文献速递小儿骨科创伤骨科

人工智能模型在小儿骨折X线检测中是否可靠用于临床应用?系统综述与Meta分析

Are Artificial Intelligence Models Reliable for Clinical Application in Pediatric Fracture Detection on Radiographs? A Systematic Review and Meta-analysis.
PubMed 文献 · Clin Orthop Relat Res · 2025-08-20

本系统综述与Meta分析纳入16项诊断准确性研究、10,203例患儿和21,789张X线片,评估AI模型检测小儿骨折的汇总敏感度93%、特异度91%、AUC 0.96;外部验证研究中敏感度93%、特异度88%、AUC 0.95;作者认为骨科医生和急诊医生可考虑将经过验证的卷积神经网络算法纳入工作流程。

要点

  • AI模型检测小儿骨折汇总敏感度93%、特异度91%、AUC 0.96。
  • 外部验证研究中敏感度93%、特异度88%、AUC 0.95。
  • 多区域模型敏感度略高,单区域模型特异度更好。

核心结论

  • Meta分析显示AI模型能准确检测小儿X线片上的骨折,该发现在纳入外部验证的研究中经受了检验。
  • 作者认为骨科医生和急诊医生可考虑将经过验证的卷积神经网络算法纳入工作流程,以提高诊断准确性,尤其是在需要快速准确决策的急性诊疗环境中。
  • 作者指出未来研究需要调查不同亚组(包括性别和解剖区域)的表现,并认为采用外部地理验证的配对设计诊断准确性研究仍是评估其真实价值的最合适方法。
  • 作者认为此类验证应作为AI模型临床推广和普及的前提优先开展,甚至应在随机试验或前瞻性实施研究之前进行。

研究设计与样本

  • 本Meta分析遵循PRISMA 2020指南,并在PROSPERO注册(CRD42024628342)。
  • 系统检索PubMed/MEDLINE、Embase和Cochrane Library,检索时间从数据库建库至2024年12月9日,共识别497条记录。
  • 纳入16项诊断准确性研究,涉及10,203例小儿患者(平均年龄8.85岁,54%为男性)和21,789张X线片,其中5882张确认骨折。
  • 数据提取遵循PIT框架,由两名评价者独立完成;偏倚风险采用QUADAS-2工具评估,证据确定性采用GRADE方法评估。
  • Meta分析采用logit变换和双变量模型估计汇总敏感度、特异度和AUC。

主要发现

  • 汇总分析显示敏感度为93%(95%CI 92%至94%),特异度为91%(95%CI 88%至93%),AUC为0.96(95%CI 0.92至0.97)。
  • 在外部数据集上评估时,AI模型保持高诊断准确性,敏感度为93%(95%CI 90%至95%),特异度为88%(95%CI 84%至91%),AUC为0.95(95%CI 0.89至0.97)。
  • 敏感度的汇总估计异质性为中等(I²=61%),特异度的汇总估计异质性为高(I²=90%)。
  • 基于Egger检验(p=0.54)和漏斗图对称性,未检测到发表偏倚证据。
  • 按特定区域划分的解剖覆盖对解释观察到的异质性有重要贡献;评估多个区域的模型显示敏感度略高,而专注于单一区域的模型显示特异度更好。

关键数值与推荐

  • 大多数研究显示低至中等偏倚风险,本研究中GRADE评估显示高确定性证据。
  • 汇总敏感度93%(95%CI 92%至94%)、特异度91%(95%CI 88%至93%)、AUC 0.96(95%CI 0.92至0.97)。
  • 外部验证研究中敏感度93%(95%CI 90%至95%)、特异度88%(95%CI 84%至91%)、AUC 0.95(95%CI 0.89至0.97)。
  • 敏感度异质性I²=61%,特异度异质性I²=90%;Egger检验发表偏倚p=0.54。
  • 证据等级为Level III,诊断性研究。

临床怎么用

  • 作者认为骨科医生和急诊医生可考虑将经过验证的卷积神经网络算法纳入工作流程,以提高诊断准确性,尤其是在需要快速准确决策的急性诊疗环境中。
  • 作者认为采用外部地理验证的配对设计诊断准确性研究仍是评估AI模型真实价值的最合适方法,此类验证应作为临床推广和普及的前提优先开展。

局限性

  • 现有研究受样本量小、诊断指标可变以及外部验证使用不一致的限制,降低了对研究结果的信心。
  • 敏感度的汇总估计异质性为中等(I²=61%),特异度的汇总估计异质性为高(I²=90%)。
  • 作者指出未来研究需要调查不同亚组(包括性别和解剖区域)的表现。

