深度学习系统在脉搏波形中检测心房颤动的诊断评估
DCNN的AUC为0.997,显著优于其他基于手工特征的检测器;单条波形灵敏度95.2%、特异度99.0%,三条波形联合灵敏度100.0%、特异度99.6%。
要点
- DCNN在单条17秒PPG波形中检测AF的AUC为0.997,优于所有对比方法。
- 单条波形灵敏度95.2%、特异度99.0%;三条联合灵敏度100.0%、特异度99.6%。
- 在AF患病率2.8%的高危门诊人群中,DCNN具有高阴性预测值。
核心结论
- 在真实世界初级保健环境中,DCNN对PPG波形检测AF具有高灵敏度、特异度、PPV和NPV,优于其他基于手工特征的方法。
主要发现
- 验证集AF患病率为2.8%,参与者平均年龄68.4岁(SD 12.2),男性占46.8%。
- DCNN的AUC为0.997(95%CI 0.996-0.999),显著高于其他AF检测器(AUC范围0.924-0.985)。
- 单条17秒PPG波形:灵敏度95.2%(95%CI 88.3%-98.7%),特异度99.0%(95%CI 98.6%-99.3%),PPV 72.7%(95%CI 65.1%-79.3%),NPV 99.9%(95%CI 99.7%-100%)。
- 三条连续PPG波形(总时间<1分钟)联合:灵敏度100.0%(95%CI 87.7%-100%),特异度99.6%(95%CI 99.0%-99.9%),PPV 87.5%(95%CI 72.5%-94.9%),NPV 100%(95%CI 99.4%-100%)。
临床怎么用
- 该DCNN系统可用于高危成人AF筛查,单条17秒PPG波形即可提供高灵敏度和特异度,三条波形联合可进一步提高灵敏度至100%。
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
OBJECTIVE: To evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms. METHODS: We trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison. RESULTS: In the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924-0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%). CONCLUSIONS: In this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.
引用
- Poh MZ, Poh YC, Chan PH, et al. Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms. Heart. 2018. PMID: 29853485. doi:10.1136/heartjnl-2018-313147
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。