文献速递神经CT

人工智能与专家获取的ASPECTS差异:相关因素及预后意义

Discrepancies in ASPECTS obtained by artificial intelligence and experts: Associated factors and prognostic implications.
PubMed 文献 · Eur J Radiol · 2024-08-28

这项多中心回顾性观察性队列研究纳入491例前循环大血管闭塞所致急性缺血性卒中患者,比较AI软件(RAPID ASPECTS)与核心实验室专家判读的ASPECTS一致性(ICC 0.63,95%CI 0.25-0.79),平均差异2.24;慢性梗死及内囊、豆状核专家评分与不一致相关;AI ASPECTS预测不良结局的AUC显著更高(0.68 vs 0.63,P=0.04)。

要点

  • AI(RAPID ASPECTS)较专家高估梗死范围,平均差异2.24分,ICC仅0.63。
  • 慢性梗死及内囊、豆状核区域专家评分是不一致的相关因素。
  • AI ASPECTS预测不良结局AUC 0.68,显著高于专家0.63(P=0.04)。

核心结论

  • 与专家ASPECTS相比,AI ASPECTS高估梗死范围;未来研究应确定AI ASPECTS评估是否应采用较低阈值筛选血管内治疗患者。

研究设计与样本

  • 多中心、回顾性、观察性队列研究,纳入491例前循环大血管闭塞所致急性缺血性卒中患者,ASPECTS由AI软件(RAPID ASPECTS)与核心实验室专家分别判定。

诊断标准与关键数值

  • 专家与AI ASPECTS的组内相关系数ICC为0.63(95%CI 0.25-0.79),两者平均差异为2.24;AI ASPECTS预测不良结局的AUC为0.68,专家ASPECTS为0.63(P=0.04)。

临床应用与阅片要点

  • 慢性梗死(OR 1.9,95%CI 1.1-3.4,P=0.021)及专家在内囊(OR 2.9,95%CI 1.1-7.7,P=0.034)和豆状核(OR 2.4,95%CI 1.3-4.7,P=0.008)的评分是不一致的相关因素。
  • 作者认为未来研究应确定AI ASPECTS评估是否应采用较低阈值筛选血管内治疗患者。

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)。

英文原文(摘要)· 点击展开

PURPOSE: The differences between the Alberta Stroke Program Early CT Score (ASPECTS) obtained by experts and artificial intelligence (AI) software require elucidation. We aimed to characterize the discrepancies between the ASPECTS obtained by AI and experts and determine the associated factors and prognostic implications.

METHODS: This multicenter, retrospective, observational cohort study included patients showing acute ischemic stroke caused by large-vessel occlusion in the anterior circulation. ASPECTS was determined by AI software (RAPID ASPECTS) and experts from the core laboratory. Interclass correlation coefficients (ICCs) and Bland-Altman plots were used to illustrate the consistency and discrepancies; logistic regression analyses were used to assess the correlates of inconsistency; and receiver operating characteristic analyses were performed to assess the diagnostic performance for predicting unfavorable clinical outcomes.

RESULTS: The study population included 491 patients. The ICC for the expert and AI ASPECTS was 0.63 (95 % confidence interval [CI]: 0.25-0.79).The mean difference between expert and AI ASPECTS was 2.24. Chronic infarcts (odds ratio [OR], 1.9; 95 % CI, 1.1-3.4; P=0.021) and expert scores in the internal capsule (OR, 2.9; 95 % CI, 1.1-7.7; P=0.034) and lentiform (OR, 2.4; 95 % CI, 1.3-4.7; P=0.008) were significant correlates of inconsistency. The ASPECTS obtained by AI showed a significantly higher area under the curve for unfavorable outcomes (0.68 vs. 0.63, P=0.04).

CONCLUSIONS: In comparison with expert ASPECTS, AI ASPECTS overestimated the infarct extent. Future studies should aim to determine whether AI ASPECTS assessments should use a lower threshold to screen patients for endovascular therapy.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Cheng X, Tian B, Huang L, et al. Discrepancies in ASPECTS obtained by artificial intelligence and experts: Associated factors and prognostic implications. Eur J Radiol. 2024. PMID: 39241301. doi:10.1016/j.ejrad.2024.111708

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。