COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models integrated with interpretation framework

Khadem, Heydar; Nemat, Hoda; Eissa, Mohammad R.; Elliott, Jackie; Benaïssa, Mohammed

doi:10.1016/j.compbiomed.2022.105361

Cited by 11 publications

(5 citation statements)

References 35 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[84,85] To support this evolution, researchers focused on new tools like unsupervised machine learning, the minimization of the total costs of healthcare supply chain distribution, the number of pollutants from delivery to storage, the maximization of the social responsibilities, and the categorization of the resilience factors to be used to face the disruptions in the healthcare supply chain. [26] Nevertheless, standard machine learning modelling analysis and the additive exPlanations (SHAP) technique was proposed by Khadem et al [86,87] for RA for diabetes mellitus patients, which are at elevated risk of in-hospital mortality from COVID-19. Particularly, a random forest (RF) classifier was trained on the entire training set to predict inpatient death due to COVID-19, while SHAP clustering was applied for the RA analysis to stratify the in-hospital mortality risk of patients, providing a technique potentially suitable for the online surveillance of hospitalized patients.…”

Section: Application Of Resilience Approach and Ra Tools To Healthcar...mentioning

confidence: 99%

Towards strengthening resilience of organizations by risk management tools: A scientometric perspective on COVID‐19 experience in a healthcare and industrial setting

Fabiano,

Guastaferro,

Pettinato

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

During the COVID‐19 pandemic, the healthcare system and the global supply chain were exposed to an unpredicted event, which increased awareness about the need of more effective strategies to support decision‐making process and to empower safety barriers. In this work, a combined scientometric and systematic review was performed to analyze tools and methodologies able to combine resilience with more traditional risk assessment, learning from the experience posed by the COVID‐19 crisis. Bibliometric and literature content analyses were carried out focusing on resilience management upon the incoming of an unexpected event. The systematic analysis of the methods and models developed on the basis of different pandemic waves provides a natural guide for future research development.

show abstract

Section: Application Of Resilience Approach and Ra Tools To Healthcar...mentioning

confidence: 99%

Towards strengthening resilience of organizations by risk management tools: A scientometric perspective on COVID‐19 experience in a healthcare and industrial setting

Fabiano,

Guastaferro,

Pettinato

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Mathematical models to study the co-interactions between SARS-CoV-2 infection and other diseases have attracted the attention of several researchers [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] , [30] , [31] , [32] , [33] . The authors in [22] analyzed a co-dynamical model for dengue and COVID-19, comparing model solutions using various fractional operators.…”

Section: Introductionmentioning

confidence: 99%

Modeling SARS-CoV-2 and HBV co-dynamics with optimal control

Omame

Abbas

2023

Physica A: Statistical Mechanics and its Applications

View full text Add to dashboard Cite

“…Remdesivir; Sotrovimab; Baricitinib; Evusheld ® (cilgavimab + tixagevimab); Paxlovid ® (nirmatadvir + ritonavir); and Molnupiravir ® were also administered during the COVID-19 crisis 23 , 24 . The majority of these drugs are based on a variety of cytokines, including IL-6, TNF, IFN, IL-10, IL-1, IL-6, IL-2, IL-8, IL-10, IL-12, and IL-10 27 – 39 . However, biomarker and immune response analysis are still necessary to better comprehend the pathogenicity of the disease and develop more effective treatments and vaccines.…”

Section: Introductionmentioning

confidence: 99%

“…Other comparable machine learning-based experiments were discussed in terms of the creation of predictive models that lacked interpretability despite their high performance. In fact, the issue with ML approaches in healthcare applications is their black-box nature 39 – 42 , in which the process of achieving a particular output is concealed. Incorporating interpretation frameworks could increase the acceptability of an ML technique designed to combat COVID-19 by incorporating interpretation frameworks.…”

Section: Introductionmentioning

confidence: 99%

Explanatory predictive model for COVID-19 severity risk employing machine learning, shapley addition, and LIME

Laatifi

Douzi

Ezzine

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The rapid spread of SARS-CoV-2 threatens global public health and impedes the operation of healthcare systems. Several studies have been conducted to confirm SARS-CoV-2 infection and examine its risk factors. To produce more effective treatment options and vaccines, it is still necessary to investigate biomarkers and immune responses in order to gain a deeper understanding of disease pathophysiology. This study aims to determine how cytokines influence the severity of SARS-CoV-2 infection. We measured the plasma levels of 48 cytokines in the blood of 87 participants in the COVID-19 study. Several Classifiers were trained and evaluated using Machine Learning and Deep Learning to complete missing data, generate synthetic data, and fill in any gaps. To examine the relationship between cytokine storm and COVID-19 severity in patients, the Shapley additive explanation (SHAP) and the LIME (Local Interpretable Model-agnostic Explanations) model were applied. Individuals with severe SARS-CoV-2 infection had elevated plasma levels of VEGF-A, MIP-1b, and IL-17. RANTES and TNF were associated with healthy individuals, whereas IL-27, IL-9, IL-12p40, and MCP-3 were associated with non-Severity. These findings suggest that these cytokines may promote the development of novel preventive and therapeutic pathways for disease management. In this study, the use of artificial intelligence is intended to support clinical diagnoses of patients to determine how each cytokine may be responsible for the severity of COVID-19, which could lead to the identification of several cytokines that could aid in treatment decision-making and vaccine development.

show abstract

COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models integrated with interpretation framework

Cited by 11 publications

References 35 publications

Towards strengthening resilience of organizations by risk management tools: A scientometric perspective on COVID‐19 experience in a healthcare and industrial setting

Towards strengthening resilience of organizations by risk management tools: A scientometric perspective on COVID‐19 experience in a healthcare and industrial setting

Modeling SARS-CoV-2 and HBV co-dynamics with optimal control

Explanatory predictive model for COVID-19 severity risk employing machine learning, shapley addition, and LIME

Contact Info

Product

Resources

About