文献速递神经CTCTA

机器学习算法在急性卒中中的真实世界应用评估

Machine-learning algorithm in acute stroke: real-world experience.
PubMed 文献 · Clin Radiol · 2022-11-18

本研究评估商业ML软件RAPID™ ASPECTS和CTA在104例疑似急性卒中患者中的临床表现,由两名神经放射科医生盲法独立回顾分析。RAPID™ CTA对LVO检测稳健可靠,敏感度92.3%、特异度85.3%、NPV 98.5%;RAPID™ ASPECTS敏感度和NPV均为87.5%,但特异度和PPV仅30.9%,假阳性率高。

要点

  • RAPID™ CTA对LVO检测敏感度92.3%、特异度85.3%、NPV 98.5%,表现稳健可靠。
  • RAPID™ ASPECTS检测急性缺血性实质改变敏感度87.5%、NPV 87.5%,但特异度和PPV仅30.9%,假阳性率51.1%。
  • 在确诊LVO病例中,RAPID™ ASPECTS与神经放射科医生盲法判读相关性良好。

核心结论

  • RAPID™ CTA对LVO检测稳健可靠,而RAPID™ ASPECTS虽敏感度和NPV高,但假阳性多,降低临床医生对算法的信心。
  • 在确诊LVO病例中,RAPID™ ASPECTS表现良好,与神经放射科医生盲法判读相关性好。

研究设计与样本

  • 单中心回顾性研究,纳入104例连续疑似急性卒中患者(43例女性,年龄范围19-93岁,中位年龄62岁),行CT和CTA检查并实时ML软件分析(RAPID™ ASPECTS和CTA)。
  • 由两名神经放射科医生以盲法独立回顾分析,参考标准为放射科医生判读。

关键影像表现/征象

  • 队列包含24例急性梗死和16例大血管闭塞(LVO)。
  • RAPID™ ASPECTS检测急性缺血性实质改变的假阳性率为51.1%。
  • RAPID™ CTA检测LVO的假阳性占12.5%,其中27.3%归因于动脉狭窄。

诊断标准与关键数值

  • RAPID™ ASPECTS检测急性缺血性实质改变:敏感度87.5%、NPV 87.5%、特异度30.9%、PPV 30.9%。
  • RAPID™ CTA检测LVO(N=13):敏感度92.3%、特异度85.3%、NPV 98.5%、PPV 52.2%。
  • 在确诊LVO病例中,RAPID™ ASPECTS与读者1的Pearson相关系数0.63,与读者2为0.69;两名读者间相关系数均为0.96。

临床应用与阅片要点

  • RAPID™ CTA可用于LVO筛查,高NPV有助于排除LVO,但需注意动脉狭窄可导致假阳性。
  • RAPID™ ASPECTS假阳性率高,判读急性缺血性实质改变时应谨慎,避免过度依赖算法结果。

局限性

  • 单中心回顾性研究,样本量较小(104例),结果外推需谨慎。

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

AIM: To assess the clinical performance of a commercially available machine learning (ML) algorithm in acute stroke.

MATERIALS AND METHODS: CT and CT angiography (CTA) studies of 104 consecutive patients (43 females, age range 19-93, median age 62) performed for suspected acute stroke at a single tertiary institution with real-time ML software analysis (RAPID™ ASPECTS and CTA) were included. Studies were retrospectively reviewed independently by two neuroradiologists in a blinded manner.

RESULTS: The cohort included 24 acute infarcts and 16 large vessel occlusions (LVO). RAPID™ ASPECTS interpretation demonstrated high sensitivity (87.5%) and NPV (87.5%) but very poor specificity (30.9%) and PPV (30.9%) for detection of acute ischaemic parenchymal changes. There was a high percentage of false positives (51.1%). In cases of proven LVO, RAPID™ ASPECTS showed good correlation with neuroradiologists' blinded independent interpretation, Pearson correlation coefficient = 0.96 (both readers), 0.63 (RAPID™ vs reader 1), 0.69 (RAPID™ vs reader 2). RAPID™ CTA interpretation demonstrated high sensitivity (92.3%), specificity (85.3%), and negative predictive (NPV) (98.5%) with moderate positive predictive value (PPV) (52.2%) for detection of LVO (N=13). False positives accounted for 12.5% of cases, of which 27.3% were attributed to arterial stenosis.

CONCLUSION: RAPID™ CTA was robust and reliable in detection of LVO. Although demonstrating high sensitivity and NPV, RAPID™ ASPECTS interpretation was associated with a high number of false positives, which decreased clinicians' confidence in the algorithm. However, in cases of proven LVO, RAPID™ ASPECTS performed well and had good correlation with neuroradiologists' blinded interpretation.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Chan, Sibtain, Booth, et al. Machine-learning algorithm in acute stroke: real-world experience. Clin Radiol. 2022. PMID: 36411087. doi:10.1016/j.crad.2022.10.007

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。