Mycoplasma pneumoniae infection prediction model for hospitalized community-acquired pneumonia children

Application of peripheral blood routine parameters in the diagnosis of influenza and Mycoplasma pneumoniae

OBJECTIVES

Influenza and Mycoplasma pneumoniae infections often present concurrent and overlapping symptoms in clinical manifestations, making it crucial to accurately differentiate between the two in clinical practice. Therefore, this study aims to explore the potential of using peripheral blood routine parameters to effectively distinguish between influenza and Mycoplasma pneumoniae infections.

METHODS

This study selected 209 influenza patients (IV group) and 214 Mycoplasma pneumoniae patients (MP group) from September 2023 to January 2024 at Nansha Division, the First Affiliated Hospital of Sun Yat-sen University. We conducted a routine blood-related index test on all research subjects to develop a diagnostic model. For normally distributed parameters, we used the T-test, and for non-normally distributed parameters, we used the Wilcoxon test.

RESULTS

Based on an area under the curve (AUC) threshold of ≥ 0.7, we selected indices such as Lym# (lymphocyte count), Eos# (eosinophil percentage), Mon% (monocyte percentage), PLT (platelet count), HFC# (high fluorescent cell count), and PLR (platelet to lymphocyte ratio) to construct the model. Based on these indicators, we constructed a diagnostic algorithm named IV@MP using the random forest method.

CONCLUSIONS

The diagnostic algorithm demonstrated excellent diagnostic performance and was validated in a new population, with an AUC of 0.845. In addition, we developed a web tool to facilitate the diagnosis of influenza and Mycoplasma pneumoniae infections. The results of this study provide an effective tool for clinical practice, enabling physicians to accurately diagnose and differentiate between influenza and Mycoplasma pneumoniae infection, thereby offering patients more precise treatment plans.

A new dynamic nomogram for predicting the risk of severe Mycoplasma pneumoniae pneumonia in children

Mycoplasma pneumoniae pneumonia (MPP) is usually mild and self-limiting, but still about 12% of them will progress to severe Mycoplasma pneumoniae pneumonia (SMPP), which have poor survival rates and often require intensive medical resource utilization. We retrospectively collected clinical data from 526 children with MPP admitted to the Children's Hospital Affiliated to Zhengzhou University from June 2018 to February 2023 and randomly divided the data into a training cohort and a validation cohort at a ratio of 4:1. Univariate and multivariate logistic regressions were used to identify independent risk factors for SMPP. Age, AGR, NLR, CRP, ESR, MPV, coinfection, pleural effusion, primary disease, fever days ≥ 7 and wheeze are independent risk factors for SMPP in children. Then, we built an online dynamic nomogram ( https://ertongyiyuanliexiantu.shinyapps.io/SMPP/ ) based on the 11 independent risk factors. The C-index, ROC curve, DCA curve and calibration curve were used to assess the performance of the nomogram, which all showed that the dynamic nomogram has excellent clinical value. Based on age, AGR, NLR, CRP, ESR, MPV, coinfection, pleural effusion, primary disease, fever days ≥ 7 and wheeze, the first dynamic nomogram for accurately predicting SMPP was successfully established.

Clinical Characteristics of Lung Consolidation with Mycoplasma pneumoniae Pneumonia and Risk Factors for Mycoplasma pneumoniae Necrotizing Pneumonia in Children

INTRODUCTION

Mycoplasma pneumoniae necrotizing pneumonia (MPNP) is an uncommon but increasingly recognized severe complication of pneumonia, and the delayed diagnosis and treatment are prone to pulmonary sequelae. The aim of this study is to explore independent risk factors for MPNP in children with lung consolidation.

METHODS

A retrospective observational study was conducted on 118 children with MPNP (MPNP group) and 184 children with lung consolidation of Mycoplasma pneumoniae pneumonia (MPP) (control group) admitted to Children's Hospital Affiliated to Zhengzhou University from June 2018 to August 2023. Clinical manifestations and laboratory data were analyzed and the independent risk factors for MPNP in children were analyzed by multivariate logistic regression.

RESULTS

The age of onset, hospitalization days, fever days, proportion of dyspnea, chest pain, complications, and need for fiberoptic bronchoscopic alveolar lavage (FBAL) were higher than those in the control group, and the difference was statistically significant (P < 0.05). The levels of white blood cells (WBC), platelets, neutrophil percentage (N%), neutrophil-to-lymphocyte ratio (NLR), C-reactive protein (CRP), fibrinogen (Fbg), D-dimer (D-D), erythrocyte sedimentation rate (ESR), alanine transaminase (ALT), γ-glutamyl transpeptidase (γ-GGT), globulin, lactate dehydrogenase (LDH), α-hydroxybutyrate dehydrogenase (α-HBDH), urea, immunoglobulin G (IgG), immunoglobulin M (IgM), immunoglobulin A (IgA), complement component 3, antistreptolysin O (ASO), serum ferritin, and interleukin-6 (IL-6) in the MPNP group were higher than those in the control group. Red blood cell (RBC), lymphocyte percentage (L%), activated partial thromboplastin time (APTT), alkaline phosphatase (ALP), total protein, albumin, albumin-to-globulin ratio (AGR), creatine kinase (CK), uric acid, natrium, chlorine, calcium, and complement C4 in the MPNP group were lower than those in the control group, and the difference was statistically significant (P < 0.05). The results of multivariate logistic regression analysis showed that age ≥ 83.50 months, fever days ≥ 10.50, ALT ≥ 15.25 U/l, IgM ≥ 1.46 g/l, complement C3 ≥ 1.47 g/l, Fbg ≥ 3.93 g/l, dyspnea and needing FBAL were independent risk factors for MPNP in children.

