Pneumonia Severity in Children: Utility of Procalcitonin in Risk Stratification

Development and validation of an early diagnosis model for severe mycoplasma pneumonia in children based on interpretable machine learning

BACKGROUND

Pneumonia is a major threat to the health of children, especially those under the age of five. Mycoplasma  pneumoniae infection is a core cause of pediatric pneumonia, and the incidence of severe mycoplasma pneumoniae pneumonia (SMPP) has increased in recent years. Therefore, there is an urgent need to establish an early warning model for SMPP to improve the prognosis of pediatric pneumonia.

METHODS

The study comprised 597 SMPP patients aged between 1 month and 18 years. Clinical data were selected through Lasso regression analysis, followed by the application of eight machine learning algorithms to develop early warning model. The accuracy of the model was assessed using validation and prospective cohort. To facilitate clinical assessment, the study simplified the indicators and constructed visualized simplified model. The clinical applicability of the model was evaluated by DCA and CIC curve.

RESULTS

After variable selection, eight machine learning models were developed using age, sex and 21 serum indicators identified as predictive factors for SMPP. A Light Gradient Boosting Machine (LightGBM) model demonstrated strong performance, achieving AUC of 0.92 for prospective validation. The SHAP analysis was utilized to screen advantageous variables, which contains of serum S100A8/A9, tracheal computed tomography (CT), retinol-binding protein(RBP), platelet larger cell ratio(P-LCR) and CD4+CD25+Treg cell counts, for constructing a simplified model (SCRPT) to improve clinical applicability. The SCRPT diagnostic model exhibited favorable diagnostic efficacy (AUC > 0.8). Additionally, the study found that S100A8/A9 outperformed clinical inflammatory markers can also differentiate the severity of MPP.

CONCLUSIONS

The SCRPT model consisting of five dominant variables (S100A8/A9, CT, RBP, PLCR and Treg cell) screened based on eight machine learning is expected to be a tool for early diagnosis of SMPP. S100A8/A9 can also be used as a biomarker for validity differentiation of SMPP when medical conditions are limited.

A Review on Risk Factors, Traditional Diagnostic Techniques, and Biomarkers for Pneumonia Prognostication and Management in Diabetic Patients

People of all ages can contract pneumonia, and it can cause mild to severe disease and even death. In addition to being a major cause of death for elderly people and those with prior medical conditions such as diabetes, it isthe world's biggest infectious cause of death for children. Diabetes mellitus is a metabolic condition with a high glucose level and is a leading cause of lower limb amputation, heart attacks, strokes, blindness, and renal failure. Hyperglycemia is known to impair neutrophil activity, damage antioxidant status, and weaken the humoral immune system. Therefore, diabetic patients are more susceptible to pneumonia than people without diabetes and linked fatalities. The absence of quick, precise, simple, and affordable ways to identify the etiologic agents of community-acquired pneumonia has made diagnostic studies' usefulness contentious. Improvements in biological markers and molecular testing techniques have significantly increased the ability to diagnose pneumonia and other related respiratory infections. Identifying the risk factors for developing severe pneumonia and early testing in diabetic patients might lead to a significant decrease in the mortality of diabetic patients with pneumonia. In this regard, various risk factors, traditional testing techniques, and pathomechanisms are discussed in this review. Further, biomarkers and next-generation sequencing are briefly summarized. Finding biomarkers with the ability to distinguish between bacterial and viral pneumonia could be crucial because identifying the precise pathogen would stop the unnecessary use of antibiotics and effectively save the patient's life.

Utility of C-reactive protein and procalcitonin in community-acquired pneumonia in children: a narrative review

The purpose of this narrative review is to analyze the most recent studies about the role of C-reactive protein (CRP) and procalcitonin (PCT), two of the main biomarkers of infection, in distinguishing viral from bacterial etiology, in predicting the severity of infection and in guiding antibiotic stewardship in children with community-acquired pneumonia (CAP). The studies examined reveal that both CRP and PCT play a valuable role in diagnosing pediatric CAP, though each has limitations. CRP has moderate accuracy in distinguishing bacterial from viral infections, but its elevated levels are not exclusive to bacterial infections; PCT, however, shows higher specificity for bacterial CAP, with studies confirming its ability to differentiate bacterial causes, especially in severe cases. When integrated with clinical findings, CRP and PCT improve the sensitivity of pneumonia diagnoses and help in predicting severe outcomes such as sepsis and empyema; furthermore, both biomarkers prove useful in guiding antibiotic therapy, with PCT showing a more dynamic response to treatment. However, even though CRP and PCT offer valuable insights into the diagnosis and management of pediatric CAP, their application should be always integrated with clinical assessment rather than used in isolation. More studies are needed to define standardized thresholds and decision algorithms that incorporate these biomarkers.

