Gastroesophageal reflux disease (GERD) is a common digestive disorder with troublesome symptoms that has been affected millions of people worldwide. Multichannel Intraluminal Impedance–pH (MII–pH) monitoring is a recently developed technique, which is currently considered as the gold standard for the diagnosis of GERD. In this paper, we address the problem of characterizing gastroesophageal reflux events in MII signals. A GER detection algorithm has been developed based on the sparse representation of local segments. Two dictionaries are trained using the online dictionary learning approach from the distal impedance data of selected patches of GER and no specific patterns intervals. A classifier is then designed based on the ${\ell _{\boldsymbol{p}}}$ –norm of dictionary approximations. Next, a preliminary permutation mask is obtained from the classification results of patches, which is then used in post–processing procedure to investigate the exact timings of GERs at all impedance sites. Our algorithm was tested on 33 MII episodes, resulting a sensitivity of 96.97% and a positive predictive value of 94.12%.

中文翻译：

---

基于稀疏表示的多通道腔内阻抗胃食管反流表征算法


胃食管反流病（GERD）是一种常见的消化系统疾病，具有令人烦恼的症状，已经影响了全世界数百万人。多通道腔内阻抗-pH (MII-pH) 监测是一项最近开发的技术，目前被认为是诊断GERD 的金标准。在本文中，我们解决了在 MII 信号中表征胃食管反流事件的问题。基于局部片段的稀疏表示，开发了一种 GER 检测算法。使用在线词典学习方法从选定的 GER 斑块的远端阻抗数据训练两个词典，没有特定的模式间隔。然后根据字典近似的 ${\ell _{\boldsymbol{p}}}$ 范数设计分类器。接下来，从补丁的分类结果中获得初步的排列掩模，然后将其用于后处理过程中以研究所有阻抗位点的 GER 的准确时序。我们的算法在 33 个 MII 事件上进行了测试，结果灵敏度为 96.97%，阳性预测值为 94.12%。