文献速递神经肿瘤

无功能巨大垂体神经内分泌肿瘤切除的预测建模:多平面视角

Predictive Modeling of Nonfunctioning Giant Pituitary Neuroendocrine Tumor Resection: A Multi-Planar Perspective.
PubMed 文献 · World Neurosurg · 2025-02-03

本研究回顾性分析100例无功能巨大垂体神经内分泌肿瘤(直径≥3 cm、体积>10 cm³),基于肿瘤直径、形状、修订Knosp分级及改良Hardy分类构建机器学习模型预测全切除(GTR)或切除范围(EOR),极端梯度提升算法内部验证AUC为0.86。

要点

  • 术前中位肿瘤体积17.35 cm³,中位EOR 97.6%,GTR率49%。
  • 改良Hardy分类(鞍外扩展)与Knosp分级预测价值最高,AUC分别为0.771和0.713。
  • 极端梯度提升模型内部验证AUC 0.86,外部验证敏感度84%、特异度77%。

核心结论

  • 利用三维方式分析术前影像参数对预测无功能巨大垂体神经内分泌肿瘤的EOR具有很高价值,预测结果可通过在线开放获取应用计算。

研究设计与样本

  • 回顾性研究,纳入100例大型无功能巨大垂体神经内分泌肿瘤(直径≥3 cm、体积>10 cm³),基于肿瘤直径、形状、修订Knosp分级及改良Hardy分类(鞍内和鞍外侵袭)5个变量构建GTR或EOR预测模型,采用受试者工作特征曲线下面积(AUC)和混淆矩阵指标评估模型性能。

主要发现

  • 术前中位肿瘤体积为17.35 cm³(四分位距12.4-27.0),中位EOR为97.6%(四分位距84.9-100),49%的患者实现GTR。
  • 预测价值最高的变量为改良Hardy分类(鞍外扩展)和Knosp分级,AUC分别为0.771和0.713。
  • 构建的机器学习模型中,极端梯度提升算法预测能力最高,内部验证AUC为0.86,外部验证敏感度、特异度、阳性预测值和阴性预测值分别为84%、77%、78%和82%。

关键数值与推荐

  • 改良Hardy分类(鞍外扩展)预测GTR或EOR的AUC为0.771。
  • Knosp分级预测GTR或EOR的AUC为0.713。
  • 极端梯度提升模型内部验证AUC为0.86,外部验证敏感度84%、特异度77%、阳性预测值78%、阴性预测值82%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

BACKGROUND: Giant pituitary neuroendocrine tumors (GPitNETs) are challenging tumors with low rates of gross total resection (GTR) and high morbidity. Previously reported machine learning (ML) models for prediction of pituitary neuroendocrine tumor extent of resection (EOR) using preoperative imaging included a heterogenous dataset of functional and nonfunctional pituitary neuroendocrine tumors of various sizes leading to variability in results. METHODS: A retrospective study of 100 large nonfunctioning GPitNETs (≥3 cm diameter, >10 cm³ volume) was conducted to develop predictive models for GTR or EOR based on 5 variables: tumor diameter, shape, revised Knosp grade, and modified Hardy classifications for sellar and extrasellar invasion. Model performance was assessed using receiver operating characteristic-area under the curve (AUC) and confusion matrix metrics. RESULTS: The median preoperative tumor volume was 17.35 cm3 (interquartile range: 12.4-27.0). The median EOR was 97.6% (interquartile range: 84.9-100), and GTR was achieved in 49% of patients. The most predictive variables were the modified Hardy classification for extrasellar extension and Knosp grade (AUC of 0.771 and 0.713, respectively). Among the constructed ML models, the extreme gradient boost algorithm had the highest predictive capability, with an internal validation AUC of 0.86, while the external validation sensitivity, specificity, positive, and negative predictive values were 84%, 77%, 78%, and 82%, respectively. CONCLUSIONS: Utilizing preoperative imaging parameters in a 3-dimensional manner proves highly valuable in predicting the EOR for nonfunctioning GPitNETs. These predictions can be easily calculated using an online open-access application: http://emoryskullbase.shinyapps.io/giant_pituitary_adenoma_resection/.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Patel BK, Zohdy YM, Lohana S, et al. Predictive Modeling of Nonfunctioning Giant Pituitary Neuroendocrine Tumor Resection: A Multi-Planar Perspective. World Neurosurg. 2025. PMID: 39793732. doi:10.1016/j.wneu.2024.123653

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。