The role of a noninvasive index 'Spo2/ Fio2' in predicting mortality among patients with COVID-19 pneumonia

Approaching Personalized Medicine: The Use of Machine Learning to Determine Predictors of Mortality in a Population with SARS-CoV-2 Infection

The COVID-19 pandemic demonstrated the need to develop strategies to control a new viral infection. However, the different characteristics of the health system and population of each country and hospital would require the implementation of self-systems adapted to their characteristics. The objective of this work was to determine predictors that should identify the most severe patients with COVID-19 infection. Given the poor situation of the hospitals in the first wave, the analysis of the data from that period with an accurate and fast technique can be an important contribution. In this regard, machine learning is able to objectively analyze data in hourly sets and is used in many fields. This study included 291 patients admitted to a hospital in Spain during the first three months of the pandemic. After screening seventy-one features with machine learning methods, the variables with the greatest influence on predicting mortality in this population were lymphocyte count, urea, FiO2, potassium, and serum pH. The XGB method achieved the highest accuracy, with a precision of >95%. Our study shows that the machine learning-based system can identify patterns and, thus, create a tool to help hospitals classify patients according to their severity of illness in order to optimize admission.

Comparison of Prognostic Scores for Patients with COVID-19 Presenting with Dyspnea in the Emergency Department

BACKGROUND

Easy-to-use bedside risk assessment is crucial for patients with COVID-19 in the overcrowded emergency department (ED).

OBJECTIVE

The aim of this study was to explore the prognostic ability of ratio of percutaneous oxygen saturation (SpO2) to fraction of inspired oxygen (FiO2) (S/F); ratio of SpO2/FiO2 to respiratory rate (ROX); National Early Warning Score (NEWS); quick Sequential Organ Failure Assessment (qSOFA); and confusion, respiratory rate, blood pressure, and age ≥ 65 years (CRB-65) in patients with COVID-19 presenting with dyspnea to the ED.

METHODS

In this retrospective observational study, clinical and demographic details of patients with COVID-19 were obtained at ED admission. S/F, ROX, NEWS, CRB-65, and qSOFA scores were calculated at the time of ED arrival. Accuracy of these five indices to predict the need for invasive mechanical ventilation (IMV) within 48 h, intensive care unit (ICU) admission, and early (7-day) mortality were determined using receiver operating characteristic curves.

RESULTS

A total of 375 patients were included in this study. Fifty patients (13.3%) required IMV within 48 h and 58 patients (15.5%) were transferred to the ICU. Seven-day mortality was 6.7% and 28-day mortality was 18.1%. Among all five scores determined from patient data on ED admission, ROX, S/F, and NEWS presented greater discriminatory performance than CRB-65 and qSOFA in predicting IMV within 48 h, ICU admission, and early mortality.

CONCLUSIONS

Emergency physicians can effectively use S/F, ROX, and NEWS scores for rapid risk stratification of patients with COVID-19 infection. Moreover, from the perspective of simplicity and ease of calculation, we recommend the use of the S/F ratio.

A pipeline to further enhance quality, integrity and reusability of the NCCID clinical data

The National COVID-19 Chest Imaging Database (NCCID) is a centralized UK database of thoracic imaging and corresponding clinical data. It is made available by the National Health Service Artificial Intelligence (NHS AI) Lab to support the development of machine learning tools focused on Coronavirus Disease 2019 (COVID-19). A bespoke cleaning pipeline for NCCID, developed by the NHSx, was introduced in 2021. We present an extension to the original cleaning pipeline for the clinical data of the database. It has been adjusted to correct additional systematic inconsistencies in the raw data such as patient sex, oxygen levels and date values. The most important changes will be discussed in this paper, whilst the code and further explanations are made publicly available on GitLab. The suggested cleaning will allow global users to work with more consistent data for the development of machine learning tools without being an expert. In addition, it highlights some of the challenges when working with clinical multi-center data and includes recommendations for similar future initiatives.

NOS3 (rs61722009) gene variants testing in prediction of COVID-19 pneumonia severity

BACKGROUND

There is a hypothesis that a sufficient level of endothelial nitric oxide synthase is important for reliable protection against COVID-19. Theoretical ideas about the NOS3 gene demonstrated that it can have an effect on links of the complications pathogenesis in COVID-associated pneumonia. We determined the goal - to investigate the association of the NOS3 gene variants with the occurence of the disease and its clinical course in patients of the intensive care unit.

METHODS

The study group included 117 patients with a diagnosis of severe "viral COVID-19 pneumonia". Determination of NOS3 gene variants was performed using the PCR method. The probability of differences in the quantitative results were determined using ANOVA or Kruskal-Wallis test (depend of normality of studied parameters).

RESULTS

Our results indicate that the presence of the NOS3 gene 4a allele increase the risk of complicated COVID-19-associated pneumonia (χ² = 18.84, p = 0.00001, OR = 3.53 (1.95-6.39)). It was showed, that carriers of the 4aa genotype had a significantly higher ratio of SpO₂/FiO₂ on the first and second days after hospitalization (p = 0.017 and p = 0.03, respectively). Patients with the 4aa genotype also had the acid-base imbalances, as showed by indicators of base deficiency and standard bicarbonate, which were beyond the reference values. Potassium and sodium concentrations on the first and second day after hospitalization were also significantly lower in patients with 4aa genotype (p = 0.009 and p = 0.048, respectively), for whom, in the same time, the concentrations of C-reactive protein and total bilirubin were significantly higher (p = 0.002 and p = 0.033, respectively).

