人工神经网络与心肌灌注图像统计定量诊断准确性的比较:一项日本多中心研究
该研究在12家医院用1001例门控负荷/静息99mTc-MIBI图像训练人工神经网络(ANN),并以364例专家判读为异常金标准进行验证。ANN对负荷缺损和负荷诱发缺血的AUC均优于SSS与SDS(0.92 vs 0.82、0.90 vs 0.75,均p<0.0001),作者认为ANN有助于诊断冠状动脉疾病。
要点
- ANN对负荷缺损的AUC为0.92,优于SSS的0.82(p<0.0001)。
- ANN对负荷诱发缺血的AUC为0.90,优于SDS的0.75(p<0.0001)。
- ANN值(异常概率)>0.80时,SSS/SRS/SDS陡增。
核心结论
- ANN在包括既往心肌梗死和冠状动脉血运重建患者在内的多种临床情形中具有诊断准确性。
- 作者认为ANN可帮助诊断冠状动脉疾病。
研究设计与样本
- ANN基于12家医院1001例门控负荷/静息99mTc-MIBI图像、按核医学专家判读结果训练,将潜在异常区域分类为真或假。
- 验证研究以364例专家判读作为异常金标准,比较ANN与常规SSS/SRS/SDS的诊断准确性并行ROC分析。
主要发现
- ANN对负荷缺损的AUC为0.92,SSS为0.82(p<0.0001),ANN识别负荷缺损更好。
- ANN对负荷诱发缺血的AUC为0.90,SDS为0.75(p<0.0001)。
- 基于静息缺损判断陈旧性心肌梗死患者的AUC:ANN为0.97,SRS为0.91(p=0.0061)。
- 基于负荷缺损、按有无血运重建史分组:有史者ANN AUC为0.94,无史者为0.90,分别与SSS比较p=0.0055和p<0.0001。
- ANN值(异常概率)>0.80时,SSS/SRS/SDS陡增。
关键数值与推荐
- 负荷缺损识别:ANN AUC 0.92 vs SSS 0.82(p<0.0001)。
- 负荷诱发缺血识别:ANN AUC 0.90 vs SDS 0.75(p<0.0001)。
- 陈旧性心肌梗死(静息缺损):ANN AUC 0.97 vs SRS 0.91(p=0.0061)。
- 有血运重建史者负荷缺损:ANN AUC 0.94 vs SSS(p=0.0055);无史者ANN AUC 0.90 vs SSS(p<0.0001)。
- ANN值(异常概率)>0.80时SSS/SRS/SDS陡增。
临床怎么用
- 原文未据此给出推荐。
- 作者认为ANN可帮助诊断冠状动脉疾病。
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
PURPOSE: Artificial neural networks (ANN) might help to diagnose coronary artery disease. This study aimed to determine whether the diagnostic accuracy of an ANN-based diagnostic system and conventional quantitation are comparable. METHODS: The ANN was trained to classify potentially abnormal areas as true or false based on the nuclear cardiology expert interpretation of 1001 gated stress/rest 99mTc-MIBI images at 12 hospitals. The diagnostic accuracy of the ANN was compared with 364 expert interpretations that served as the gold standard of abnormality for the validation study. Conventional summed stress/rest/difference scores (SSS/SRS/SDS) were calculated and compared with receiver operating characteristics (ROC) analysis. RESULTS: The ANN generated a better area under the ROC curves (AUC) than SSS (0.92 vs. 0.82, p < 0.0001), indicating better identification of stress defects. The ANN also generated a better AUC than SDS (0.90 vs. 0.75, p < 0.0001) for stress-induced ischemia. The AUC for patients with old myocardial infarction based on rest defects was 0.97 (0.91 for SRS, p = 0.0061), and that for patients with and without a history of revascularization based on stress defects was 0.94 and 0.90 (p = 0.0055 and p < 0.0001 vs. SSS, respectively). The SSS/SRS/SDS steeply increased when ANN values (probability of abnormality) were >0.80. CONCLUSION: The ANN was diagnostically accurate in various clinical settings, including that of patients with previous myocardial infarction and coronary revascularization. The ANN could help to diagnose coronary artery disease.
引用
- Nakajima K, Kudo T, Nakata T, et al. Diagnostic accuracy of an artificial neural network compared with statistical quantitation of myocardial perfusion images: a Japanese multicenter study. Eur J Nucl Med Mol Imaging. 2017. PMID: 28948350. doi:10.1007/s00259-017-3834-x
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。