“…To the best of our knowledge, this is the first study to develop a predictive model of mortality in patients with severe COVID-19 infection at such an early stage using routine laboratory results and demographic characteristics. as poor prognostic factors for COVID-19 patients [26][27][28] . These markers, however, are not usually used as predictors of the severity of disease in clinical practice.…”
Rationale
Given the expanding number of COVID-19 cases and the potential for upcoming waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.
Objectives
Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission.
Methods
We studied retrospectively 263 COVID-19 ICU patients. To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Logistic regression and random forest (RF) algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP).
Results
Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume, white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patients outcomes with a sensitivity of 70% and a specificity of 75%.
Conclusions
The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW along with gender and age. Complete blood count parameters were also crucial for some patients. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.
“…To the best of our knowledge, this is the first study to develop a predictive model of mortality in patients with severe COVID-19 infection at such an early stage using routine laboratory results and demographic characteristics. as poor prognostic factors for COVID-19 patients [26][27][28] . These markers, however, are not usually used as predictors of the severity of disease in clinical practice.…”
Rationale
Given the expanding number of COVID-19 cases and the potential for upcoming waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.
Objectives
Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission.
Methods
We studied retrospectively 263 COVID-19 ICU patients. To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Logistic regression and random forest (RF) algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP).
Results
Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume, white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patients outcomes with a sensitivity of 70% and a specificity of 75%.
Conclusions
The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW along with gender and age. Complete blood count parameters were also crucial for some patients. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.
“…This has been an approach espoused by Robert Hancock's group, which they address in a review article (Haney et al, 2019). Moreover, hMSC-related AMPs, which could include additional yet-to-be-discovered peptides, could be interacting in synergy with other beneficial agents secreted by hMSCs, such as exosomal agents that limit immune thrombosis, increase fibrinolytic activity, re-stabilize endothelial integrity, reduce lymphocyte trafficking, and promote recruitment of M2 macrophages and regulatory T cells (Gomzikova et al, 2019;Jamshidi et al, 2021;Moradinasab et al, 2021;Su et al, 2021).…”
Section: Mesenchymal Stem Cells and Covid-19: Plausible Role For Antimicrobial Peptidesmentioning
Human-derived antimicrobial peptides (AMPs), such as defensins and cathelicidin LL-37, are members of the innate immune system and play a crucial role in early pulmonary defense against viruses. These AMPs achieve viral inhibition through a variety of mechanisms including, but not limited to, direct binding to virions, binding to and modulating host cell-surface receptors, blocking viral replication, and aggregation of viral particles and indirectly by functioning as chemokines to enhance or curb adaptive immune responses. Given the fact that we are in a pandemic of unprecedented severity and the urgent need for therapeutic options to combat severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), naturally expressed AMPs and their derivatives have the potential to combat coronavirus disease 2019 (COVID-19) and impede viral infectivity in various ways. Provided the fact that development of effective treatments is an urgent public health priority, AMPs and their derivatives are being explored as potential prophylactic and therapeutic candidates. Additionally, cell-based platforms such as human mesenchymal stem cell (hMSC) therapy are showing success in saving the lives of severely ill patients infected with SARS-CoV-2. This could be partially due to AMPs released from hMSCs that also act as immunological rheostats to modulate the host inflammatory response. This review highlights the utilization of AMPs in strategies that could be implemented as novel therapeutics, either alone or in combination with other platforms, to treat CoV-2–infected individuals.
“…Ordinarily, it is expected that a wellcoordinated immune response restricts the spread of the virus, whereas an excessive inflammatory response causes cytokine storm. It seems that this hyperinflammatory/immunodeficiency state is developed as a result of impaired innate immune response (Jamshidi et al, 2021). Type I interferons (IFNs), a group of innate immune cytokines, are secreted from virally infected cells and act on more than 7,000 genes that regulate critical cellular processes, including metabolism, survival, migration, and inhibition of virus replication and assembly (Wang and Fish, 2019).…”
Section: Supporting Evidence For Hypothesis Interferons Impairment In Covid-19mentioning
confidence: 99%
“…In addition to the carrier role of MSCs, these cells can provide extra benefits due to their inherent characteristics, such as immunomodulatory effect by controlling cytokine release, regulating RAAS function, increasing alveolar fluid clearance, and decreasing the chance of hypercoagulation (Jamshidi et al, 2021). The roles of MSCs in eliminating COVID-19 complications are shown in Figure 2.…”
The SARS-CoV-2, the virus that causes COVID-19, has infected millions of people worldwide. The symptoms of this disease are primarily due to pulmonary involvement, uncontrolled tissue inflammation, and inadequate immune response against the invader virus. Impaired interferon (IFN) production is one of the leading causes of the immune system’s inability to control the replication of the SARS-CoV-2. Mitochondria play an essential role in developing and maintaining innate cellular immunity and IFN production. Mitochondrial function is impaired during cellular stress, affecting cell bioenergy and innate immune responses. The mitochondrial antiviral-signaling protein (MAVS), located in the outer membrane of mitochondria, is one of the key elements in engaging the innate immune system and interferon production. Transferring healthy mitochondria to the damaged cells by mesenchymal stem cells (MSCs) is a proposed option for regenerative medicine and a viable treatment approach to many diseases. In addition to mitochondrial transport, these cells can regulate inflammation, repair the damaged tissue, and control the pathogenesis of COVID-19. The immune regulatory nature of MSCs dramatically reduces the probability of an immune rejection. In order to induce an appropriate immune response against the SARS-CoV-2, we hypothesize to donate mitochondria to the host cells of the virus. We consider MSCs as an appropriate biological carrier for mitochondria. Besides, enhancing the expression of MAVS protein in MSCs and promoting the expression of SARS-CoV-2 viral spike protein as a specific ligand for ACE2+ cells will improve IFN production and innate immune responses in a targeted manner.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.