Chen Cheng, Zhan Li, Pan Xiaoxin, Wang Zhiliang, Guo Xiaoyu, Qin Handai, Xiong Fen, Shi Wei, Shi Min, Ji Fei, Wang Qiuju, Yu Ning, Xiao Ruoxiu
School of Computer and Communication Engineering, University of Science & Technology Beijing, Beijing, China.
College of Otolaryngology Head and Neck Surgery, National Clinical Research Center for Otolaryngologic Diseases, Key Lab of Hearing Science, Ministry of Education, Beijing Key Lab of Hearing Impairment for Prevention and Treatment, Chinese PLA General Hospital, Beijing, China.
Front Med (Lausanne). 2021 Jan 11;7:613708. doi: 10.3389/fmed.2020.613708. eCollection 2020.
Auditory brainstem response (ABR) testing is an invasive electrophysiological auditory function test. Its waveforms and threshold can reflect auditory functional changes in the auditory centers in the brainstem and are widely used in the clinic to diagnose dysfunction in hearing. However, identifying its waveforms and threshold is mainly dependent on manual recognition by experimental persons, which could be primarily influenced by individual experiences. This is also a heavy job in clinical practice. In this work, human ABR was recorded. First, binarization is created to mark 1,024 sampling points accordingly. The selected characteristic area of ABR data is 0-8 ms. The marking area is enlarged to expand feature information and reduce marking error. Second, a bidirectional long short-term memory (BiLSTM) network structure is established to improve relevance of sampling points, and an ABR sampling point classifier is obtained by training. Finally, mark points are obtained through thresholding. The specific structure, related parameters, recognition effect, and noise resistance of the network were explored in 614 sets of ABR clinical data. The results show that the average detection time for each data was 0.05 s, and recognition accuracy reached 92.91%. The study proposed an automatic recognition of ABR waveforms by using the BiLSTM-based machine learning technique. The results demonstrated that the proposed methods could reduce recording time and help doctors in making diagnosis, suggesting that the proposed method has the potential to be used in the clinic in the future.
听性脑干反应（ABR）测试是一种侵入性的电生理听觉功能测试。其波形和阈值能够反映脑干听觉中枢的听觉功能变化，在临床上被广泛用于诊断听力功能障碍。然而，识别其波形和阈值主要依赖实验人员的人工识别，这可能主要受个人经验影响。这在临床实践中也是一项繁重的工作。在这项工作中，记录了人类ABR。首先，进行二值化处理，相应地标记1024个采样点。ABR数据的选定特征区域为0 - 8毫秒。扩大标记区域以扩展特征信息并减少标记误差。其次，建立双向长短期记忆（BiLSTM）网络结构以提高采样点的相关性，并通过训练获得ABR采样点分类器。最后，通过阈值处理获得标记点。在614组ABR临床数据中探索了该网络的具体结构、相关参数、识别效果和抗噪声能力。结果表明，每组数据的平均检测时间为0.05秒，识别准确率达到92.91%。该研究提出了一种基于BiLSTM机器学习技术的ABR波形自动识别方法。结果表明，所提出的方法可以减少记录时间并帮助医生进行诊断，表明该方法未来有可能在临床上得到应用。
