文献速递儿科影像骨肌DR

AI作为教师:基于AI的训练模块提升受训者儿童骨折检测能力的效果

AI as teacher: effectiveness of an AI-based training module to improve trainee pediatric fracture detection.
PubMed 文献 · Skeletal Radiol · 2025-04-14

研究将240例儿童上肢X线片分为两组各120例,4名医学生和4名PGY-2放射科住院医师先无AI辅助评估120例,再通过训练模块复习AI标注,随后无AI辅助解读另120例。住院医师骨折检测准确率从71.3%显著提升至77.5%(p=0.032),医学生从56.3%至57.3%无显著变化(p=0.794),88%应答参与者(7/8)推荐该学习模式。

要点

  • 住院医师骨折检测准确率从71.3%提升至77.5%(p=0.032)。
  • 医学生准确率从56.3%至57.3%无显著变化(p=0.794)。
  • 88%应答参与者(7/8)推荐该学习模式。

核心结论

  • 量身定制的AI训练模块使住院医师儿童骨折检测准确率提高6.2%。
  • 医学生准确率未提高,可能因其对该任务背景熟悉度有限。
  • AI提供可扩展方法自动生成覆盖多样病理的标注教学病例,使住院医师高效地从模拟经验中学习。

研究设计与样本

  • 研究纳入240例儿童上肢X线检查,分为两组各120例。
  • 使用先前开发的开源深度学习骨折检测算法(www.childfx.com)标注X线片。
  • 4名医学生和4名PGY-2放射科住院医师先无AI辅助评估120例,再通过训练模块复习AI标注,随后无AI辅助解读另120例。
  • 采用卡方检验评估干预前后骨折检测准确率。

诊断标准与关键数值

  • 住院医师骨折检测准确率干预前71.3% vs 干预后77.5%(p=0.032)。
  • 医学生骨折检测准确率干预前56.3% vs 干预后57.3%(p=0.794)。

临床应用与阅片要点

  • AI训练模块可用于住院医师儿童骨折检测教学,医学生可能因背景熟悉度有限而获益不明显。
  • 88%应答参与者(7/8)推荐该学习模式。

局限性

  • 医学生准确率未提高,原文认为可能因其对该任务背景熟悉度有限。

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

OBJECTIVE: Prior work has demonstrated that AI access can help residents more accurately detect pediatric fractures. We wished to evaluate the effectiveness of an unsupervised AI-based training module as a pediatric fracture detection educational tool.

MATERIALS AND METHODS: Two hundred forty radiographic examinations from throughout the pediatric upper extremity were split into two groups of 120 examinations. A previously developed open-source deep learning fracture detection algorithm ( www.childfx.com ) was used to annotate radiographs. Four medical students and four PGY-2 radiology residents first evaluated 120 examinations for fracture without AI assistance and subsequently reviewed AI annotations on these cases via a training module. They then interpreted 120 different examinations without AI assistance. Pre- and post-intervention fracture detection accuracy was evaluated using a chi-squared test.

RESULTS: Overall resident fracture detection accuracy significantly improved from 71.3% pre-intervention to 77.5% post-intervention (p = 0.032). Medical student fracture detection accuracy was not significantly changed from 56.3% pre-intervention to 57.3% post-intervention (p = 0.794). Eighty-eight percent of responding participants (7/8) would recommend this model of learning.

CONCLUSION: We found that a tailored AI-based training module increased resident accuracy for detecting pediatric fractures by 6.2%. Medical student accuracy was not improved, likely due to their limited background familiarity with the task. AI offers a scalable method for automatically generating annotated teaching cases covering varied pathology, allowing residents to efficiently learn from simulated experience.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. O'Rourke S, Xu S, Carrero S, et al. AI as teacher: effectiveness of an AI-based training module to improve trainee pediatric fracture detection. Skeletal Radiol. 2025. PMID: 40227327. doi:10.1007/s00256-025-04927-0

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。