Predicting the severity of mycoplasma pneumoniae pneumonia in pediatric and adult patients: a multicenter study.

The purpose of this study is to develop a nomogram model for early prediction of the severe mycoplasma pneumoniae pneumonia (SMPP) in Pediatric and Adult Patients. A retrospective analysis was conducted on patients with MPP, classifying them into SMPP and non-severe MPP (NSMPP) groups. A total of 550 patients (NSMPP 374 and SMPP 176) were enrolled in the study and allocated to training, validation cohorts. 278 patients (NSMPP 224 and SMPP 54) were retrospectively collected from two institutions and allocated to testing cohort. The risk factors for SMPP were identified using univariate analysis. For radiomic feature selection, Spearman's correlation and the least absolute shrinkage and selection operator (LASSO) were utilized. Logistic regression was used to build different models, including clinical, imaging, radiomics, and integrated models (combining clinical, imaging, and radiomics features selected). The model's discrimination was evaluated using a receiver operating characteristic curve, its calibration with a calibration curve, and the results were visualized using the Hosmer-Lemeshow goodness-of-fit test. Thirteen clinical features and fourteen imaging features were selected for constructing the clinical and imaging models. Simultaneously, a set of twenty-five radiomics features were utilized to build the radiomics model. The integrated model demonstrated good calibration and discrimination in the training cohorts (AUC, 0.922; 95% CI: 0.900, 0.942), validation cohorts (AUC, 0.879; 95% CI: 0.806, 0.920), and testing cohorts (AUC, 0.877; 95% CI: 0.836, 0.916). The discriminatory and predictive efficacy of the clinical model in testing cohorts increased further after clinical and radiological features were incorporated (AUC, 0.849 vs. 0.922, P = 0.002). The model demonstrated exemplary predictive efficacy for SMPP by leveraging a comprehensive set of inputs, encompassing clinical data, quantitative and qualitative radiological features, along with radiomics features. The integration of these three aspects in the predictive model further enhanced the performance of the clinical model, indicating the potential for extensive clinical applications.

Zhuo LY ，Hao JW ，Song ZJ ，Meng H ，Wang TD ，Yang LL ，Yang ZM ，Ma JM ，Shen D ，Cui JJ ，Chen WJ ，Yang W ，Zang LL ，Wang JN ，Yin XP ... -  《Scientific Reports》

Development and Evaluation of a Nomogram for Predicting Pulmonary Embolism in Children With Severe Mycoplasma pneumoniae Pneumonia.

To construct a nomogram utilizing pediatric severe Mycoplasma pneumoniae pneumonia (SMPP) risk factors for pulmonary embolism (PE), facilitating the clinical identification and management of high-risk patients and reducing the excessive use of CT pulmonary angiography (CTPA). This was a retrospective analysis conducted between August 2021 and March 2024. We identified 35 children with SMPP complicated by PE, forming the PE group. A control group of 70 age- and sex-matched children with SMPP without PE was randomly selected at a 1:2 ratio. Clinical, laboratory, and CT findings were compared between the groups. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to develop a scoring model using a nomogram. The model's performance was assessed via the receiver operating characteristic curve (ROC), fivefold cross-validation, calibration curve, and clinical decision curve analysis. LASSO regression and multivariate logistic regression analyses revealed that D-dimer, neutrophil ratio, time to admission, pleural effusion, and necrotizing pneumonia were independent risk factors for PE in patients with SMPP. A nomogram prediction model was established based on the aforementioned independent risk factors. The area under ROC curve was 0.900. Fivefold cross-validation results further confirmed the model's stability. The calibration curve revealed good agreement between the predicted and actual probabilities of PE caused by SMPP, and the decision curve demonstrated that the nomogram model had a higher clinical net benefit. The nomogram serves as a predictive tool to aid in early intervention for pediatric patients with SMPP at high risk for PE, while minimizing unnecessary CTPA and overtreatment in low-risk patients.

Guan Y ，Zhao B ，Song C ，Hou Q ，Tong T ，Xu S ... -  《-》

Optimization strategy for the early timing of bronchoalveolar lavage treatment for children with severe mycoplasma pneumoniae pneumonia.

Early evaluation of severe mycoplasma pneumoniae pneumonia (SMPP) and the prompt utilization of fiberoptic bronchoscopic manipulation can effectively alleviate complications and restrict the progression of sequelae. This study aim to establish a nomogram forecasting model for SMPP in children and explore an optimal early therapeutic bronchoalveolar lavage (TBAL) treatment strategy. This retrospective study included children with mycoplasma pneumoniae pneumonia (MPP) from January 2019 to December 2021. Multivariate logistic regression analysis was used to screen independent risk factors for SMPP and establish a nomogram model. The bootstrap method was employed and a receiver operator characteristic (ROC) curve was drawn to evaluate the accuracy and robustness of the model. Kaplan-Meier analysis was used to assess the effect of lavage and hospitalization times. A total of 244 cases were enrolled in the study, among whom 68 with SMPP and 176 with non-SMPP (NSMPP). A prediction model with five independent risk factors: left upper lobe computed tomography (CT) score, sequential organ failure assessment (SOFA) score, acute physiology and chronic health assessment (APACHE) II score, bronchitis score (BS), and c-reactive protein (CRP) was established based on the multivariate logistic regression analysis. The ROC curve of the prediction model showed the area under ROC curve (AUC) was 0.985 (95% confidence interval (CI) 0.972-0.997). The Hosmer-Lemeshow goodness-of-fit test results showed that the nomogram model predicted the risk of SMPP well (χ2 = 2.127, P = 0.977). The log-rank result suggested that an early BAL treatment could shorten MPP hospitalization time (P = 0.0057). This nomogram model, based on the left upper lobe CT score, SOFA score, APACHE II score, BS, and CRP level, represents a valuable tool to predict the risk of SMPP in children and optimize the timing of TBAL.

