文献速递胸部CT

人工智能与传统回归模型在肺癌风险预测中的比较:系统综述与Meta分析

Comparing Artificial Intelligence and Traditional Regression Models in Lung Cancer Risk Prediction Using A Systematic Review and Meta-Analysis.
PubMed 文献 · J Am Coll Radiol · 2025-03-04

该系统综述与Meta分析纳入140项研究,含185个传统回归模型与64个人工智能模型,按AUC比较其预测肺癌风险的表现。外部验证汇总AUC:人工智能模型0.82(95%CI 0.80-0.85),传统回归模型0.73(95%CI 0.72-0.74);含低剂量CT的人工智能模型亚组汇总AUC为0.85(95%CI 0.82-0.88)。两类模型总体偏倚风险均高。

要点

  • 外部验证汇总AUC:人工智能模型0.82 vs 传统回归模型0.73。
  • 含低剂量CT的人工智能模型亚组汇总AUC为0.85(95%CI 0.82-0.88)。
  • 作者认为人工智能模型在肺癌风险预测上似乎优于传统回归模型,尤其使用影像数据者。

核心结论

  • 人工智能模型,尤其使用影像数据者,在肺癌风险预测上似乎优于传统回归模型。
  • 作者提出未来研究应聚焦人工智能模型的前瞻性验证及在多样人群中与传统方法的直接比较。

研究设计与样本

  • 系统综述与Meta分析,按PRISMA指南报告,检索MEDLINE、Embase、Scopus与CINAHL数据库。
  • 共纳入140项研究,含185个传统回归模型与64个人工智能模型,其中16个人工智能模型与65个传统模型经过外部验证。
  • 由两名研究者筛选文献、第三名研究者解决分歧,采用预测模型偏倚风险评估工具(PROBAST)评价研究质量,以AUC汇总判别性能。

诊断标准与关键数值

  • 人工智能模型外部验证汇总AUC为0.82(95%CI 0.80-0.85)。
  • 传统回归模型外部验证汇总AUC为0.73(95%CI 0.72-0.74)。
  • 亚组分析中含低剂量CT的人工智能模型汇总AUC为0.85(95%CI 0.82-0.88)。

临床应用与阅片要点

  • 原文未据此给出推荐。

局限性

  • 人工智能模型与传统模型的总体偏倚风险均为高。
  • 作者指出未来研究应聚焦人工智能模型的前瞻性验证及在多样人群中与传统方法的直接比较,提示现有证据尚待前瞻性验证。

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: Accurately identifying individuals who are at high risk of lung cancer is critical to optimize lung cancer screening with low-dose CT (LDCT). We sought to compare the performance of traditional regression models and artificial intelligence (AI)-based models in predicting future lung cancer risk.

METHODS: A systematic review and meta-analysis were conducted with reporting according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched MEDLINE, Embase, Scopus, and the Cumulative Index to Nursing and Allied Health Literature databases for studies reporting the performance of AI or traditional regression models for predicting lung cancer risk. Two researchers screened articles, and a third researcher resolved conflicts. Model characteristics and predictive performance metrics were extracted. The quality of studies was assessed using the Prediction model Risk of Bias Assessment Tool. A meta-analysis assessed the discrimination performance of models, based on area under the receiver operating characteristic curve (AUC).

RESULTS: One hundred forty studies met inclusion criteria and included 185 traditional and 64 AI-based models. Of these, 16 AI models and 65 traditional models have been externally validated. The pooled AUC of external validations of AI models was 0.82 (95% confidence interval [CI], 0.80-0.85), and the pooled AUC for traditional regression models was 0.73 (95% CI, 0.72-0.74). In a subgroup analysis, AI models that included LDCT had a pooled AUC of 0.85 (95% CI, 0.82-0.88). Overall risk of bias was high for both AI and traditional models.

CONCLUSION: AI-based models, particularly those using imaging data, show promise for improving lung cancer risk prediction over traditional regression models. Future research should focus on prospective validation of AI models and direct comparisons with traditional methods in diverse populations.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Leonard S, Patel MA, Zhou Z, et al. Comparing Artificial Intelligence and Traditional Regression Models in Lung Cancer Risk Prediction Using A Systematic Review and Meta-Analysis. J Am Coll Radiol. 2025. PMID: 40049569. doi:10.1016/j.jacr.2025.02.042

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。