Gong Yushun, Wang Jianjie, Li Jingru, Wei Liang, Li Yongqin
Department of Biomedical Engineering and Imaging Medicine Army Medical University Chongqing China.
J Am Heart Assoc. 2025 Apr;14(7):e039527. doi: 10.1161/JAHA.124.039527. Epub 2025 Mar 27.
Quantitative ventricular fibrillation (VF) analysis has the potential to optimize defibrillation by predicting shock outcomes, but its performance remains unsatisfactory. This study investigated whether combining VF features with defibrillation parameters could enhance the ability of shock outcome prediction.
VF was electrically induced and left untreated for 30 to 180 seconds in 55 New Zealand rabbits. A defibrillatory shock was applied with 1 of 9 biphasic waveforms with different tilts and durations. A 4-step up-and-down protocol was used to maintain the success rate near 50% for each waveform. Ten features and 10 parameters were obtained from the recorded VF and defibrillation waveforms. Logistic regression and a convolutional neural network were used to combine VF features with defibrillation parameters.
The area under the curve value for the combination of a single VF feature and a single defibrillation parameter (0.725 [95% CI, 0.676-0.775] versus 0.644 [95% CI, 0.589-0.699]; =0.002) was significantly greater than that for the optimal VF feature. The area under the curve value for the combination of multiple VF features and multiple defibrillation parameters (0.752 [95% CI, 0.704-0.800] versus 0.657 [95% CI, 0.602-0.712]; <0.001) was significantly greater than that the combination of multiple VF features. The area under the curve for the combination of the raw VF waveform and raw defibrillation waveform (0.781 [95% CI, 0.734-0.828] versus 0.685 [95% CI, 0.632-0.738]; =0.007) was significantly greater than that for the raw VF waveform.
In this animal model, combining VF features with defibrillation parameters greatly enhanced the ability of shock outcome prediction, whether it was based on extracted features/parameters or directly using raw waveforms with machine learning methods.
定量心室颤动（VF）分析有通过预测电击结果来优化除颤的潜力，但其性能仍不尽人意。本研究调查了将VF特征与除颤参数相结合是否能增强电击结果预测能力。
在55只新西兰兔身上电诱发VF，并使其持续30至180秒不进行处理。使用9种不同倾斜度和持续时间的双相波形之一施加除颤电击。采用4步上下法使每种波形的成功率维持在50%左右。从记录的VF和除颤波形中获取10个特征和10个参数。使用逻辑回归和卷积神经网络将VF特征与除颤参数相结合。
单个VF特征与单个除颤参数组合的曲线下面积值（0.725 [95%CI，0.676 - 0.775] 对比0.644 [95%CI，0.589 - 0.699]；P = 0.002）显著大于最佳VF特征的曲线下面积值。多个VF特征与多个除颤参数组合的曲线下面积值（0.752 [95%CI，0.704 - 0.800] 对比0.657 [95%CI，0.602 - 0.712]；P < 0.001）显著大于多个VF特征的组合。原始VF波形与原始除颤波形组合的曲线下面积（0.781 [95%CI，0.734 - 0.828] 对比0.685 [95%CI，0.632 - 0.738]；P = 0.007）显著大于原始VF波形的曲线下面积。
在该动物模型中，将VF特征与除颤参数相结合极大地增强了电击结果预测能力，无论是基于提取的特征/参数还是直接使用原始波形并采用机器学习方法。
