Risk factors analysis of COVID-19 patients with ARDS and prediction based on machine learning

Xu, Wan; Sun, Nannan; Gao, Hainv; Chen, Zhiyuan; Yang, Yongrong; Ju, Bin; Tang, Lingling

doi:10.1038/s41598-021-82492-x

Cited by 81 publications

(65 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when patients were re-evaluated for development of ARDS one week after admission, we found that the incidence ARDS was significantly higher among obese-diabetic COVID-19 patients than in non-obese non-diabetic group. Our results were in accordance with the results of Xu et al 2021 32 who analyzed the risk factors for development of ARDS in COVID-19 patients. The authors found that 52.3% of ARDS patients had a BMI >25, while 31.7% of non-ARDS patients had a BMI >25 (p 0.007).…”

Section: Discussionsupporting

confidence: 93%

See 1 more Smart Citation

Impact of High Serum Levels of MMP-7, MMP-9, TGF-β and PDGF Macrophage Activation Markers on Severity of COVID-19 in Obese-Diabetic Patients

El-din¹,

Ata²,

Abdel-Gawad³

et al. 2021

IDR

View full text Add to dashboard Cite

Objective The aim of this study was to identify an association between the severity of COVID-19 in obese-diabetic patients and altered serum levels of MMP-7, MMP-9, TGF-β, and PDGF macrophage activation markers. Methodology The study included 70 COVID-19 patients, divided into two groups: Group 1 included: Obese COVID-19 patients with type 2 diabetes mellitus (T2D, n=22 patients) and group 2 included; non-obese, non-diabetic COVID-19 patients as an age- and sex-matched control group (n=48 patients). Serum levels of the tested biomarkers were measured by ELISA at admission and after one weak follow-up. Results There was a significant reduction in the serum levels of LBP in obese-diabetic COVID-19 patients versus the control group (8.34±3.94 vs 20.78±7.61) (p 0.0001). Significant elevation of MMP-7, MMP-9, PDGF and TGF-β was detected in obese diabetic COVID-19 patients compared to the non-obese non-diabetic group: 1044.7±519.6 vs 405.6±164.1, 483.05±46.5 vs 173.31±76.26, 154.5±62.78 vs 39.77±21.52, and 603.05±258.82 vs 180.29±97.17, respectively. The serum levels of macrophage activation markers in obese-diabetic patients one week after admission revealed that patients with acute respiratory distress syndrome (ARDS) had significantly higher serum levels of MMP-7 and MMP-9 than non-ARDS patients (p 0.02 and p 0.01 respectively). Conclusion Macrophages were mainly polarized towards the M2 phenotype in obese-diabetic COVID-19 patients with significant upregulation of the pro-fibrotic markers MMP-7, MMP-9, PDGF, and TGF-β. Thus, high levels of MMP-7 and MMP-9 are associated with ARDS in severe COVID-19 disease among obese-diabetic patients.

show abstract

Section: Discussionsupporting

confidence: 93%

“… Plain chest X-ray was of low sensitivity and revealed bilateral consolidations accompanied by peripheral ground glass opacities in the lower lobes. 32 …”

Section: Methodsmentioning

confidence: 99%

Impact of High Serum Levels of MMP-7, MMP-9, TGF-β and PDGF Macrophage Activation Markers on Severity of COVID-19 in Obese-Diabetic Patients

El-din¹,

Ata²,

Abdel-Gawad³

et al. 2021

IDR

View full text Add to dashboard Cite

show abstract

“…Different ML models have been proposed to predict risk of developing severe complications and mortality (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26)(27). This is important since there are limited resources compared to the increasing number of COVID-19 patients.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Karthikeyan