Wu X ，Lu W ，Wang T ，Xiao A ，Guo X ，Xu Y ，Li S ，Liu X ，Zeng H ，He S ，Zhang X ... -  《-》

Prediction Model for Severe Mycoplasma pneumoniae Pneumonia in Pediatric Patients by Admission Laboratory Indicators.

The purpose of this study was to develop a model for predicting severe Mycoplasma pneumoniae pneumonia (SMPP) in pediatric patients with Mycoplasma pneumoniae pneumonia (MPP) on admission by laboratory indicators. Pediatric patients with MPP from January 2019 to December 2020 in our hospital were enrolled in this study. SMPP was diagnosed according to guideline for diagnosis and treatment of community-acquired pneumonia in children (2019 version). Prediction model was developed according to the admission laboratory indicators. Receiver operating characteristic curve and Goodness-of-fit test were analyzed for the predictive value. A total of 233 MPP patients were included in the study, with 121 males and 112 females, aged 4.541 (1-14) years. Among them, 84 (36.1%, 95% CI 29.9-42.6%) pediatric patients were diagnosed as SMPP. Some admission laboratory indicators (immunoglobulins M (IgM), eosinophil proportion, eosinophil count, hemoglobin, erythrocyte sedimentation rate (ESR), total protein, albumin and prealbumin) were found statistically different (p < 0.05) between non-SMPP group and SMPP group. Logistic regress analysis showed IgM, eosinophil proportion, eosinophil count, ESR and prealbumin were independent risk factors for SMPP. According to these five admission laboratory indicators, the prediction model for SMPP in pediatric patients was developed. The area under curve of the prediction model was 0.777, and the goodness-of-fit test showed that the predicted SMPP incidence by the model was consistent with the actual incidence (χ2 = 244.51, p = 0.203). We developed a model for predicting SMPP in pediatric patients by admission laboratory indicators. This model has good discrimination and calibration, which provides a basis for the early identification SMPP on admission. However, this model should be validated by multicenter studies with large sample.

Chang Q ，Chen HL ，Wu NS ，Gao YM ，Yu R ，Zhu WM ... -  《-》

Development and multicenter validation of a CT-based radiomics signature for predicting severe COVID-19 pneumonia.

To develop and validate a radiomics nomogram for timely predicting severe COVID-19 pneumonia. Three hundred and sixteen COVID-19 patients (246 non-severe and 70 severe) were retrospectively collected from two institutions and allocated to training, validation, and testing cohorts. Radiomics features were extracted from chest CT images. Radiomics signature was constructed based on reproducible features using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm with 5-fold cross-validation. Logistic regression modeling was employed to build different models based on quantitative CT features, radiomics signature, clinical factors, and/or the former combined features. Nomogram performance for severe COVID-19 prediction was assessed with respect to calibration, discrimination, and clinical usefulness. Sixteen selected features were used to build the radiomics signature. The CT-based radiomics model showed good calibration and discrimination in the training cohort (AUC, 0.9; 95% CI, 0.843-0.942), the validation cohort (AUC, 0.878; 95% CI, 0.796-0.958), and the testing cohort (AUC, 0.842; 95% CI, 0.761-0.922). The CT-based radiomics model showed better discrimination capability (all p < 0.05) compared with the clinical factors joint quantitative CT model (AUC, 0.781; 95% CI, 0.708-0.843) in the training cohort, the validation cohort (AUC, 0.814; 95% CI, 0.703-0.897), and the testing cohort (AUC, 0.696; 95% CI, 0.581-0.796). Decision curve analysis demonstrated that in terms of clinical usefulness, the radiomics model outperformed the clinical factors model and quantitative CT model alone. The CT-based radiomics signature shows favorable predictive efficacy for severe COVID-19, which might assist clinicians in tailoring precise therapy. • Radiomics can be applied in CT images of COVID-19 and radiomics signature was an independent predictor of severe COVID-19. • CT-based radiomics model can predict severe COVID-19 with satisfactory accuracy compared with subjective CT findings and clinical factors. • Radiomics nomogram integrated with the radiomics signature, subjective CT findings, and clinical factors can achieve better severity prediction with improved diagnostic performance.

Li L ，Wang L ，Zeng F ，Peng G ，Ke Z ，Liu H ，Zha Y ... -  《-》