文献速递甲状腺疾病

机器学习预测儿童甲状腺癌复发:基于XGBoost与SHAP的内分泌恶性肿瘤队列分析

Machine Learning Prediction of Recurrence in Pediatric Thyroid Cancer: Malignant Endocrine Tumors Cohort Analysis Using XGBoost and SHAP.
PubMed 文献 · J Clin Endocrinol Metab · 2026-01-01

该研究基于德国儿童肿瘤血液学恶性内分泌肿瘤登记库(1997-2023)250例18岁以下分化型甲状腺癌患者,采用XGBoost构建可解释机器学习模型预测24个月内结构复发或未缓解。独立测试集AUROC为0.86,50次验证平均AUROC为0.82(SD±0.05),SHAP分析显示诊断年龄小(<10岁)、术后甲状腺球蛋白升高和远处转移是最重要预测因素。

要点

  • XGBoost模型在独立测试集预测儿童DTC复发/未缓解的AUROC为0.86。
  • 50次验证平均AUROC 0.82(SD±0.05),敏感度0.81(SD±0.09),特异度0.64(SD±0.06)。
  • SHAP提示诊断年龄<10岁、术后甲状腺球蛋白升高和远处转移为最重要预测因素。

核心结论

  • 该可解释机器学习模型能可靠预测儿童分化型甲状腺癌早期复发或未缓解,可能补充现有风险分层系统以支持个体化风险适配治疗决策。

研究设计与样本

  • 回顾性分析德国儿童肿瘤血液学恶性内分泌肿瘤登记库(1997-2023)中250例18岁以下儿童分化型甲状腺癌患者,要求诊断年龄已知且随访≥24个月。
  • 复合研究终点为初始治疗后24个月内结构复发或未缓解。
  • 极端梯度提升分类器在80%数据上训练,剩余20%作为独立测试集,并通过50次随机分层训练-验证拆分评估泛化性,采用SHAP解释特征贡献。

主要发现

  • 最终模型在独立测试集上AUROC为0.86。
  • 50次验证拆分的平均AUROC为0.82(SD±0.05),敏感度0.81(SD±0.09),特异度0.64(SD±0.06)。
  • SHAP分析识别诊断年龄较小(<10岁)、术后甲状腺球蛋白水平升高和远处转移为最具影响力的预测因素。

临床怎么用

  • 该模型可用于儿童分化型甲状腺癌早期风险分层,辅助识别可能复发或未缓解的高危患者。
  • SHAP提示的预测因素(诊断年龄<10岁、术后甲状腺球蛋白升高、远处转移)有助于临床医生理解模型输出并个体化调整随访与治疗强度。

局限性

  • 回顾性研究设计,样本来自单一登记库(德国),外部泛化性需进一步验证。
  • 独立测试集仅占20%,样本量有限,敏感度与特异度存在一定波动(SD±0.09与±0.06)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

CONTEXT: Pediatric differentiated thyroid carcinoma (DTC) often presents with advanced disease but generally has excellent long-term survival. However, recurrence or failure to achieve remission remains relatively frequent, underscoring the need for improved early risk stratification. OBJECTIVE: To develop and evaluate an interpretable machine learning model for predicting recurrence or nonremission in pediatric DTC using routine clinical and biochemical variables. DESIGN AND SETTING: Retrospective analysis of 250 pediatric patients (aged <18 years) enrolled in the German Pediatric Oncology Hematology-Malignant Endocrine Tumors Registry (1997-2023). Inclusion required known age at diagnosis and ≥24 months of follow-up. The composite study endpoint was structural recurrence or failure to achieve remission within 24 months of initial therapy. METHODS: An extreme gradient boosting classifier was trained on 80% of the data, with the remaining 20% used as an independent test set. Model generalizability was assessed via 50 randomized stratified train-validation splits of the training dataset. SHapley Additive exPlanations (SHAP) were used to interpret feature contributions. RESULTS: The final model achieved an area under the receiver operating characteristic curve (AUROC) of 0.86 on the independent test set. Across 50 validation splits, the mean AUROC was 0.82 (SD ± 0.05), sensitivity 0.81 (SD ± 0.09), and specificity 0.64 (SD ± 0.06). SHAP analysis identified younger age at diagnosis (<10 years), elevated postoperative thyroglobulin levels, and distant metastases as the most influential predictors. CONCLUSION: This interpretable machine learning model reliably predicts early recurrence or nonremission in pediatric DTC and may complement current risk stratification systems to support personalized, risk-adapted treatment decisions.

来源:J Clin Endocrinol Metab,查看原文。版权归原作者所有。

引用

  1. Redlich A, Pfaehler E, Kunstreich M, et al. Machine Learning Prediction of Recurrence in Pediatric Thyroid Cancer: Malignant Endocrine Tumors Cohort Analysis Using XGBoost and SHAP. J Clin Endocrinol Metab. 2026. PMID: 40890050. doi:10.1210/clinem/dgaf487

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。