文献速递妇科

深度学习评估机器人辅助阴道残端缝合技术技能研究

Deep learning for Evaluation and Prediction of TecHnical Skills in robotic-assisted vaginal cuff closure study.
PubMed 文献 · Am J Obstet Gynecol · 2026-03-19

这项多中心前瞻性观察队列研究基于40段机器人辅助全子宫切除的阴道残端缝合视频,开发深度学习模型预测技术错误和通用手术技能。模型在5样本设置下准确率达81.70%,多模态技能评估与人工评分高度一致(rs=0.85±0.02),为人工智能驱动的质量监测奠定基础。

要点

  • 深度学习可客观评分阴道残端缝合的通用手术技能并初步标记帧级错误。
  • 多模态模型与人工评估高度一致(rs=0.85±0.02,平均绝对误差=1.85±0.16)。
  • 经验水平与技能评分显著相关,手术时间与技能和错误数均相关。

核心结论

  • 深度学习可基于阴道残端缝合视频客观评分通用手术技能并初步标记帧级错误,与经验证的工具一致。

研究设计与样本

  • 多中心前瞻性观察队列研究,纳入2023至2025年机器人辅助全子宫切除术的40段阴道残端缝合视频(667分钟,1,201,654帧),来自2个中心、11名术者(3初级、5中级、3专家)。
  • 视频由2名受训外科医生双重标注,错误采用Objective Clinical Human Reliability Analysis,整体技能采用Modifiable Global Evaluative Assessment of Robotic Skills。
  • 开发3条深度学习流程:手术视频错误检测(时序建模)、手术技能评估(少样本学习)和多模态学习。

主要发现

  • Modifiable Global Evaluative Assessment of Robotic Skills评分组内相关系数0.807(P=.001),Objective Clinical Human Reliability Analysis错误计数组内相关系数0.712(P=.010)。
  • Modifiable Global Evaluative Assessment of Robotic Skills中位评分21.0(四分位距19.1-24.6),错误中位数25.0(四分位距16.3-31.5)。
  • 经验水平与Modifiable Global Evaluative Assessment of Robotic Skills显著相关(Kruskal-Wallis检验<0.002)。
  • 手术时间与Modifiable Global Evaluative Assessment of Robotic Skills(rs=-0.534,P<.001)和Objective Clinical Human Reliability Analysis(rs=0.421,P=.007)显著相关。
  • 少样本实验中,模型在5样本设置下准确率81.70%、F1分数81.30%;多模态技能评估模型与人工评分高度一致(rs=0.85±0.02;平均绝对误差=1.85±0.16)。

关键数值与推荐

  • 少样本学习在5样本设置下准确率81.70%、F1分数81.30%。
  • 多模态模型与人工评分一致性rs=0.85±0.02,平均绝对误差=1.85±0.16。
  • Modifiable Global Evaluative Assessment of Robotic Skills组内相关系数0.807(P=.001),Objective Clinical Human Reliability Analysis组内相关系数0.712(P=.010)。
  • 经验水平与Modifiable Global Evaluative Assessment of Robotic Skills的Kruskal-Wallis检验<0.002。
  • 手术时间与Modifiable Global Evaluative Assessment of Robotic Skills(rs=-0.534,P<.001)和Objective Clinical Human Reliability Analysis(rs=0.421,P=.007)相关。

临床怎么用

  • 可用于微创妇科手术中阴道残端缝合的技能客观评估和帧级错误初步标记。
  • 为人工智能驱动的质量监测和循证资质认证提供概念验证基础。

局限性

  • 样本量较小(40段视频、11名术者),需更大规模多中心数据集验证。
  • 研究为概念验证,尚未在临床常规中实施。

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: To support surgical education, an increasing focus has been on integrating surgical data, including surgical motion and activity and process understanding, to develop predictive models to assess surgical skills. OBJECTIVE: This study aimed to develop deep learning models based on fine-grained analysis to predict technical errors and generic surgical skills during robotic-assisted vaginal cuff closures as part of a hysterectomy. STUDY DESIGN: This was a multicenter prospective observational cohort study of robotic-assisted total hysterectomy performed between 2023 and 2025. Vaginal cuff closure video segments, recorded on the Touch Surgery video platform via the DS1 computer, were extracted and double-annotated by 2 trained surgeons: errors via Objective Clinical Human Reliability Analysis and global skill via Modifiable Global Evaluative Assessment of Robotic Skills. Of note, 3 deep learning pipelines were developed: 2 crucial surgical tasks (surgical video error detection via temporal modeling models and surgical skill assessment via few-shot surgical skill assessment) and multimodal learning. RESULTS: A total of 40 videos, including 667 minutes (1,201,654 frames), from 2 centers were analyzed. Of note, 11 surgeons performed vaginal cuff closure (3 beginners, 5 intermediates, and 3 experts). Interrater reliability was good for both Modifiable Global Evaluative Assessment of Robotic Skills (intraclass correlation coefficient, 0.807; P=.001) and Objective Clinical Human Reliability Analysis error counts (intraclass correlation coefficient, 0.712; P=.010). The median Modifiable Global Evaluative Assessment of Robotic Skills score was 21.0 (interquartile range, 19.1-24.6), and the median error was 25.0 (interquartile range, 16.3-31.5). Level of experience showed a significant correlation to Modifiable Global Evaluative Assessment of Robotic Skills: the Kruskal-Wallis test was <0.002. Significant correlations were found between operative time and Modifiable Global Evaluative Assessment of Robotic Skills and Objective Clinical Human Reliability Analysis (rs=-0.534 [P<.001] and rs=0.421 [P=.007], respectively). Few-shot experiments showed that the model achieves a performance of 81.70% accuracy and 81.30% F1 score in the 5-shot setting. The multimodal skill assessment model achieved excellent agreement with manual assessment ratings (rs=0.85±0.02; mean absolute error=1.85±0.16). CONCLUSION: This proof of concept shows that deep learning can objectively score generic surgical skill and initial flag frame-level errors in vaginal cuff closure videos, aligning with validated objective assessment tools. Although larger, multicenter datasets remain essential, these results lay the groundwork for artificial intelligence-driven quality monitoring and evidence-based credentialing in minimally invasive gynecologic surgery.

来源:Am J Obstet Gynecol,查看原文。版权归原作者所有。

引用

  1. Tesfai F, Xu J, Anastasiou D, et al. Deep learning for Evaluation and Prediction of TecHnical Skills in robotic-assisted vaginal cuff closure study. Am J Obstet Gynecol. 2026. PMID: 41864316. doi:10.1016/j.ajog.2026.03.015

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。