文献速递胃肠外科急腹症与外科感染

多中心验证人工智能平台诊断急性阑尾炎

Multicenter validation of an artificial intelligence (AI)-based platform for the diagnosis of acute appendicitis.
PubMed 文献 · Surgery · 2024-06-22

这项国际多中心回顾性队列研究评估人工智能平台诊断急性阑尾炎的准确性,使用多中心真实数据集(n=2,579)和合成数据集(n=9736)。平台灵敏度92.2%、特异度97.2%、阴性预测值98.7%,曲线下面积等指标良好。与CT相比,平台曲线下面积(0.92 vs 0.76)、特异度(90.9 vs 53.3)更优,灵敏度相当(99.2 vs 100),阴性预测值较低(67.6 vs 99.5)。作者认为该平台可能有助于疑似急性阑尾炎患者的决策,尤其当CT可及性有限时。

要点

  • 平台在多中心真实数据集(n=2,579)中灵敏度92.2%、特异度97.2%、阴性预测值98.7%。
  • 与CT相比,平台曲线下面积(0.92 vs 0.76)和特异度(90.9 vs 53.3)更优。
  • 平台灵敏度与CT相当(99.2 vs 100),但阴性预测值较低(67.6 vs 99.5)。

核心结论

  • 当前人工智能平台具有优异的灵敏度、特异度和超过90%的准确性,可能有助于临床医生对疑似急性阑尾炎患者做出决策,尤其当CT扫描可及性有限时。

研究设计与样本

  • 国际多中心回顾性队列研究,使用多中心真实数据集(n=2,579)和合成数据集(n=9736)评估人工智能平台的诊断准确性。

主要发现

  • 平台灵敏度92.2%、特异度97.2%、阴性预测值98.7%,受试者工作特征曲线下面积、精确率、F1分数和Matthews相关系数分别为0.97、86.7、0.89、0.88。
  • 与CT扫描相比,人工智能平台受试者工作特征曲线下面积更优(0.92 vs 0.76),特异度更高(90.9 vs 53.3),精确率更高(99.8 vs 98.9),Matthews相关系数更高(0.77 vs 0.72),灵敏度相当(99.2 vs 100),阴性预测值较低(67.6 vs 99.5)。
  • 决策曲线分析和临床影响曲线分析显示,平台在6%至96%的现实概率范围内具有显著的净获益。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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: The current scores used to help diagnose acute appendicitis have a "gray" zone in which the diagnosis is usually inconclusive. Furthermore, the universal use of CT scanning is limited because of the radiation hazards and/or limited resources. Hence, it is imperative to have an accurate diagnostic tool to avoid unnecessary, negative appendectomies. METHODS: This was an international, multicenter, retrospective cohort study. The diagnostic accuracy of the artificial intelligence platform was assessed by sensitivity, specificity, negative predictive value, the area under the receiver curve, precision curve, F1 score, and Matthews correlation coefficient. Moreover, calibration curve, decision curve analysis, and clinical impact curve analysis were used to assess the clinical utility of the artificial intelligence platform. The accuracy of the artificial intelligence platform was also compared to that of CT scanning. RESULTS: Two data sets were used to assess the artificial intelligence platform: a multicenter real data set (n = 2,579) and a well-qualified synthetic data set (n = 9736). The platform showed a sensitivity of 92.2%, specificity of 97.2%, and negative predictive value of 98.7%. The artificial intelligence had good area under the receiver curve, precision, F1 score, and Matthews correlation coefficient (0.97, 86.7, 0.89, 0.88, respectively). Compared to CT scanning, the artificial intelligence platform had a better area under the receiver curve (0.92 vs 0.76), specificity (90.9 vs 53.3), precision (99.8 vs 98.9), and Matthews correlation coefficient (0.77 vs 0.72), comparable sensitivity (99.2 vs 100), and lower negative predictive value (67.6 vs 99.5). Decision curve analysis and clinical impact curve analysis intuitively revealed that the platform had a substantial net benefit within a realistic probability range from 6% to 96%. CONCLUSION: The current artificial intelligence platform had excellent sensitivity, specificity, and accuracy exceeding 90% and may help clinicians in decision making on patients with suspected acute appendicitis, particularly when access to CT scanning is limited.

来源:Surgery,查看原文。版权归原作者所有。

引用

  1. Ghareeb WM, Draz E, Chen X, et al. Multicenter validation of an artificial intelligence (AI)-based platform for the diagnosis of acute appendicitis. Surgery. 2024. PMID: 38910047. doi:10.1016/j.surg.2024.05.007

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。