文献速递胃肠外科急腹症与外科感染围术期管理与 ERAS

基于AI的疾病严重度分级预测腹腔镜阑尾切除术并发症

AI-based disease severity grading predicts complications in laparoscopic appendectomy.
PubMed 文献 · Surg Endosc · 2026-08-24

本回顾性研究纳入632例腹腔镜阑尾切除术手术视频,由AI平台常规分析生成严重度评分并分为低危和高危组。高危组并发症率显著更高(26.7% vs 10%),AI严重度评分独立预测并发症(OR 2.76),校正 operative-AAST 后仍显著(OR 1.90)。模型区分度中等(AUC 0.63),与 operative-AAST 相似,在中等风险区间净获益最高。

要点

  • AI手术视频严重度评分可独立预测腹腔镜阑尾切除术并发症。
  • 高危组并发症率26.7%,显著高于低危组的10%。
  • 模型区分度中等(AUC 0.63),与 operative-AAST 相似。

核心结论

  • 自动AI手术视频评估可作为腹腔镜阑尾切除术风险预测的补充工具,提供可扩展的风险分层。

研究设计与样本

  • 回顾性研究,纳入2022年6月至2024年1月连续632例腹腔镜阑尾切除术手术视频,由AI平台常规分析。

主要发现

  • 高危组总体并发症率26.7%,低危组10%(p<0.001)。
  • 高危组术中并发症率11.8%,低危组3.2%(p<0.001)。
  • 高危组术后并发症率15.5%,低危组7.5%(p=0.005)。
  • AI严重度评分独立预测并发症(OR 2.76,95%CI 1.62-4.73;p<0.001)。
  • 校正 operative-AAST 后AI评分仍独立预测并发症(OR 1.90,95%CI 1.07-3.36;p=0.028)。

关键数值与推荐

  • AI严重度评分区分度AUC=0.63,operative-AAST的AUC=0.68。
  • 校准图显示并发症率随预测概率增加而上升,极端值一致性可接受,中等风险区间对齐改善。
  • 决策曲线分析显示模型在中等风险区间净获益最高,与 operative-AAST 相当或更高。

临床怎么用

  • 可将AI手术视频严重度评分用于腹腔镜阑尾切除术的常规风险分层,辅助围术期决策。

局限性

  • 模型区分度中等(AUC 0.63),需进一步研究和模型优化。

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: Appendicitis severity underpins contemporary management guidelines, where laparoscopic appendectomy remains gold standard. Preoperative measures poorly predict actual disease severity or complication risk, while operative grading systems such as the American Association for the Surgery of Trauma (AAST) remains largely confined to research settings. Artificial intelligence (AI) may provide practical solutions. We evaluated a previously validated AI-derived surgical video assessment of disease severity for predicting perioperative complications. METHODS: This retrospective study included consecutive surgical videos (6/2022-1/2024) routinely analyzed by the AI platform. AI-derived severity scores were stratified into Low (uncomplicated) and High (complicated) groups. Multivariable analysis identified independent predictors of complications. Operative-AAST served for benchmarking. Model discrimination (AUC), post hoc recalibration plot, and decision curve analysis (DCA) were evaluated. RESULTS: Of 632 cases, 74.5% were low severity and 25.5% high. The High group had higher complication rates (26.7% vs. 10%; p<0.001), including intraoperative (11.8 vs. 3.2%; p < 0.001) and postoperative complications (15.5 vs. 7.5%; p = 0.005). AI-derived severity independently predicted complications (OR 2.76, 95% CI 1.62-4.73; p < 0.001), even after adjustment for operative-AAST (OR 1.90, 95% CI 1.07-3.36; p = 0.028). Discrimination was modest (AUC = 0.63), similar to operative-AAST (AUC = 0.68). Calibration plot showed incremental increase in complication rates across probabilities, with acceptable agreements at extremes and improved alignment at intermediate-risk. DCA showed the model had highest net benefit at intermediate-risk, comparable or higher than operative-AAST. CONCLUSIONS: Automated AI-based surgical video assessment shows promise as a complementary tool for risk-prediction of laparoscopic appendectomy. It offers scalable risk stratification that may be implemented in routine clinical practice. Nevertheless, further study and model refinement are warranted.

来源:Surg Endosc,查看原文。版权归原作者所有。

引用

  1. Kardish T, Ortenzi M, Nizri E, et al. AI-based disease severity grading predicts complications in laparoscopic appendectomy. Surg Endosc. 2026. PMID: 42637944. doi:10.1007/s00464-026-13302-6

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。