文献速递垂体与肾上腺疾病性腺与生殖内分泌

机器学习加速先天性肾上腺类固醇生成障碍的病因诊断

Machine learning algorithms to accelerate etiological diagnosis of congenital disorders of adrenal steroidogenesis.
PubMed 文献 · J Clin Endocrinol Metab · 2026-01-01

本研究利用LC-MS/MS检测血浆类固醇激素谱,构建LightGBM结合决策树的机器学习模型,对先天性肾上腺类固醇生成障碍(CDAS)进行分型诊断。开发队列1027人(325例基因确诊CDAS、702例对照)中模型平均总体准确率97.1%、敏感度99.5%、特异度93.7%,验证队列507例中总体准确率98.9%。11-脱氧皮质醇、17-羟孕酮、21-脱氧皮质醇和皮质酮为最强判别特征。

要点

  • 机器学习辅助类固醇谱可高准确度区分CDAS亚型
  • 11-脱氧皮质醇、17-羟孕酮等为关键判别激素
  • 模型具可解释性,有望用于儿科内分泌决策支持

核心结论

  • 机器学习辅助类固醇谱为CDAS提供准确且高可解释性的诊断方法,有望整合进儿科内分泌诊断与决策支持系统。

研究设计与样本

  • 开发队列1027人(325例基因确诊CDAS、涵盖8个亚型,702例对照)用于建模,采用LightGBM筛选关键类固醇激素并构建优化决策树分类器,5折交叉验证评估内部性能。
  • 验证队列包含507份独立LC-MS/MS类固醇谱用于进一步评估模型性能。
  • 附加分析包括SHAP、混淆矩阵可视化、主成分分析(PCA)和UMAP。

主要发现

  • 开发队列中模型平均总体准确率97.1%、敏感度99.5%、特异度93.7%,宏平均AUC为0.97。
  • 大多数主要CDAS亚型的亚型水平准确率超过98%。
  • 验证队列中总体准确率98.9%、敏感度93.6%、特异度99.8%。
  • 特征重要性与SHAP分析识别11-脱氧皮质醇、17-羟孕酮、21-脱氧皮质醇和皮质酮为最强判别因子。
  • PCA与UMAP显示CDAS各亚型聚类分明,支持模型预测的生物学一致性。

临床怎么用

  • 对于疑诊CDAS的儿科患者,可基于LC-MS/MS类固醇谱结合机器学习模型辅助病因分型,提高早期靶向管理效率。

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: Early and accurate etiological diagnosis of congenital disorders of adrenal steroidogenesis (CDAS) is critical as timely targeted management can prevent life-threatening complications and improve long-term outcomes. OBJECTIVE: To develop and validate a machine learning-assisted decision tree model for classifying CDAS using plasma steroid hormone profiles quantified by liquid chromatography-mass spectrometry (LC-MS/MS). METHODS: A development cohort of 1027 participants (325 genetically confirmed CDAS patients representing 8 subtypes/702 controls) was used for model construction. The Light Gradient Boosting Machine algorithm identified key discriminatory steroid hormones, which were integrated into an optimized decision-tree classifier. Internal performance was assessed through 5-fold cross-validation. The performance of the model was further evaluated using a validation cohort comprising 507 independent LC-MS/MS steroid profiles. Additional analyses included Shapley additive explanations (SHAP), confusion matrix visualization, principal component analysis (PCA), and Uniform Manifold Approximation and Projection (UMAP). RESULTS: In the development cohort, the model achieved a mean overall accuracy of 97.1%, sensitivity of 99.5%, and specificity of 93.7%, with a macro-AUC (area under curve) of 0.97. Subtype-level accuracy exceeded 98% for most major CDAS subtypes. In the validation cohort, overall accuracy was 98.9%, sensitivity 93.6%, specificity 99.8%. Feature importance analysis and SHAP identified 11-deoxycortisol, 17-hydroxyprogesterone, 21-deoxycortisol, and corticosterone as the strongest discriminators. Principal component analysis and UMAP revealed distinct clustering of CDAS subtypes, confirming the biological coherence of model predictions. CONCLUSION: Machine learning-assisted steroid profiling provides an accurate and highly interpretable diagnostic approach for CDAS, with potential for integration into pediatric endocrine diagnostics and decision-support systems.

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

引用

  1. Gurpinar Tosun B, Ercetin AN, Turan S, et al. Machine learning algorithms to accelerate etiological diagnosis of congenital disorders of adrenal steroidogenesis. J Clin Endocrinol Metab. 2026. PMID: 42359583. doi:10.1210/clinem/dgag237

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。