CONCLUSIONS

Age, fever days, ALT, IgM, complement C3, Fbg, dyspnea, and needing FBAL were independent risk factors for MPNP in children. For children suspected of MPNP, pediatricians should pay close attention to the above indicators, strive for early diagnosis and treatment, and improve prognosis.

Clinical characteristics of hospitalized children with community-acquired pneumonia and respiratory infections: Using machine learning approaches to support pathogen prediction at admission

BACKGROUND

Acute respiratory infections (ARIs) are common in children. We developed machine learning models to predict pediatric ARI pathogens at admission.

METHODS

We included hospitalized children with respiratory infections between 2010 and 2018. Clinical features were collected within 24 h of admission to construct models. The outcome of interest was the prediction of 6 common respiratory pathogens, including adenovirus, influenza virus types A and B, parainfluenza virus (PIV), respiratory syncytial virus (RSV), and Mycoplasma pneumoniae (MP). Model performance was estimated using area under the receiver operating characteristic curve (AUROC). Feature importance was measured using Shapley Additive exPlanation (SHAP) values.

RESULTS

A total of 12,694 admissions were included. Models trained with 9 features (age, event pattern, fever, C-reactive protein, white blood cell count, platelet count, lymphocyte ratio, peak temperature, peak heart rate) achieved the best performance (AUROC: MP 0.87, 95% CI 0.83-0.90; RSV 0.84, 95% CI 0.82-0.86; adenovirus 0.81, 95% CI 0.77-0.84; influenza A 0.77, 95% CI 0.73-0.80; influenza B 0.70, 95% CI 0.65-0.75; PIV 0.73, 95% CI 0.69-0.77). Age was the most important feature to predict MP, RSV and PIV infections. Event patterns were useful for influenza virus prediction, and C-reactive protein had the highest SHAP value for adenovirus infections.

CONCLUSION

We demonstrate how artificial intelligence can assist clinicians identify potential pathogens associated with pediatric ARIs upon admission. Our models provide explainable results that could help optimize the use of diagnostic testing. Integrating our models into clinical workflows may lead to improved patient outcomes and reduce unnecessary medical costs.

Reduced serum 25(OH)D is closely related to bronchial mucus plug formation in children with mycoplasma pneumonia: A prospective cohort study

Background

The relationship between vitamin D nutritional status and the formation of bronchial mucus plugs (BMPs) is unclear. The aims of the current study were to investigate associations between serum 25(OH)D levels, serum inflammatory factors, and clinical characteristics in children with mycoplasma pneumonia (MPP), and to summarize the risk factors for BMPs in children with MPP.

Methods

Clinical data from 175 children with MPP were collected and analyzed, the children were divided into a BMP group and a non-BMP group. Serum 25(OH)D levels, IL-8, and various inflammatory factors were compared in the two groups. Associations between 25(OH)D levels and IL-8, various inflammatory factors, and clinical characteristics were analyzed, and the diagnostic value of serum 25(OH)D levels was assessed.

Results

Serum 25(OH)D level was significantly lower in the BMP group (p < 0.05). Serum IL-8 level, percentages of neutrophils, and some inflammatory factors were significantly higher in the BMP group (p < 0.05). Serum 25(OH)D level was negatively correlated with IL-8, neutrophil percentage, various inflammatory factors (all p < 0.05). It was also associated with lobular infection, pleural effusion, mechanical ventilation, and mycoplasma 2,063/2,064 mutation (all p < 0.05). In multivariate regression analysis 25(OH)D [odds ratio (OR) 0.98, 95% confidence interval (CI) 0.97-0.99, p = 0.003], IL-8 (OR 1.02, 95% CI 1.00-1.04, p = 0.002), polylobular infection (OR 1.75, 95% CI 1.17-2.64, p = 0.007), and MP DNA copies (OR 0.98, 95% CI 1.04-1.01, p = 0.022) were independent risk factors for BMPs, and the area under the curve value was 0.915 (95% CI 0.895-0.935). If the serum 25(OH)D level was <50 nmol/L, the respective percentages for sensitivity, specificity, positive predictive value, and negative predictive value were 97, 81, 78.9, and 97.6%.

Conclusions

Vitamin D deficiency is common in children with MPP, and 25(OH)D levels are closely associated with inflammatory factors and disease severity in children. The serum 25 (OH) D level of MPP children with BMPs was lower than that of children without BMPs. Serum 25(OH)D can be used as a marker for the diagnosis of MPP in children with BMPs.