A Hidden Markov Model Approach for Ventricular Fibrillation Detection
A Hidden Markov Model Approach for Ventricular Fibrillation Detection
复制标题
DOI：
10.22489/cinc.2018.120
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Borja Altamira;E. Alonso;U. Irusta;E. Aramendi;M. Daya
中科院分区：
文献类型：
--
作者：
Borja Altamira;E. Alonso;U. Irusta;E. Aramendi;M. Daya
室颤（VF）的早期检测和除颤与使用自动体外除颤器（AED）治疗的院外心脏骤停（OHCA）患者的生存率提高相关。本研究提出了一种方法，用于VF检测使用心电图从OHCA患者。该研究的数据集包含来自169名OHCA患者的596个10秒ECG片段，144个可电击和452个不可电击。将数据集按患者分为训练集（60%）和测试集（40%）。对每个ECG段进行带通滤波（1-30 Hz），计算波形特征并将其作为观察结果馈送给隐马尔可夫模型（HMM），该模型将每个观察结果分配给两个隐藏状态之一，可电击或不可电击。使用k-means聚类减少了可能的观察值的数量。该方法的优化包括特征选择和通过前向贪婪包裹方法在训练集中使用逐患者10倍交叉验证来优化聚类数量。使用测试集，根据灵敏度（SE）和特异性（SP）计算该方法的性能。重复该过程500次以估计性能度量的分布。该方法显示平均（SD）SE和SP分别为94.4%（3.8）和97.8%（1.2）。该方法符合美国心脏协会的要求。
Early detection and defibrillation of ventricular fibrillation (VF) has been associated with improved survival of out-of-hospital cardiac arrest (OHCA) patients treated with automated external defibrillators (AEDs). This study proposes a method for VF detection using ECGs obtained from OHCA patients. The dataset of the study contained 596 10-s ECG segments, 144 shockable and 452 non-shockable, from 169 OHCA patients. The dataset was split patient-wise into training (60%) and test (40%) sets. Each ECG segment was band-pass filtered (1–30 Hz), waveform features were computed and fed as observations to a Hidden Markov Model (HMM) that assigned each observation to one of the two hidden states, shockable or non-shockable. The number of possible observations was reduced using k-means clustering. The optimization of the method consisted of feature selection and optimization of the number of clusters through a forward greedy wrapping approach using patient-wise 10-fold cross validation in the training set. The performance of the method was computed in terms of sensitivity (SE) and specificity (SP) using the test set. This procedure was repeated 500 times to estimate the distributions of the performance metrics. The method showed a mean (SD) SE and SP of 94.4% (3.8) and 97.8% (1.2), respectively. The method is compliant with the American Heart Association requirements.