CONCLUSIONS

Our results confirmed that the rs61722009 variant of the NOS3 gene is associated with an increased risk of severe СOVID-19-associated pneumonia and its adverse clinical course with potential progression of kidney and liver damage, and occurrence risk of systemic inflammatory response syndrome. These results require further research for the new metabolic strategy formation, in order to prevent the severe COVID-19 associated pneumonia and its complications.

Efficacy of blood urea nitrogen-to-albumin ratio for predicting prognostic outcomes of inpatients with COVID-19: A meta-analysis

BACKGROUND

The associations between blood urea nitrogen (BUN)/albumin ratio and poor prognosis in patients with diagnosis of coronavirus disease 2019 (COVID-19) remain to be clarified.

METHODS

A search based on 4 electronic databases (i.e., EMBASE, Google scholar, MEDLINE, and Cochrane Library) was performed on June 23, 2022. The association of BUN/Albumin ratio with poor prognostic outcomes, defined as patients with mortality/severe illnesses, were analyzed.

RESULTS

Results from analysis of 7 cohort studies (3600 individuals with COVID-19) published between 2020 and 2022 showed a higher BUN/Albumin ratio in the poor-prognosis group (Mean difference:  = 2.838, 95% confidence interval: 2.015-3.66, P < .001, I2 = 92.5%) than the good-prognosis group. Additional investigation into the connection between BUN/Albumin ratio as a binary variable (i.e., high or low) and the risk of poor outcome also supported an association between a higher BUN/Albumin ratio and a poor prognostic risk (odd ratio = 3.009, 95% confidence interval: 1.565-5.783, P = .001, I2 = 93.7%, 5 studies). Merged analysis of poor prognosis produced a sensitivity of 0.76, specificity of 0.72, and area under curve of 0.81.

CONCLUSION

This meta-analysis demonstrated a positive correlation between BUN/albumin ratio and poor outcome in patients with COVID-19. Additional large-scale prospective studies are needed to verify our findings.

Comorbid Asthma Increased the Risk for COVID-19 Mortality in Asia: A Meta-Analysis

We aimed to explore the influence of comorbid asthma on the risk for mortality among patients with coronavirus disease 2019 (COVID-19) in Asia by using a meta-analysis. Electronic databases were systematically searched for eligible studies. The pooled odds ratio (OR) with 95% confidence interval (CI) was estimated by using a random-effect model. An inconsistency index (I2) was utilized to assess the statistical heterogeneity. A total of 103 eligible studies with 198,078 COVID-19 patients were enrolled in the meta-analysis; our results demonstrated that comorbid asthma was significantly related to an increased risk for COVID-19 mortality in Asia (pooled OR = 1.42, 95% CI: 1.20−1.68; I2 = 70%, p < 0.01). Subgroup analyses by the proportion of males, setting, and sample sizes generated consistent findings. Meta-regression indicated that male proportion might be the possible sources of heterogeneity. A sensitivity analysis exhibited the reliability and stability of the overall results. Both Begg’s analysis (p = 0.835) and Egger’s analysis (p = 0.847) revealed that publication bias might not exist. In conclusion, COVID-19 patients with comorbid asthma might bear a higher risk for mortality in Asia, at least among non-elderly individuals.

Association of Prognostic Nutritional Index with Severity and Mortality of Hospitalized Patients with COVID-19: A Systematic Review and Meta-Analysis

The associations of prognostic nutritional index (PNI) with disease severity and mortality in patients with coronavirus disease 2019 (COVID-19) remain unclear. Electronic databases, including MEDLINE, EMBASE, Google scholar, and Cochrane Library, were searched from inception to 10 May 2022. The associations of PNI with risk of mortality (primary outcome) and disease severity (secondary outcome) were investigated. Merged results from meta-analysis of 13 retrospective studies (4204 patients) published between 2020 and 2022 revealed a lower PNI among patients in the mortality group [mean difference (MD): −8.65, p < 0.001] or severity group (MD: −5.19, p < 0.001) compared to those in the non-mortality or non-severity groups. A per-point increase in PNI was associated with a reduced risk of mortality [odds ratio (OR) = 0.84, 95% CI: 0.79 to 0.9, p < 0.001, I2 = 67.3%, seven studies] and disease severity (OR = 0.84, 95% CI: 0.77 to 0.92, p < 0.001, I2 = 83%, five studies). The pooled diagnostic analysis of mortality yielded a sensitivity of 0.76, specificity of 0.71, and area under curve (AUC) of 0.79. Regarding the prediction of disease severity, the sensitivity, specificity, and AUC were 0.8, 0.61, and 0.65, respectively. In conclusion, this study demonstrated a negative association between PNI and prognosis of COVID-19. Further large-scale trials are warranted to support our findings.