The Association of the MeMed BV Test With Radiographic Pneumonia in Children

BACKGROUND

The MeMed BV Test produces a score that increases with increasing likelihood of bacterial infection. We evaluated its association with radiographic pneumonia in children.

METHODS

We performed a secondary analysis of a multicenter prospective study of febrile children 90 days to 18 years presenting to an emergency department. We evaluated the association of the MeMed BV test with radiographic pneumonia in adjusted logistic regression models.

RESULTS

Of 182 children, 74 (41%) had radiographic pneumonia. Among children with a high likelihood of having viral illness per the BV test, 26% had radiographic pneumonia; this increased to 64% among those with a BV test which indicated a high likelihood of bacterial infection. The sensitivity and specificity for radiographic pneumonia when using a BV test classification of moderate or high likelihood of bacterial infection were 60.8% and 62.0%, respectively. A BV test indicating the highest likelihood of bacterial infection had 23.61 higher adjusted odds (95% confidence interval 6.30-88.6) of radiographic pneumonia. The most common radiographic finding among children classified as having a high likelihood of viral infection by the BV test was interstitial opacities. The most common finding among children classified as having a high likelihood of bacterial infection were infiltrates. Except for antibiotic use, clinical outcomes occurred in similar proportions by BV category.

CONCLUSIONS

Children with moderate to high likelihoods of bacterial infection on the BV test had higher odds of radiographic pneumonia. Apart from antibiotic use, the test was not significantly associated with clinical outcomes in this study.

miR-486-5p predicted adverse outcomes of SCAP and regulated K. pneumonia infection via FOXO1

PURPOSE

Severe community-acquired pneumonia (SCAP) is a common respiratory system disease with rapid development and high mortality. Exploring effective biomarkers for early detection and development prediction of SCAP is of urgent need. The function of miR-486-5p in SCAP diagnosis and prognosis was evaluated to identify a promising biomarker for SCAP.

PATIENTS AND METHODS

The serum miR-486-5p in 83 patients with SCAP, 52 healthy individuals, and 68 patients with mild CAP (MCAP) patients were analyzed by PCR. ROC analysis estimated miR-486-5p in screening SCAP, and the Kaplan-Meier and Cox regression analyses evaluated the predictive value of miR-486-5p. The risk factors for MCAP patients developing SCAP were assessed by logistic analysis. The alveolar epithelial cell was treated with Klebsiella pneumonia to mimic the occurrence of SCAP. The targeting mechanism underlying miR-486-5p was evaluated by luciferase reporter assay.

RESULTS

Upregulated serum miR-486-5p screened SCAP from healthy individuals and MCAP patients with high sensitivity and specificity. Increasing serum miR-486-5p predicted the poor outcomes of SCAP and served as a risk factor for MCAP developing into SCAP. K. pneumonia induced suppressed proliferation, significant inflammation and oxidative stress in alveolar epithelial cells, and silencing miR-486-5p attenuated it. miR-486-5p negatively regulated FOXO1, and the knockdown of FOXO1 reversed the effect of miR-486-5p in K. pneumonia-treated alveolar epithelial cells.

CONCLUSION

miR-486-5p acted as a biomarker for the screening and monitoring of SCAP and predicting the malignancy of MCAP. Silencing miR-486-5p alleviated inflammation and oxidative stress induced by K. pneumonia via negatively modulating FOXO1.

Diagnostic and Prognostic Roles of Procalcitonin and Other Tools in Community-Acquired Pneumonia: A Narrative Review

Community-acquired pneumonia (CAP) is among the most common causes of death and one of the leading healthcare concerns worldwide. It can evolve into sepsis and septic shock, which have a high mortality rate, especially in critical patients and comorbidities. The definitions of sepsis were revised in the last decade as "life-threatening organ dysfunction caused by a dysregulated host response to infection". Procalcitonin (PCT), C-reactive protein (CRP), and complete blood count, including white blood cells, are among the most commonly analyzed sepsis-specific biomarkers also used in pneumonia in a broad range of studies. It appears to be a reliable diagnostic tool to expedite care of these patients with severe infections in the acute setting. PCT was found to be superior to most other acute phase reactants and indicators, including CRP as a predictor of pneumonia, bacteremia, sepsis, and poor outcome, although conflicting results exist. In addition, PCT use is beneficial to judge timing for the cessation of antibiotic treatment in most severe infectious states. The clinicians should be aware of strengths and weaknesses of known and potential biomarkers in expedient recognition and management of severe infections. This manuscript is intended to present an overview of the definitions, complications, and outcomes of CAP and sepsis in adults, with special regard to PCT and other important markers.

Incorporation of biomarkers into a prediction model for paediatric radiographic pneumonia

Objective

The aim of this study was to evaluate biomarkers to predict radiographic pneumonia among children with suspected lower respiratory tract infections (LRTI).

