Assessing the risk of concurrent mycoplasma pneumoniae pneumonia in children with tracheobronchial tuberculosis: retrospective study.

Objective: This study aimed to create a predictive model based on machine learning to identify the risk for tracheobronchial tuberculosis (TBTB) occurring alongside Mycoplasma pneumoniae pneumonia in pediatric patients. Methods: Clinical data from 212 pediatric patients were examined in this retrospective analysis. This cohort included 42 individuals diagnosed with TBTB and Mycoplasma pneumoniae pneumonia (combined group) and 170 patients diagnosed with lobar pneumonia alone (pneumonia group). Three predictive models, namely XGBoost, decision tree, and logistic regression, were constructed, and their performances were assessed using the receiver's operating characteristic (ROC) curve, precision-recall curve (PR), and decision curve analysis (DCA). The dataset was divided into a 7:3 ratio to test the first and second groups, utilizing them to validate the XGBoost model and to construct the nomogram model. Results: The XGBoost highlighted eight significant signatures, while the decision tree and logistic regression models identified six and five signatures, respectively. The ROC analysis revealed an area under the curve (AUC) of 0.996 for XGBoost, significantly outperforming the other models (p < 0.05). Similarly, the PR curve demonstrated the superior predictive capability of XGBoost. DCA further confirmed that XGBoost offered the highest AIC (43.226), the highest average net benefit (0.764), and the best model fit. Validation efforts confirmed the robustness of the findings, with the validation groups 1 and 2 showing ROC and PR curves with AUC of 0.997, indicating a high net benefit. The nomogram model was shown to possess significant clinical value. Conclusion: Compared to machine learning approaches, the XGBoost model demonstrated superior predictive efficacy in identifying pediatric patients at risk of concurrent TBTB and Mycoplasma pneumoniae pneumonia. The model's identification of critical signatures provides valuable insights into the pathogenesis of these conditions.

Spatiotemporal analysis of pertussis in Hunan Province, China, 2009-2019.

OBJECTIVES: This study aims to explore the spatial and spatiotemporal distribution of pertussis in Hunan Province, and provide a scientific basis for targeting preventive measures in areas with a high incidence of pertussis. DESIGN: In this retrospective spatial and spatiotemporal (ecological) study, the surveillance and population data of Hunan Province from 2009 to 2019 were analysed. The ArcGIS V.10.3 software was used for spatial autocorrelation analysis and visual display, and SaTScan V.9.6 software was used for statistical analysis of spatiotemporal scan data. SETTINGS: Confirmed and suspected pertussis cases with current addresses in Hunan Province and onset dates between 1 January 2009 and 31 December 2019 were included in the study. PARTICIPANTS: The study used aggregated data, including 6796 confirmed and suspected pertussis cases. RESULTS: The seasonal peak occurred between March and September, and scattered children were at high risk. The global Moran's I was between 0.107 and 0.341 (p<0.05), which indicated that the incidence of pertussis in Hunan had a positive spatial autocorrelation. The results of local indicators of spatial autocorrelation analysis showed that the hot spots were mainly distributed in the northeast region of Hunan Province. Moreover, both purely space and spatiotemporal scans showed that the central and northeastern parts were the most likely cluster areas with an epidemic period between March and October in 2018 and 2019. CONCLUSION: The distribution of the pertussis epidemic in Hunan Province from 2009 to 2019 shows spatiotemporal clustering. The clustering areas of the pertussis epidemic were concentrated in the central and northeastern parts of Hunan Province between March and October 2018 and 2019. In areas with low pertussis incidence, the strengthening of the monitoring system may reduce under-reporting. In areas with high pertussis incidence where we could study whether the genes of endemic pertussis strains are mutated and differ from vaccine strains.