Scholarlink

Objective <p>To analyze the clinical characteristics of children with invasive pneumococcal disease (IPD) admitted to Kunming Children’s Hospital from 2020 to 2024, and to develop a risk stratification model for pneumococcal meningitis among children with confirmed or highly suspected IPD using multiple machine learning algorithms.</p> Methods <p>A retrospective analysis was conducted on 65 pediatric patients with confirmed IPD, divided into a meningitis group (<i>n</i> = 37) and a non-meningitis group (<i>n</i> = 28). Clinical characteristics between the two groups were compared. Variable selection was performed using LASSO regression, and six machine learning models—Logistic Regression (LR), K-Nearest Neighbor (KNN), Naive Bayes (NB), Multilayer Perceptron (MLP), Random Forest (RF), and XGBoost—were constructed based on the selected features. Model performance was evaluated using AUC, F1 score, accuracy, sensitivity, and specificity, while Decision Curve Analysis (DCA) was employed to assess clinical utility.</p> Results <p>The meningitis group exhibited stronger inflammatory responses and poorer outcomes (in-hospital death and treatment abandonment). The predominant serotypes were 19&#xa0;F (25.8%), 19&#xa0;A (20.9%), and 14 (17.7%). LASSO regression identified six key predictive variables: headache, vomiting, nuchal rigidity, disease course, C-reactive protein (CRP), and blood urea nitrogen (BUN). Among the machine learning models, Logistic Regression and MLP performed best, with AUC values of 0.942 and 0.947, respectively. DCA indicated the highest net clinical benefit for these two models. A nomogram based on the Logistic Regression model enabled individualized risk estimation within the IPD population.</p> Conclusion <p>Pediatric pneumococcal meningitis remains associated with high disability rates and poor prognosis. The machine learning-based predictive model integrating clinical symptoms and laboratory indicators demonstrated a discriminative ability and may hold the potential to serve as a supportive tool for risk stratification among children with invasive pneumococcal disease.</p> Clinical trial number <p>Not applicable.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning and meningitis prediction in pediatric invasive pneumococcal disease: a retrospective single-center study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月21日

查看全文
  • Yonghan Luo,
  • Mingbiao Ma,
  • Mengyue Tong,
  • Xin Ma,
  • Deyuan Jiang,
  • Hao Wu,
  • Lijiao Yuan,
  • Yan Guo,
  • Ying Zhu,
  • Haifeng Jin,
  • Penghao Cui,
  • Ruonan Li,
  • Qingping Tang,
  • Yanchun Wang

摘要

Objective

To analyze the clinical characteristics of children with invasive pneumococcal disease (IPD) admitted to Kunming Children’s Hospital from 2020 to 2024, and to develop a risk stratification model for pneumococcal meningitis among children with confirmed or highly suspected IPD using multiple machine learning algorithms.

Methods

A retrospective analysis was conducted on 65 pediatric patients with confirmed IPD, divided into a meningitis group (n = 37) and a non-meningitis group (n = 28). Clinical characteristics between the two groups were compared. Variable selection was performed using LASSO regression, and six machine learning models—Logistic Regression (LR), K-Nearest Neighbor (KNN), Naive Bayes (NB), Multilayer Perceptron (MLP), Random Forest (RF), and XGBoost—were constructed based on the selected features. Model performance was evaluated using AUC, F1 score, accuracy, sensitivity, and specificity, while Decision Curve Analysis (DCA) was employed to assess clinical utility.

Results

The meningitis group exhibited stronger inflammatory responses and poorer outcomes (in-hospital death and treatment abandonment). The predominant serotypes were 19 F (25.8%), 19 A (20.9%), and 14 (17.7%). LASSO regression identified six key predictive variables: headache, vomiting, nuchal rigidity, disease course, C-reactive protein (CRP), and blood urea nitrogen (BUN). Among the machine learning models, Logistic Regression and MLP performed best, with AUC values of 0.942 and 0.947, respectively. DCA indicated the highest net clinical benefit for these two models. A nomogram based on the Logistic Regression model enabled individualized risk estimation within the IPD population.

Conclusion

Pediatric pneumococcal meningitis remains associated with high disability rates and poor prognosis. The machine learning-based predictive model integrating clinical symptoms and laboratory indicators demonstrated a discriminative ability and may hold the potential to serve as a supportive tool for risk stratification among children with invasive pneumococcal disease.

Clinical trial number

Not applicable.