Methods

We performed a single-centre prospective cohort study of children 3 months to 18 years evaluated in the emergency department with signs and symptoms of LRTI. We evaluated the incorporation of four biomarkers (white blood cell count, absolute neutrophil count, C-reactive protein (CRP) and procalcitonin), in isolation and in combination, with a previously developed clinical model (which included focal decreased breath sounds, age and fever duration) for an outcome of radiographic pneumonia using multivariable logistic regression. We evaluated the improvement in performance of each model with the concordance (c-) index.

Results

Of 580 included children, 213 (36.7%) had radiographic pneumonia. In multivariable analysis, all biomarkers were statistically associated with radiographic pneumonia, with CRP having the greatest adjusted odds ratio of 1.79 (95% CI 1.47-2.18). As an isolated predictor, CRP at a cut-off of 3.72 mg·dL^-1 demonstrated a sensitivity of 60% and a specificity of 75%. The model incorporating CRP demonstrated improved sensitivity (70.0% versus 57.7%) and similar specificity (85.3% versus 88.3%) compared to the clinical model when using a statistically derived cutpoint. In addition, the multivariable CRP model demonstrated the greatest improvement in concordance index (0.780 to 0.812) compared with a model including only clinical variables.

Conclusion

A model consisting of three clinical variables and CRP demonstrated improved performance for the identification of paediatric radiographic pneumonia compared with a model with clinical variables alone.

Serum level of S100A8/A9 as a biomarker for establishing the diagnosis and severity of community-acquired pneumonia in children

Background

S100A8/A9, which is a member of S100 proteins, may be involved in the pathophysiology of Community-acquired pneumonia (CAP) that seriously threatens children's health. However, circulating markers to assess the severity of pneumonia in children are yet to be explored. Therefore, we aimed to investigate the diagnostic performance of serum S100A8/A9 level in determining the severity of CAP in children.

Methods

In this prospective and observational study, we recruited 195 in-hospital children diagnosed with CAP. In comparison, 63 healthy children (HC) and 58 children with non-infectious pneumonia (pneumonitis) were included as control groups. Demographic and clinical data were collected. Serum S100A8/A9 levels, serum pro-calcitonin concentrations, and blood leucocyte counts were quantified.

Results

The serum S100A8/A9 levels in patients with CAP was 1.59 ± 1.32 ng/mL, which was approximately five and two times higher than those in healthy controls and those in children with pneumonitis, respectively. Serum S100A8/A9 was elevated parallelly with the clinical pulmonary infection score. The sensitivity, specificity, and Youden's index of S100A8/A9 ≥1.25 ng/mL for predicting the severity of CAP in children was optimal. The area under the receiver operating characteristic curve of S100A8/A9 was the highest among the indices used to evaluate severity.

Conclusions

S100A8/A9 may serve as a biomarker for predicting the severity of the condition in children with CAP and establishing treatment grading.

Is Serum Endocan Level an Indicator of the Severity of Childhood Community-Acquired Pneumonia?

Objective We aimed to investigate the relationship between serum endocan, procalcitonin (PCT), C-reactive protein (CRP), white blood cell count (WBC), neutrophil/lymphocyte ratios (NLR), and the severity of the disease in childhood community-acquired pneumonia (CAP) cases.

Methods This cross-sectional designed study included 30 pneumonia cases and 30 severe pneumonia cases aged between 3 months and 18 years who were hospitalized and treated in our hospital with the diagnosis of CAP. We also included 30 healthy controls in the same age range. Pearson's correlation and receiver operating characteristic (ROC) curve analyzes were performed.

Results PCT, endocan, NLR, and CRP levels were found to be significantly higher in patients with severe pneumonia. Sensitivity and specificity values in detecting pneumonia were 72.5 and 93% for PCT, 78.4 and 83.3% for CRP, 78.4 and 76.7% for endocan, and 64.7 and 63.3% for NLR. However, the area under the curve in ROC analysis were 0.821, 0.840, 0.842, and 0.670 for PCT, CRP, endocan, and NLR respectively.

Conclusion Endocan may be a marker of the diagnosis of pneumonia and not clinical severity, but studies are needed in large patient populations.

PRO: Procalcitonin has clinical utility in children with community-acquired pneumonia

Procalcitonin (PCT) is a useful, albeit imperfect, diagnostic aid that can help clinicians make more informed decisions around antibiotic use in children with lower respiratory tract infections (LRTI), including community-acquired pneumonia (CAP). Recent data suggest that a very low PCT concentration has a high negative predictive value to identify a population of children at low risk of typical bacterial infections. Although the preponderance of data on the clinical utility of PCT in LRTI come from adult studies, the potential for benefit is likely greatest in paediatric CAP and other LRTIs where viral aetiologies predominate, yet antibiotics are frequently prescribed.