2nd Floor Education and Research Centre, University Hospital South Manchester, The University of Manchester, Southmoor Road, Manchester, M23 9LT, UK.
Expert Rev Respir Med. 2010 Oct;4(5):673-83. doi: 10.1586/ers.10.63.
Coughing produces a characteristic sound that is readily recognized by the human ear and provides the opportunity to objectively quantify coughing through acoustic recordings. The development of digital recording technologies has facilitated such recordings over the extended time periods needed to capture symptom episodes. However, the manual counting of coughs by listening to long recordings is time-consuming, laborious and restricts usage to research studies. This article outlines the challenges in recording, analyzing and quantifying cough sounds and describes the systems under development. Progress is being made towards automated algorithms to identify and count cough sounds; however, current systems have only been tested over short time periods and in limited patient groups. Further work is required to achieve broadly applicable accurate cough monitoring systems.
咳嗽会产生一种特征性的声音，人耳很容易识别，这为通过声学记录客观量化咳嗽提供了机会。数字录音技术的发展使得在需要捕捉症状发作的较长时间段内进行此类录音变得更加容易。然而，通过长时间的录音来手动计数咳嗽既耗时费力，又限制了其在研究中的使用。本文概述了在记录、分析和量化咳嗽声音方面所面临的挑战，并描述了正在开发的系统。目前已经开发出用于识别和计数咳嗽声音的自动化算法，但这些系统仅在短时间内和有限的患者群体中进行了测试。要实现广泛适用且准确的咳嗽监测系统，还需要进一步的工作。
