COVID-19: Critical appraisal of the evidence

Rodríguez, Paz González; Pérez-Moneo, Begoña; Rodríguez, María Salomé Albi; Galdeano, Pilar Aizpurua; Rodrigo, María Aparicio; Rodríguez, María Mercedes Fernández; Olcina, María Jesús Esparza; Sangrador, Carlos Ochoa

doi:10.1016/j.anpede.2021.05.003

Cited by 10 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Positive results from PCR may indicate a high risk of developing MODS and shock in patients with viral infections. 47…”

Section: Resultsmentioning

confidence: 99%

Clinical predictions of COVID-19 patients using deep stacking neural networks

Hussain,

Songhua,

Aslam

et al. 2023

Journal of Investigative Medicine

View full text Add to dashboard Cite

The COVID-19 pandemic, which emerged in late 2019, has caused millions of infections and fatalities globally, disrupting various aspects of human society, including socio-economic, political and educational systems. One of the key challenges during the COVID-19 pandemic is accurately predicting the clinical development and outcome of the infected patients. In response, scientists and medical professionals globally have mobilized to develop prognostic strategies such as risk scores, biomarkers, and machine learning models to predict the clinical course and outcome of COVID-19 patients. In this contribution, we deployed a mathematical approach called matrix factorization feature selection (MFFS) to select the most relevant features from the anonymized laboratory biomarkers and demographic data of COVID-19 patients. Based on these features, we developed a model that can assist clinical care by using the deep stacking neural network (DSNN) to predict patients mortality risk. To gauge the performance of our suggested model, we performed a comparative analysis with principal component analysis plus support vector machine, deep learning, and random forest, achieving outstanding performances. The DSNN model outperformed all the other models in terms of area under the curve (96.0%), 1-score (98.1%), recall (98.5%), accuracy (99.0%), precision (97.7%), specificity (97.0%), and maximum probability of correction decision (93.4%). Our model outperforms the clinical predictive models regarding patient mortality risk and classification in the literature. Therefore, we conclude that our robust model can help healthcare professionals to manage COVID-19 patients more effectively. We expect that early prediction of COVID-19 patients and preventive interventions can reduce the mortality risk of patients.

show abstract

“…Positive results from PCR may indicate a high risk of developing MODS and shock in patients with viral infections. 47…”

Section: Resultsmentioning

confidence: 99%

Clinical predictions of COVID-19 patients using deep stacking neural networks

Hussain,

Songhua,

Aslam

et al. 2023

Journal of Investigative Medicine

View full text Add to dashboard Cite

show abstract

“…Since this might erode the confidence of CPG readers, lead to misleading recommendations [ 28 ], and difficult the clinicians’ decision making [ 36 ], CPGs developers should use systematic and transparent methodologies (such as GRADE) not only to show the summarized estimates and its certainty, but to manage indirectness, consider other factors, and finally reach a decision.…”

Section: Discussionmentioning

confidence: 99%

Characteristics and conflicting recommendations of clinical practice guidelines for COVID-19 management in children: A scoping review

Quincho-Lopez

Chávez-Rimache

Montes-Alvis

et al. 2022

Travel Medicine and Infectious Disease

View full text Add to dashboard Cite

“…In a review carried out by the Committee of Evidence-Based Pediatrics of the Spanish Association of Pediatrics and the Spanish Association of Primary Care Pediatrics, it is established with a low level of evidence that mortality in pediatric patients admitted for COVID-19 is 413/100.000 patients and, in series that also include non-hospitalized patients, from 104 to 208/100,000 cases. Most of the deaths are due to complications of serious chronic diseases, and the direct causality of COVID-19 is unclear [ 73 ].…”

Section: What Is the Mortality Rate Of Covid-19 In The Pediatric Age ...mentioning

confidence: 99%

COVID in Pediatric Age: an opinion paper

Hernández-Sampelayo¹,

Gómez-Pavón²,

Castillo³

et al. 2022

Rev Esp Quimioter

View full text Add to dashboard Cite

The incidence of COVID in pediatrics was underestimated during the first months of the pandemic due to the oligosymptomatic nature of the infection in many children and the scarcity of diagnostic tests applied to this population. It is now accepted that children are infected and transmit the disease in the same way as adults. On the contrary, children have less severe and less lethal COVID, probably due to a lower maturity of the child’s immune system, a lower number of ACE2 receptors and the lower presence of comorbidities in this population group. The development of a multisystemic inflammatory syndrome after SARS-CoV-2 infection in children, despite its rarity, is a very serious condition that frequently requires intensive care. Other less severe post-COVID manifestations have been described in children but are not yet well defined. COVID has had and continues to have a significant psychological impact on the children themselves, on their caregivers and on the exacerbation of pre-existing psychiatric conditions. We apply adult therapeutic principles to children but with very low levels of evidence. Information on the tolerability of the available medications in this population group is still scarce. The mortality of COVID in children is very low and generally affects children with significant comorbidities. There are, at present, three vaccines licensed for pediatric use which are compatible with all other vaccines applicable to children. In these circumstances, there has been much speculation about the indication for vaccination in the pediatric age group, but given its good tolerance, there are clinical and ethical reasons that, in our opinion, justify it.

show abstract

COVID-19: Critical appraisal of the evidence

Cited by 10 publications

References 26 publications

Clinical predictions of COVID-19 patients using deep stacking neural networks

Clinical predictions of COVID-19 patients using deep stacking neural networks

Characteristics and conflicting recommendations of clinical practice guidelines for COVID-19 management in children: A scoping review

COVID in Pediatric Age: an opinion paper

Contact Info

Product

Resources

About