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: Artificial intelligence (AI) applications for pediatric fracture diagnosis using radiographs have demonstrated growing potential in clinical settings. Despite this growing potential, existing studies are limited by small sample sizes, variability in their diagnostic metrics, and inconsistent use of external validation, which reduces confidence in their findings. These limitations hinder the assessment of real-world performance. A meta-analysis would help address these gaps by pooling data to generate more robust, generalizable estimates for clinical application and future guidance. QUESTIONS/PURPOSES: (1) What is the pooled diagnostic performance of AI models, including sensitivity, specificity, and area under the curve (AUC), for detecting pediatric fractures on radiographs? (2) What is the clinical applicability of AI models, as determined by whether their diagnostic performance is sustained in studies that employed external validation? (3) How does anatomic coverage influence the diagnostic performance of AI models? METHODS: This meta-analysis adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines and was registered in PROSPERO (CRD42024628342). A systematic search of PubMed/MEDLINE, Embase, and the Cochrane Library was conducted from database inception through December 9, 2024. A total of 497 records were identified. Eligible studies included pediatric patients with suspected fractures evaluated by AI models on radiographs. Studies were excluded if they lacked sufficient data to calculate sensitivity, specificity, or AUC; if they combined adult and pediatric populations; or if they focused on rib fractures. Sixteen diagnostic accuracy studies were included, involving 10,203 pediatric patients with a mean age of 8.85 years, 54% of whom were male, and 21,789 radiographs, of which 5882 confirmed fractures. Data extraction followed the Population, Index test, Target condition (PIT) framework and was performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, which evaluates four domains (patient selection, index test, reference standard, and flow/timing) for low, high, or unclear risk. Most studies exhibited low to moderate risk of bias. Certainty of evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach, which classifies evidence as high, moderate, low, or very low, and in this study demonstrated high certainty of evidence. Heterogeneity in the pooled estimates was moderate for sensitivity (I 2 = 61%) and high for specificity (I 2 = 90%). No evidence of publication bias was detected based on Egger test (p = 0.54) and funnel plot symmetry. Meta-analyses used logit transformation and bivariate modeling to estimate pooled sensitivity, specificity, and AUC. RESULTS: The pooled analysis demonstrated a sensitivity of 93% (95% confidence interval [CI] 92% to 94%), a specificity of 91% (95% CI 88% to 93%), and an AUC of 0.96 (95% CI 0.92 to 0.97). The AUC reflects the overall ability of a model to distinguish between patients with and without fractures, with values closer to 1.0 indicating better diagnostic performance. When evaluated on external data sets, AI models maintained high diagnostic accuracy, with a sensitivity of 93% (95% CI 90% to 95%), specificity of 88% (95% CI 84% to 91%), and an AUC of 0.95 (95% CI 0.89 to 0.97), supporting their potential for clinical applicability. Anatomic coverage by specific region made a meaningful contribution to explaining the observed heterogeneity. Models evaluating multiple regions showed slightly higher sensitivity, while those focused on single regions demonstrated better specificity, suggesting that a broader anatomic scope may improve fracture detection but slightly reduce accuracy in ruling out false positives. CONCLUSION: This meta-analysis demonstrates that AI models can accurately detect pediatric fractures on radiographs, a finding that withstood scrutiny in studies that included external validation. These findings suggest that orthopaedic surgeons and emergency physicians can consider incorporating validated convolutional neural network algorithms into workflows to enhance diagnostic accuracy, especially in acute care settings where rapid and accurate decision-making is critical. Nevertheless, future research is needed to investigate performance across specific subgroups, including sex and anatomic regions. Paired-design diagnostic accuracy studies with external geographic validation remain the most appropriate method to assess their real-world value. Such validation should be prioritized as a prerequisite for clinical generalization and democratization of AI models, even before randomized trials or prospective implementation studies. LEVEL OF EVIDENCE: Level III, diagnostic study.

来源:Clin Orthop Relat Res,查看原文。版权归原作者所有。

引用

  1. Ximenes GF, Costa ÁL, Leite LL, et al. Are Artificial Intelligence Models Reliable for Clinical Application in Pediatric Fracture Detection on Radiographs? A Systematic Review and Meta-analysis. Clin Orthop Relat Res. 2025. PMID: 40839831. doi:10.1097/CORR.0000000000003660

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。