多模态人工智能用于肝纤维化分期的范围综述
本范围综述纳入21项研究、34个多模态AI模型,主要整合影像与临床或血清数据预测肝纤维化分期。研究多来自中国并聚焦乙肝相关肝病,以CT影像组学联合血清标志物最常见。107次AUC评估中位数为0.890,但模型外验证、校准和临床效用报告存在明显不足。
要点
- 多模态AI以CT影像组学联合血清标志物最常见,阅片时需关注同时输入的临床指标
- 多数模型缺乏外验证与校准报告,解读其诊断效能结论应保持审慎
- 现有证据集中于乙肝相关肝病,外推至其他病因肝纤维化缺乏依据
核心结论
- 多模态AI用于肝纤维化分期仍处于初步探索阶段,诊断性能有前景但方法学缺口显著
- 34个多模态AI模型的107次AUC评估中位数为0.890,四分位距为0.850-0.925
- 外验证AUC共12次评估来自6项研究,范围为0.808-0.990
- 单篇研究报告的3次内部测试AUC低于0.70
研究设计与样本
- 采用Joanna Briggs Institute方法学与PRISMA-ScR指南进行范围综述
- 检索MEDLINE、Web of Science、CENTRAL和IEEE Xplore数据库,检索日期为2025年8月12日
- 纳入开发AI或机器学习模型预测肝纤维化且整合至少一种影像模态与其他数据类别的研究
- 共2,849条记录,最终21项研究符合纳入标准,产生34个多模态AI模型
- 3名评价者独立筛选记录,提取数据由2名其他评价者独立核查
关键影像表现/征象
- 研究地理分布集中于中国,占81%
- 研究对象以乙型肝炎相关肝病为主
- CT影像组学联合血清生物标志物是最常见的模型构建方式
- 深度学习架构在纳入模型中使用较少
诊断标准与关键数值
- 107次AUC评估中位数为0.890,四分位距为0.850-0.925
- 外验证AUC共12次评估来自6项研究,范围为0.808-0.990
- 单篇研究报告的3次内部测试AUC低于0.70
- 仅20.6%的模型报告了外验证
- 校准报告占评估次数的23.1%,决策曲线分析占24.1%
临床应用与阅片要点
- 当前多模态AI模型对肝纤维化分期诊断效能尚可,但缺乏足够外验证前不应直接用于临床决策
- 阅片或报告中涉及多模态AI结果时需记录同时纳入的血清指标与临床参数
- 因证据集中在乙肝相关肝病,应用于其他病因时需额外验证
局限性
- 仅20.6%的模型报告外部验证,普遍缺乏方法学严谨的验证
- 校准报告仅占评估次数的23.1%,决策曲线分析仅占24.1%
- 研究地理分布高度集中于中国,以乙肝相关肝病为主,证据代表性有限
- 深度学习架构应用较少,多模态融合方法存在实质性方法学差距
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
Multimodal artificial intelligence (AI) approaches integrating heterogeneous data sources represent an emerging frontier in liver fibrosis assessment. However, use of multimodal AI for liver fibrosis staging has been only preliminarily explored, and the existing evidence is constrained by substantial methodological gaps. This scoping review aimed to comprehensively map the current evidence on multimodal AI models that integrate medical imaging with other data categories for predicting liver fibrosis stage. Following the Joanna Briggs Institute methodology and PRISMA-ScR guidelines, we searched MEDLINE, Web of Science, CENTRAL, and IEEE Xplore on August 12, 2025. Studies developing AI or machine learning models for liver fibrosis prediction integrating at least one imaging modality with heterogeneous data categories (e.g., clinical parameters or serum biomarkers) were included. Three reviewers independently screened records, and extracted data were independently verified by two additional reviewers. Of 2,849 records, 21 studies met the eligibility criteria, yielding 34 distinct multimodal AI models. Research was geographically concentrated in China (81%) and predominantly focused on hepatitis B-related liver disease. CT-based radiomics combined with serum biomarkers represented the most common approach, whereas deep learning architectures were less frequently applied. Across 107 AUC evaluations, the median AUC was 0.890 (interquartile range 0.850-0.925). External-validation AUCs (12 evaluations from 6 studies) ranged 0.808-0.990; 3 internal-test AUCs from a single study fell below 0.70. However, external validation was reported for only 20.6% of models, with calibration and decision curve analysis reported in 23.1% and 24.1% of evaluations, respectively. This scoping review revealed a nascent field with encouraging diagnostic performance but with substantial gaps in external validation, calibration reporting, and clinical utility assessment. Future research should prioritize methodologically rigorous validation and evaluate the impact on clinical decision-making.
引用
- Yoshida, Asahi, Ganchiku, et al. Multimodal artificial intelligence models for liver fibrosis staging: a scoping review. Abdom Radiol (NY). 2026. PMID: 42380350. doi:10.1007/s00261-026-05667-y
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。