Neutrophil-lymphocyte ratios in blood to distinguish children with asthma exacerbation from healthy subjects

Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers

BACKGROUND

Asthma is a chronic respiratory disease affecting millions of people worldwide, but early detection can be challenging due to the time-consuming nature of the traditional technique. Machine learning has shown great potential in the prompt prediction of asthma. However, because of the inherent complexity of asthma-related patterns, current models often fail to capture the correlation between data samples, limiting their accuracy. Our objective was to use our novel model to address the above problem via an Affinity Graph Enhanced Classifier (AGEC) to improve predictive accuracy.

METHODS

The clinical dataset used in this study consisted of 152 samples, where 24 routine blood markers were extracted as features to participate in the classification due to their ease of sourcing and relevance to asthma. Specifically, our model begins by constructing a projection matrix to reduce the dimensionality of the feature space while preserving the most discriminative features. Simultaneously, an affinity graph is learned through the resulting subspace to capture the internal relationship between samples better. Leveraging domain knowledge from the affinity graph, a new classifier (AGEC) is introduced for asthma prediction. AGEC's performance was compared with five state-of-the-art predictive models.

RESULTS

Experimental findings reveal the superior predictive capabilities of AGEC in asthma prediction. AGEC achieved an accuracy of 72.50%, surpassing FWAdaBoost (61.02%), MLFE (60.98%), SVR (64.01%), SVM (69.80%) and ERM (68.40%). These results provide evidence that capturing the correlation between samples can enhance the accuracy of asthma prediction. Moreover, the obtained [Formula: see text] values also suggest that the differences between our model and other models are statistically significant, and the effect of our model does not exist by chance.

CONCLUSION

As observed from the experimental results, advanced statistical machine learning approaches such as AGEC can enable accurate diagnosis of asthma. This finding holds promising implications for improving asthma management.

The Neutrophil to Lymphocyte Ratio in Children with Bronchial Asthma

The discovery of an effective airway inflammation marker which correctly identifies the condition and phenotype of asthma still constitutes a significant challenge. The determination of NLR, that is, the ratio of neutrophils to lymphocytes, would overcome this challenge. The role of the neutrophil-lymphocytic index in the diagnosis of specific types of asthma is investigated in the present study. The results of laboratory tests of 482 pediatric patients were used for the analysis. The results of 107 children without allergic disease symptoms were selected for the control group. The mean NLR in patients with asthma was 3.42 ± 4.05, and in the control group it was 1.94 ± 1.91. The difference between the NLR in allergic and non-allergic asthma was statistically significant in the allergic asthma and control groups. There was no statistically significant difference between NLR and body temperature, BMI, and gender. The value of NLR was significantly higher in the blood of patients suffering from asthma compared to the control group. The NLR was the highest among patients with allergic asthma. The use of this blood test in daily practice may facilitate the diagnosis of asthma and differentiation between asthma types, especially when the results of other tests are inconclusive.

Severe Acute Bronchial Asthma with Sepsis: Determining the Status of Biomarkers in the Diagnosis of the Disease

Bronchial asthma is a widely prevalent illness that substantially impacts an individual's health standard worldwide and has a significant financial impact on society. Global guidelines for managing asthma do not recommend the routine use of antimicrobial agents because most episodes of the condition are linked to viral respiratory tract infections (RTI), and bacterial infection appears to have an insignificant impact. However, antibiotics are recommended when there is a high-grade fever, a consolidation on the chest radiograph, and purulent sputum that contains polymorphs rather than eosinophils. Managing acute bronchial asthma with sepsis, specifically the choice of whether or not to initiate antimicrobial treatment, remains difficult since there are currently no practical clinical or radiological markers that allow for a simple distinction between viral and bacterial infections. Researchers found that serum procalcitonin (PCT) values can efficiently and safely minimize antibiotic usage in individuals with severe acute asthma. Again, the clinical manifestations of acute asthma and bacterial RTI are similar, as are frequently used test values, like C-reactive protein (CRP) and white blood cell (WBC) count, making it harder for doctors to differentiate between viral and bacterial infections in asthma patients. The role and scope of each biomarker have not been precisely defined yet, although they have all been established to aid healthcare professionals in their diagnostics and treatment strategies.

Evaluating the baseline hemoglobin, albumin, lymphocyte, and platelet (HALP) score in the United States adult population and comorbidities: an analysis of the NHANES

Introduction

As a composite immunonutritional biomarker, the Hemoglobin, Albumin, Lymphocyte, Platelet (HALP) score has shown promise in assessing a patient's overall health status by integrating several routinely collected laboratory indicators. This biomarker has been examined in many different populations of patients and disease states (i.e., cancer), but an integrated, universal rubric using standardized thresholds has not thus far been developed. Pre-existing large population-based databases represent an ideal source to examine the distribution of HALP and the influence of diverse health statuses on this score.

Methods

We conducted a cross-sectional study using data from the National Health and Nutrition Examination Survey (NHANES) between 2017-2020, evaluating 8,245 participants across numerous demographic, socioeconomic, and health-related variables. Univariate and multivariate linear regression analyses assessed the associations between HALP scores and these factors.

Results

Our findings revealed significant associations between HALP scores and various demographic, socioeconomic, and health conditions. The median HALP score among the representative population was 49.0, with varying median scores across different groups and normal reference ranges for males and females. Multivariate regression analysis showed that anemia treatment, age over 65 years, weak/failing kidneys, and cancer were independent risk factors associated with lower HALP scores. Male participants demonstrated higher HALP scores than female participants, and age was inversely related to HALP. Moreover, HALP scores were negatively associated with the number of comorbidities.

Conclusion/discussion

This study set out to explore the HALP score from a population-based perspective, uncovering notable associations that offer vital insights into the score's clinical relevance and future applications. By determining a median HALP score of 49.0 and normal reference ranges within our diverse, representative sample, we establish a robust foundation for researchers to refine optimal HALP applications and thresholds. Considering the growing focus on personalized medicine, HALP holds promise as a prognostic tool, enabling clinicians to comprehend their patients' immunonutritional status better and deliver customized care.

Elevated Neutrophil-to-Lymphocyte Ratio Is Associated with Severe Asthma Exacerbation in Children

Asthma is the most common chronic respiratory disease in children. The neutrophil-to-lymphocyte ratio (NLR) is a marker of a chronic inflammatory state; however, data on the association of NLR with acute asthma exacerbations in children is lacking. In this cross-sectional study, between 2016 and 2021, children aged 2-18 years who were referred to the emergency department (ED) due to asthma exacerbation, were included. NLR, calculated from complete blood count upon arrival, was assessed as a continuous variable and was classified into four groups according to quartiles. The association between severity parameters and NLR quartiles was examined. A total of 831 ED visits for asthma exacerbation were included in the study. The median NLR was 1.6, 3.8, 6.7, and 12.9 in quartiles 1-4, respectively (p < 0.001). Demographic parameters, background diseases, and chronic medications were similar between the quartiles. Higher heart rate, body temperature, systolic blood pressure, and respiratory rate were observed in the higher NLR quartiles, as well as lower oxygen saturation. Higher urgency scale and higher rates of intravenous magnesium sulfate were observed in the higher NLR quartiles, with higher admission rates and prolonged hospitalizations. In summary, NLR upon admission is associated with the severity of asthma exacerbation and higher chances of hospitalization among children in the ED.