This study aims to develop a machine learning (ML)-based predictive model for assessing the risk of multilobar pulmonary consolidation in children with macrolide-resistant Mycoplasma pneumoniae pneumonia (MRMP) caused by the 23S rRNA A2063G mutation, a subgroup underrepresented in prior studies. A total of 404 MRMP cases diagnosed between October 2024 and February 2025 were included in this study. Key clinical characteristics, including laboratory test results, symptoms, and treatment outcomes, were extracted from electronic medical records. Six ML models, including Logistic Regression, Naive Bayes, K-Nearest Neighbors, Multilayer Perceptron, Random Forest, and XG-Boost, were developed to predict multilobar pulmonary consolidation. Least absolute shrinkage and selection operator (LASSO) regression was used to select relevant variables. Model performance was then evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Finally, Sharpley Additive Explanations was used for model interpretability. XG-Boost demonstrated the highest predictive performance with an area under the ROC curve of 0.976 and 0.904 in the training and validation sets, respectively, showing a high sensitivity of 0.97, specificity of 0.81, accuracy of 0.94, and an F1 score of 0.95. Key predictors identified for multilobar pulmonary consolidation included the top 10 variables: C-reactive protein, lactate dehydrogenase, fibrinogen, platelet count, albumin, hemoglobin, creatinine, aspartate aminotransferase, interleukin-6, and oxygen therapy. DCA showed that the model also exhibited strong clinical utility. The XG-Boost predictive model offers a robust tool for identifying high-risk children with MRMP caused by the 23S rRNA A2063G mutation. By integrating clinical features, the model enhances early risk stratification and can support clinical decision-making, improving the accuracy and efficiency of treatment plans. IMPORTANCE: Macrolide-resistant Mycoplasma pneumoniae pneumonia caused by the 23S rRNA A2063G mutation poses a significant threat to pediatric health, often leading to severe multilobar pulmonary consolidation. This study develops a high-performance machine learning model (XG-Boost) that accurately predicts this complication using key clinical indicators such as C-reactive protein, lactate dehydrogenase, and IL-6. With an area under the ROC curve of 0.976, the model enables early risk stratification, guiding clinicians in optimizing treatment for high-risk children. By improving diagnostic precision and intervention timing, this tool can reduce disease severity, minimize hospital stays, and enhance patient outcomes. The interpretability of the model via Sharpley Additive Explanations analysis further ensures its clinical applicability, making it a valuable advancement in managing antibiotic-resistant pediatric pneumonia.

Objectives: This study aimed to analyze the clinical characteristics and genetic features of children with adverse reactions to the Bacillus Calmette-Guérin (BCG) vaccine. The goal was to improve understanding of this condition, provide insights into early diagnosis and intervention, and support stratified management.Methods: Clinical data of 35 children hospitalized at Kunming Children’s Hospital between January 2014 and June 2024 with complete records and diagnosed with BCG vaccine adverse reactions were collected. Cases were classified into two groups: disseminated BCG disease (BCG-D) and BCG-itis. Children with primary immunodeficiency (PID) were further divided into severe combined immunodeficiency (SCID) and non-SCID groups. Clinical characteristics, immunological profiles, genetic backgrounds, and outcomes were compared between the groups.Results: Among the 35 cases, 25 were male, and 10 were female, with a median age of onset of 2 months (1–4 months). Eight cases (22.9%) were diagnosed with BCG-D, while 27 cases (77.1%) were classified as BCG-itis. Sixteen cases (45.7%) were confirmed to have PID, including SCID (7 cases, 20.0%), chronic granulomatous disease (6 cases, 17.1%), Mendelian susceptibility to mycobacterial disease (2 cases, 5.7%), and fas associated via death domain (FADD) gene mutation (1 case, 2.6%). Compared to the BCG-itis group, the BCG-D group exhibited significantly higher rates of fever, hepatosplenomegaly, elevated white blood cell counts, neutrophil counts, and C-reactive protein (CRP) levels, along with lower red blood cell counts and hemoglobin levels (p<0.05). Similarly, the SCID group showed significantly lower age, lymphocyte counts, IgM levels, CD3, CD4, and CD8 cell ratios, but higher CD19 cell ratios and mortality rates compared to the non-SCID group (p<0.05). Twenty-seven (77.1%) cases were discharged after improvement, and eight children (22.9%) succumbed to the condition, including six with SCID gene mutations (representing 85.7% of the total SCID cases), one with an interleukin 12 receptor subunit beta 1(IL12RB1) mutation, and one who was not genetically tested but diagnosed with disseminated BCG disease.Conclusions: In children presenting with adverse reactions to the BCG vaccine, the presence of fever, hepatosplenomegaly, elevated neutrophil levels, and CRP should prompt evaluation for disseminated BCG disease and assessment of immunological status. Early identification of underlying PID, particularly SCID, is crucial, given the high mortality and poor prognosis associated with the condition, necessitating timely interventions.

This study aimed to develop and validate a simple-to-use nomogram for predicting severe scrub typhus (ST) in children. A retrospective study of 256 patients with ST was performed at the Kunming Children’s Hospital from January 2015 to November 2022. ALL patients were divided into a common and severe group based on the severity of the disease. A least absolute shrinkage and selection operator (LASSO) regression model was used to identify the optimal predictors, and the predictive nomogram was plotted by multivariable logistic regression. The nomogram was assessed by calibration, discrimination, and clinical utility. LASSO regression analysis identified that hemoglobin count (Hb), platelet count (PLT), lactate dehydrogenase (LDH), blood urea nitrogen (BUN), creatine kinase isoenzyme MB(CK-MB) and hypoproteinemia were the optimal predictors for severe ST. The nomogram was plotted by the six predictors. The area under the receiver operating characteristic (ROC) curve of the nomogram was 0.870(95% CI = 0.812 ~ 0.928) in training set and 0.839(95% CI = 0.712 ~ 0.967) in validation set. The calibration curve demonstrated that the nomogram was well-fitted, and the decision curve analysis (DCA) showed that the nomogram was clinically beneficial. This study developed and validated a simple‐to‐use nomogram for predicting severe ST in children based on six predictors including Hb, PLT, LDH, BUN, CK-MB and hypoproteinemia, demonstrating excellent predictive accuracy for the data, though external and prospective validation is required to assess its potential clinical utility. Scrub typhus (ST) is a serious infectious disease caused by Orientia tsutsugamushi transmitted through mite bites. It is particularly dangerous for children, and predicting its severity is critical for timely intervention. This study aimed to develop a simple, user-friendly tool to predict severe ST in children. Through a retrospective analysis of clinical data from 256 ST patients, we identified six critical factors—hemoglobin count (Hb), platelet count (PLT), lactate dehydrogenase (LDH), blood urea nitrogen (BUN), creatine kinase isoenzyme MB(CK-MB) and hypoproteinemia—that can predict disease severity. Based on these six factors, we developed a nomogram tool to assist healthcare providers in quickly assessing the risk of severe ST in children. The validation of the nomogram demonstrated its accuracy and utility in clinical decision-making. Our findings suggest that this nomogram could serve as a valuable tool in pediatric healthcare, aiding physicians in identifying children at higher risk for severe ST and making more informed treatment decisions.