Scholarlink

Background <p>Epstein-Barr virus (EBV) infection is a common pediatric infectious disease. Infectious mononucleosis (IM) and hemophagocytic lymphohistiocytosis (HLH), two major complications of EBV infection, share similar clinical manifestations in the early stage. While IM is typically self-limiting, HLH is life-threatening and requires immediate intervention. Early differentiation between these two conditions is crucial for clinical decision-making; however, reliable prediction models based on readily available laboratory parameters remain scarce. This study aimed to develop and validate a machine learning prediction model using routine blood parameters obtained within 24&#xa0;h of hospital admission in children with confirmed acute EBV infection to distinguish EBV-associated IM (EBV-IM) from EBV-associated HLH (EBV-HLH).</p> Methods <p>This retrospective cohort study included 4,871 pediatric patients diagnosed with either EBV-IM or EBV-HLH from two campuses of Children’s Hospital of Chongqing Medical University. Demographic information and initial complete blood count (CBC) parameters within 24&#xa0;h of admission were collected. The cohort was divided into a model development group (Yuzhong Campus, <i>n</i> = 2,848; 70% for training, 30% for internal testing) and an external validation group (Liangjiang Campus, <i>n</i> = 2,023). Thirteen machine learning algorithms were evaluated using random search with 5-fold cross-validation for hyperparameter tuning. Shapley Additive exPlanations (SHAP) analysis was performed to interpret model predictions.</p> Results <p>EBV-HLH accounted for 12.46% (607/4,871) of the total cohort, with significantly different prevalence between the development and validation cohorts (18.29% vs. 4.25%, <i>p</i> &lt; 0.001). Significant differences were observed between cohorts in age and all CBC parameters except gender (<i>p</i> &lt; 0.05). The Random Forest (RF) model demonstrated optimal performance in the internal validation set (AUC = 0.993, 95% CI: 0.990–0.996). In the external validation cohort, the RF model maintained robust discriminative ability (AUC = 0.971, 95% CI: 0.949–0.992). Calibration curves indicated excellent agreement between predicted probabilities and actual risks. SHAP analysis identified WBC, PLT, LAC, and Hb as the most critical predictors of EBV-HLH. DCA demonstrated substantial clinical net benefit. A free online decision-support tool (<a href="https://wangrj1988.shinyapps.io/EBV-HLH-IM/">https://wangrj1988.shinyapps.io/EBV-HLH-IM/</a>) was developed based on the RF model to facilitate real-time risk assessment.</p> Conclusions <p>The RF-based model using routine CBC parameters enables admission-based risk assessment of pediatric EBV-HLH with excellent generalizability, offering a cost-effective tool for diverse healthcare settings.</p> Trial registration <p>Clinical trial number: 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

Development and external validation of a machine learning prediction model for Epstein-Barr virus-associated hemophagocytic lymphohistiocytosis in children using routine blood parameters: a retrospective cohort study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月27日

查看全文
  • Li Xiao,
  • Meiling Liao,
  • Yan Meng,
  • Jie Yu,
  • Yinghui Cui,
  • Haiyan Liu,
  • Wanxing Liu,
  • Ruijue Wang,
  • Zhu Li

摘要

Background

Epstein-Barr virus (EBV) infection is a common pediatric infectious disease. Infectious mononucleosis (IM) and hemophagocytic lymphohistiocytosis (HLH), two major complications of EBV infection, share similar clinical manifestations in the early stage. While IM is typically self-limiting, HLH is life-threatening and requires immediate intervention. Early differentiation between these two conditions is crucial for clinical decision-making; however, reliable prediction models based on readily available laboratory parameters remain scarce. This study aimed to develop and validate a machine learning prediction model using routine blood parameters obtained within 24 h of hospital admission in children with confirmed acute EBV infection to distinguish EBV-associated IM (EBV-IM) from EBV-associated HLH (EBV-HLH).

Methods

This retrospective cohort study included 4,871 pediatric patients diagnosed with either EBV-IM or EBV-HLH from two campuses of Children’s Hospital of Chongqing Medical University. Demographic information and initial complete blood count (CBC) parameters within 24 h of admission were collected. The cohort was divided into a model development group (Yuzhong Campus, n = 2,848; 70% for training, 30% for internal testing) and an external validation group (Liangjiang Campus, n = 2,023). Thirteen machine learning algorithms were evaluated using random search with 5-fold cross-validation for hyperparameter tuning. Shapley Additive exPlanations (SHAP) analysis was performed to interpret model predictions.

Results

EBV-HLH accounted for 12.46% (607/4,871) of the total cohort, with significantly different prevalence between the development and validation cohorts (18.29% vs. 4.25%, p < 0.001). Significant differences were observed between cohorts in age and all CBC parameters except gender (p < 0.05). The Random Forest (RF) model demonstrated optimal performance in the internal validation set (AUC = 0.993, 95% CI: 0.990–0.996). In the external validation cohort, the RF model maintained robust discriminative ability (AUC = 0.971, 95% CI: 0.949–0.992). Calibration curves indicated excellent agreement between predicted probabilities and actual risks. SHAP analysis identified WBC, PLT, LAC, and Hb as the most critical predictors of EBV-HLH. DCA demonstrated substantial clinical net benefit. A free online decision-support tool (https://wangrj1988.shinyapps.io/EBV-HLH-IM/) was developed based on the RF model to facilitate real-time risk assessment.

Conclusions

The RF-based model using routine CBC parameters enables admission-based risk assessment of pediatric EBV-HLH with excellent generalizability, offering a cost-effective tool for diverse healthcare settings.

Trial registration

Clinical trial number: not applicable.