文献速递炎症性肠病

人工智能驱动的炎症性肠病临床试验:自动化与增强疾病评估和研究管理

Artificial Intelligence-Enabled Clinical Trials in Inflammatory Bowel Disease: Automating and Enhancing Disease Assessment and Study Management.
PubMed 文献 · Gastroenterology · 2025-03-28

本文为叙述性综述,聚焦当前可用的人工智能工具、其预期实施方式以及人工智能重塑炎症性肠病临床试验的未来机遇。综述指出人工智能图像分析在內镜、组织学和横断面影像中可快速、可重复且减少偏倚地复现专家判断,并能比人类专家更详细精确地量化疾病特征;大语言模型和生成式人工智能可自动化从电子记录中采集高质量数据并改善患者结局预测。

要点

  • 人工智能图像分析在內镜、组织学和横断面影像中可快速、可重复且减少偏倚地复现专家判断。
  • 人工智能分析能比人类专家更详细、更精确地量化疾病特征。
  • 大语言模型和生成式人工智能可自动化从电子记录中采集高质量数据并改善患者结局预测。

核心结论

  • 人工智能将通过标准化疾病评分、提高活动度和表型评估的敏感性与精确性以及自动化繁琐耗时的研究功能,从根本上改善临床试验的实施方式。

研究设计与样本

  • 叙述性综述,聚焦当前可用的人工智能工具、其预期实施方式以及人工智能重塑炎症性肠病临床试验的未来机遇。

主要发现

  • 人工智能图像分析在內镜、组织学和横断面影像中正快速证明能够以速度、可重复性和减少偏倚的方式复现专家判断。
  • 人工智能分析提供比人类专家更详细、更精确地量化疾病特征的能力。
  • 大语言模型和生成式人工智能正在自动化从电子记录中采集高质量数据,并改善预测患者结局的能力。

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

Artificial intelligence (AI) will fundamentally improve how we perform clinical trials by addressing issues of standardizing disease scoring, improving the sensitivity and precision of activity and phenotype assessments, and automating laborious and time-consuming study functions. Progress in AI image analysis is quickly proving to replicate expert judgment in endoscopy, histology, and cross-sectional imaging with speed, reproducibility, and reduced bias. However, AI analytics offer the ability to quantify disease characteristics with more detail and precision than human experts. Large language models and generative AI are automating the collection of high-quality data from electronic records and improving our ability to predict patient outcomes. This narrative review will focus on AI tools available today, their expected implementation, and future-facing opportunities for AI to reimagine inflammatory bowel disease clinical trials.

来源:Gastroenterology,查看原文。版权归原作者所有。

引用

  1. Stidham RW, Ghanem LR, Fletcher JG, et al. Artificial Intelligence-Enabled Clinical Trials in Inflammatory Bowel Disease: Automating and Enhancing Disease Assessment and Study Management. Gastroenterology. 2025. PMID: 40158739. doi:10.1053/j.gastro.2025.02.039

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。