文献速递腹部技术与安全CT

基于增强CT的人工智能在胰腺导管腺癌中的诊断效能:系统评价与Meta分析

Diagnostic performance of artificial intelligence based on contrast-enhanced computed tomography in pancreatic ductal adenocarcinoma: a systematic review and meta-analysis.
PubMed 文献 · Abdom Radiol (NY) · 2025-07-02

本Meta分析系统评价基于增强CT(CECT)的人工智能(AI)检测胰腺导管腺癌(PDAC)的诊断效能,检索PubMed、Embase和Web of Science至2025年3月,纳入19项研究。内部验证合并敏感度0.94、特异度0.93、AUC 0.98;外部验证敏感度0.84、特异度0.93、AUC 0.94。异质性显著(I²>85%),结论认为AI诊断效能优异但随临床情境和肿瘤分期变化,需前瞻性多中心试验验证。

要点

  • 内部验证合并敏感度0.94、特异度0.93、AUC 0.98。
  • 外部验证敏感度降至0.84、AUC降至0.94,特异度0.93与内部验证相仿。
  • 异质性显著(I²>85%),主要源于AI架构和队列规模的方法学差异。

核心结论

  • AI在CECT上对PDAC诊断表现优异,内部与外部验证均获高敏感度和特异度,但效能随临床情境和肿瘤分期显著变化,需前瞻性多中心试验采用标准化方案和多样队列(含早期肿瘤和复杂良性病变)验证其临床效用。

研究设计与样本

  • 系统评价与Meta分析,遵循PRISMA-DTA指南,检索PubMed、Embase和Web of Science自建库至2025年3月,纳入19项研究,内部验证队列5,986例、外部验证队列2,069例,采用双变量随机效应模型合并敏感度、特异度和AUC,以I²统计量评估异质性并行亚组分析。

诊断标准与关键数值

  • 内部验证:合并敏感度0.94(95%CI 0.89-0.96)、特异度0.93(95%CI 0.90-0.96)、AUC 0.98(95%CI 0.96-0.99);外部验证:敏感度0.84(95%CI 0.78-0.89)、特异度0.93(95%CI 0.87-0.96)、AUC 0.94(95%CI 0.92-0.96)。

临床应用与阅片要点

  • 作者认为,AI在CECT上对PDAC诊断效能优异,但效能随临床情境和肿瘤分期显著变化,需前瞻性多中心试验采用标准化方案和多样队列(含早期肿瘤和复杂良性病变)验证其临床效用。

局限性

  • 异质性显著(I²>85%),主要归因于AI架构的方法学差异和队列规模的不一致。
  • 作者指出需前瞻性多中心试验采用标准化方案和多样队列(含早期肿瘤和复杂良性病变)验证AI的临床效用。

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)。

英文原文(摘要)· 点击展开

PURPOSE: This meta-analysis systematically evaluated the diagnostic performance of artificial intelligence (AI) based on contrast-enhanced computed tomography (CECT) in detecting pancreatic ductal adenocarcinoma (PDAC).

METHODS: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Diagnostic Test Accuracy (PRISMA-DTA) guidelines, a comprehensive literature search was conducted across PubMed, Embase, and Web of Science from inception to March 2025. Bivariate random-effects models pooled sensitivity, specificity, and area under the curve (AUC). Heterogeneity was quantified via I² statistics, with subgroup analyses examining sources of variability, including AI methodologies, model architectures, sample sizes, geographic distributions, control groups and tumor stages.

RESULTS: Nineteen studies involving 5,986 patients in internal validation cohorts and 2,069 patients in external validation cohorts were included. AI models demonstrated robust diagnostic accuracy in internal validation, with pooled sensitivity of 0.94 (95% CI 0.89-0.96), specificity of 0.93 (95% CI 0.90-0.96), and AUC of 0.98 (95% CI 0.96-0.99). External validation revealed moderately reduced sensitivity (0.84; 95% CI 0.78-0.89) and AUC (0.94; 95% CI 0.92-0.96), while specificity remained comparable (0.93; 95% CI 0.87-0.96). Substantial heterogeneity (I² > 85%) was observed, predominantly attributed to methodological variations in AI architectures and disparities in cohort sizes.

CONCLUSIONS: AI demonstrates excellent diagnostic performance for PDAC on CECT, achieving high sensitivity and specificity across validation scenarios. However, its efficacy varies significantly with clinical context and tumor stage. Therefore, prospective multicenter trials that utilize standardized protocols and diverse cohorts, including early-stage tumors and complex benign conditions, are essential to validate the clinical utility of AI.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Yan G, Chen X, Wang Y, et al. Diagnostic performance of artificial intelligence based on contrast-enhanced computed tomography in pancreatic ductal adenocarcinoma: a systematic review and meta-analysis. Abdom Radiol (NY). 2025. PMID: 40601025. doi:10.1007/s00261-025-05089-2

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。