Garg

Vinod

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19), caused by the virus SARS-CoV-2, is an acute respiratory disease that has been classified as a pandemic by the World Health Organization (WHO). The sudden spike in the number of infections and high mortality rates have put immense pressure on the public healthcare systems. Hence, it is crucial to identify the key factors for mortality prediction to optimize patient treatment strategy. Different routine blood test results are widely available compared to other forms of data like X-rays, CT-scans, and ultrasounds for mortality prediction. This study proposes machine learning (ML) methods based on blood tests data to predict COVID-19 mortality risk. A powerful combination of five features: neutrophils, lymphocytes, lactate dehydrogenase (LDH), high-sensitivity C-reactive protein (hs-CRP), and age helps to predict mortality with 96% accuracy. Various ML models (neural networks, logistic regression, XGBoost, random forests, SVM, and decision trees) have been trained and performance compared to determine the model that achieves consistently high accuracy across the days that span the disease. The best performing method using XGBoost feature importance and neural network classification, predicts with an accuracy of 90% as early as 16 days before the outcome. Robust testing with three cases based on days to outcome confirms the strong predictive performance and practicality of the proposed model. A detailed analysis and identification of trends was performed using these key biomarkers to provide useful insights for intuitive application. This study provide solutions that would help accelerate the decision-making process in healthcare systems for focused medical treatments in an accurate, early, and reliable manner.

show abstract

“…The evidence of excessive inflammatory activity in severe COVID-19, captured during the early phases of the pandemic, prompted the investigation of the clinical role of specific biomarkers of inflammatory and immunomodulating pathways, particularly C-reactive protein (CRP), white blood cell count (WBC), neutrophils, lymphocytes, platelets, procalcitonin, ferritin, and serum amyloid A [ [3] , [4] , [5] , [6] ]. Additional research has shown that patients with COVID-19 can also experience structural and functional abnormalities of specific organs and systems, e.g., cardiovascular, hematological, gastrointestinal, and neurological, in addition to the well-known respiratory compromise, characterized by the development of interstitial pneumonia and acute respiratory distress syndrome (ARDS) [ [7] , [8] , [9] ]. In particular, COVID-19 patients might present with subclinical or overt evidence of myocardial necrosis, which might manifest as acute coronary syndrome, myocarditis, arrhythmias, or heart failure [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Serum CK-MB, COVID-19 severity and mortality: An updated systematic review and meta-analysis with meta-regression

Zinellu

Sotgia

Fois

et al. 2021

Advances in Medical Sciences

View full text Add to dashboard Cite

Objectives We conducted a systematic review and meta-analysis with meta-regression of creatine kinase-MB (CK-MB), a biomarker of myocardial injury, in COVID-19 patients. Methods We searched PubMed, Web of Science and Scopus, for studies published between January 2020 and January 2021 that reported CK-MB, COVID-19 severity and mortality (PROSPERO registration number: CRD42021239657). Results Fifty-five studies in 11,791 COVID-19 patients were included in the meta-analysis. The pooled results showed that CK-MB concentrations were significantly higher in patients with high disease severity or non-survivor status than patients with low severity or survivor status (standardized mean difference, SMD, 0.81, 95% CI 0.61 to 1.01, p<0.001). The rate of patients with CK-MB values above the normal range was also significantly higher in the former than the latter (60/350 vs 98/1,780; RR=2.84, 95%CI 1.89 to 4.27, p<0.001; I 2 =19.9, p=0.254). Extreme between-study heterogeneity was observed (I 2 =93.4%, p<0.001). Sensitivity analysis, performed by sequentially removing each study and re-assessing the pooled estimates, showed that the magnitude and direction of the effect size was not modified (effect size range, 0.77 to 0.84). Begg's (p=0.50) and Egger's (p=0.86) t-tests did not show publication bias. In meta-regression analysis, the SMD was significantly and positively associated with the white blood count, aspartate aminotransferase, myoglobin, troponin, brain natriuretic peptide, lactate dehydrogenase, and D-dimer. Conclusions Higher CK-MB concentrations were significantly associated with severe disease and mortality in COVID-19 patients. This biomarker of myocardial injury might be useful for risk stratification in this group.

show abstract

Risk factors analysis of COVID-19 patients with ARDS and prediction based on machine learning

Cited by 81 publications

References 47 publications

Impact of High Serum Levels of MMP-7, MMP-9, TGF-β and PDGF Macrophage Activation Markers on Severity of COVID-19 in Obese-Diabetic Patients

Impact of High Serum Levels of MMP-7, MMP-9, TGF-β and PDGF Macrophage Activation Markers on Severity of COVID-19 in Obese-Diabetic Patients

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Serum CK-MB, COVID-19 severity and mortality: An updated systematic review and meta-analysis with meta-regression

Contact Info

Product

Resources

About