文献速递甲状腺疾病

机器学习预测抗甲状腺药物相关胰腺炎风险:一项全国性回顾性观察研究

Machine Learning Prediction of Pancreatitis Risk With Antithyroid Drugs: A Nationwide Retrospective Observational Study.
PubMed 文献 · J Clin Endocrinol Metab · 2025-01-01

丙硫氧嘧啶使用使急性胰腺炎概率增加0.10倍(10%)〔P=0.0009〕,普萘洛尔使用使急性胰腺炎概率降低0.5倍(5%)〔P=0.032〕,预测成功率为52.2%;甲巯咪唑使用与急性胰腺炎概率无统计学显著关联。

要点

  • 甲状腺功能亢进患者中诊断后发生急性胰腺炎的比例为0.81%(10815/1329934)。
  • 丙硫氧嘧啶使用与急性胰腺炎概率增加0.10倍(10%)相关〔P=0.0009〕。
  • 普萘洛尔使用与急性胰腺炎概率降低0.5倍(5%)相关〔P=0.032〕,预测成功率为52.2%。

核心结论

  • 甲巯咪唑使用未增加急性胰腺炎风险,但丙硫氧嘧啶使用增加、普萘洛尔使用降低甲状腺功能亢进患者发生急性胰腺炎的风险。
  • 尽管药物诱导的急性胰腺炎相对罕见,临床医生应充分了解相关药物以恰当诊断和治疗患者。

研究设计与样本

  • 共分析1329934例诊断为甲状腺功能亢进的患者,采用国际疾病分类第十版编码识别甲亢后发生急性胰腺炎者。
  • 使用R Studio 4.2.0软件,在Cox回归模型中采用训练-测试技术作为机器学习方法。

主要发现

  • 1329934例甲状腺功能亢进患者中,10815例(0.81%)在诊断甲亢后发生急性胰腺炎。
  • 丙硫氧嘧啶使用使发生急性胰腺炎诊断的概率增加0.10倍(10%)〔P=0.0009〕。
  • 普萘洛尔使用使发生急性胰腺炎的概率降低0.5倍(5%)〔P=0.032〕,预测成功率为52.2%。
  • 根据所建模型,甲巯咪唑使用与急性胰腺炎发生概率之间无任何统计学显著关联。

临床怎么用

  • 原文结论指出,临床医生应充分了解与急性胰腺炎相关的药物,以恰当诊断和治疗患者。

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: In recent years, there has been increasing data showing that the risk of acute pancreatitis (AP) is increased in patients using methimazole (MMI). The aim of this population-based study was to investigate the association between drugs used in the treatment of hyperthyroidism (MMI, propylthiouracil, propranolol) and the diagnosis of AP. MATERIAL AND METHODS: The database consisted of more than 85 million citizen records between January 1, 2017, and December 31, 2022. Within the scope of the study, the data were examined of patients diagnosed with hyperthyroidism and the individuals who developed acute pancreatitis after being diagnosed with hyperthyroidism, which was accomplished using the International Classification of Diseases, Tenth Revision codes. Analyses were carried out using R Studio 4.2.0 software. The test-train technique as a machine learning method was used in Cox regression models. RESULTS: A total of 1 329 934 individuals diagnosed with hyperthyroidism were examined. Of these, 10 815 (0.81%) patients developed AP after being diagnosed with hyperthyroidism. The use of propylthiouracil was determined to increase the probability of experiencing AP diagnosis 0.10-fold (10%) (P .0009), and the use of propranolol decreased the probability of experiencing AP 0.5-fold (5%) (P .032), with a 52.2% predictive success rate. There is no any statistically significant association between MMI use and the probability of experiencing AP according to the model we built. CONCLUSION: Although the risk of experiencing AP was not increased by MMI use, propylthiouracil use increased and propranolol use decreased the risk of experiencing AP in patients with hyperthyroidism. Although drug-induced AP is relatively rare, a firm understanding of the drugs associated with the condition should alert the clinician to appropriately diagnose and treat patients.

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

引用

  1. Kizilgul M, Yigit T, Ata N, et al. Machine Learning Prediction of Pancreatitis Risk With Antithyroid Drugs: A Nationwide Retrospective Observational Study. J Clin Endocrinol Metab. 2025. PMID: 39324654. doi:10.1210/clinem/dgae628

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。