients. The best models are selected by area under the receiver operating characteristic curve (AUC) scores to construct two homogeneous ensemble models for predicting infection levels and mortality, respectively. The first-hand clinical data of 760 patients are collected from Zhongnan Hospital of Wuhan University between 3 January and 8 March 2020. We preprocess data with cleaning, imputation, and normalization.

Results

Our models obtain AUC = 0.7059 and Recall (Weighted avg) = 0.7248 in predicting infection level, while AUC=0.8436 and Recall (Weighted avg) = 0.8486 in predicting mortality ratio. This study also identifies two sets of essential clinical features. One is C-reactive protein (CRP) or high sensitivity C-reactive protein (hs-CRP) and the other is chest tightness, age, and pleural effusion.

Conclusions

Two homogeneous ensemble models are proposed to predict infection levels and mortality of COVID-19 patients in China. New findings of clinical features for benefiting the machine learning models are reported. The evaluation of an actual dataset collected from January 3 to March 8, 2020 demonstrates the effectiveness of the models by comparing them with state-of-the-art models in prediction.

SUBMITTER: Wang J

PROVIDER: S-EPMC9630904 | biostudies-literature | 2022 Jan-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China.

Wang Jiafeng J Zhou Xianlong X Hou Zhitian Z Xu Xiaoya X Zhao Yueyue Y Chen Shanshan S Zhang Jun J Shao Lina L Yan Rong R Wang Mingshan M Ge Minghua M Hao Tianyong T Tu Yuexing Y Huang Haijun H

Digital health 20220101

<h4>Background</h4>Persistence of long-term COVID-19 pandemic is putting high pressure on healthcare services worldwide for several years. This article aims to establish models to predict infection levels and mortality of COVID-19 patients in China.<h4>Methods</h4>Machine learning models and deep learning models have been built based on the clinical features of COVID-19 patients. The best models are selected by area under the receiver operating characteristic curve (AUC) scores to construct two ...[more]

PMID: 36339905

Similar Datasets

Project description:BackgroundPerinatal mortality in Ethiopia is the highest in Africa, with 68 per 1000 pregnancies intrapartum deaths. It is mainly associated with home delivery, which contributes to more than 75% of perinatal deaths. Financial constraints significantly impact timely access to maternal health care. Financial incentives, such as health insurance, may address the demand- and supply-side factors. This study, hence, aims to predict perinatal mortality based on maternal health status and health insurance service using homogeneous ensemble machine learning methods.MethodsThe data was collected from the Ethiopian demographic health survey from 2011 to 2019 G.C. The data were pre-processed to get quality data that are suitable for the homogenous ensemble machine-learning algorithms to develop a model that predicts perinatal mortality. We have applied filter (chi-square and mutual information) and wrapper (sequential forward and sequential backward) feature selection methods. After selecting all the relevant features, we developed a predictive model using cat boost, random forest, and gradient boosting algorithms and evaluated the model using both objective (accuracy, precision, recall, F1_score, ROC) and subjective (domain expert) based evaluation techniques.ResultsPerinatal mortality prediction models were developed using random forest, gradient boosting, and cat boost algorithms with the overall accuracy of 89.95%, 90.24%, and 82%, respectively. Risk factors of perinatal mortality were identified using feature importance analysis and relevant rules were extracted using the best performing model.ConclusionsA prediction model that was developed using gradient boosting algorithms was selected for further use in the risk factor analysis, generating relevant rules, development of artifacts, and model deployment because it has registered better performance with 90.24% accuracy. The most determinant risk factors of perinatal mortality were identified using feature importance and some of them are community-based health insurance, mother's educational level, region and place of residence, age, wealth status, birth interval, preterm, smoking cigarette, anemia level, hemoglobin level, and marital status.

Project description:BackgroundMorbidity and mortality rates associated with heart failure remain high. A wide variety of demographic and clinical factors as well as biomarkers are associated with increased mortality rates. Despite this, most multivariate predictive models for heart failure mortality have predictive accuracies characterized by a C-statistic (area under the receiver operating curve) of ≈0.74.Methods and resultsWe analyzed data on 963 patients enrolled in the Vesnarinone Evaluation of Survival Trial (VEST), including circulating levels of 2 cytokines (tumor necrosis factor and interleukin-6) and their receptors sampled at baseline and at 8, 16, and 24 weeks. We built multivariate logistic regression models by using standard clinical variables and time-series of cytokine and cytokine receptor levels, using independent components analysis to handle collinearity among cytokine measurements, and L2-penalized stepwise regression for variable selection. We also built ensemble models with these data, using gentle boosting. Our multivariate logistic regression model using time-series cytokine measurements predicts 1-year mortality rates significantly better (P=0.001) than the baseline model, with a C-statistic of 0.81±0.03. Without the cytokines, the baseline model has a C-statistic of 0.73±0.03, and, with only baseline cytokine and cytokine receptor levels added, the model has a C-statistic of 0.74±0.04. An ensemble model of 100 decision stumps with serial cytokine measurements has a significantly better (P=0.04) C-statistic of 0.84±0.02. An ensemble model with baseline cytokine data and without the serial measurements has a C-statistic of 0.74±0.04.ConclusionsSignificant gains in accuracy of one year mortality prediction in chronic heart failure can be obtained by using logistic regression models that incorporate serial measurements of biomarkers such as cytokine and cytokine receptor levels. Ensemble models capture inherent variability in large patient populations, and boost predictive accuracy through the use of time-series measurements.

Project description:We present a restricted infection rate inverse binomial-based approach to better predict COVID-19 cases after a family gathering. The traditional inverse binomial (IB) model is inappropriate to match the reality of COVID-19, because the collected data contradicts the model's requirement that variance should be larger than the expected value. Our version of an IB model is more appropriate, as it can accommodate all potential data scenarios in which the variance is smaller, equal, or larger than the mean. This is unlike the usual IB, which accommodates only the scenario in which the variance is more than the mean. Therefore, we propose a refined version of an IB model to be able to accommodate all potential data scenarios. The application of the approach is based on a restricted infectivity rate and methodology on COVID-19 data, which exhibit two clusters of infectivity. Cluster 1 has a smaller number of primary cases and exhibits larger variance than the expected cases with a negative correlation of 28%, implying that the number of secondary cases is lesser when the number of primary cases increases and vice versa. The traditional IB model is appropriate for Cluster 1. The probability of contracting COVID-19 is estimated to be 0.13 among the primary, but is 0.75 among the secondary in Cluster 1, with a wider gap. Cluster 2, with a larger number of primary cases, exhibits smaller variance than the expected cases with a correlation of 79%, implying that the number of primary and secondary cases do increase or decrease together. Cluster 2 disqualifies the traditional IB model and requires its refined version. The probability of contracting COVID-19 is estimated to be 0.74 among the primary, but is 0.72 among the secondary in Cluster 2, with a narrower gap. The advantages of the proposed approach include the model's ability to estimate the community's health system memory, as future policies might reduce COVID's spread. In our approach, the current hazard level to be infected with COVID-19 and the odds of not contracting COVID-19 among the primary in comparison to the secondary groups are estimable and interpretable.

Dataset Information

Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China.

Background

Methods

Results

Conclusions

Publications

Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets