Supplementary Material for: Continuous Sound Collection Using Smartphones and Machine Learning to Measure Cough

<b><i>Background:</i></b> Despite the efforts of research groups to develop and implement at least partial automation, cough counting remains impractical. Analysis of 24-h cough frequency is an established regulatory endpoint which, if addressed in an automated manner, has the potential to ease cough symptom evaluation over multiple 24-h periods in a patient-centric way, supporting the development of novel treatments for chronic cough, an unmet clinical need. <b><i>Objectives:</i></b> In light of recent technological advancements, we propose a system based on the use of smartphones for objective continuous sound collection, suitable for automated cough detection and analysis. Two capabilities were identified as necessary for naturalistic cough assessment: (1) recording sound in a continuous manner (sound collection), and (2) detection of coughs from the recorded sound (cough detection). <b><i>Methods:</i></b> This work did not involve any human subject testing or trials. For sound collection, we designed, built, and verified technical parameters of a smartphone application for sound collection. Our cough detection work describes the development of a mathematical model for sound analysis and cough identification. Performance of the model was compared to previously published results of commercially available solutions and to human raters. The compared solutions use the following methods to automatically or semi-automatically assess cough: 24-h sound recording with an ambulatory device with multiple microphones, automatic silence removal, and manual recording review for cough count. <b><i>Results:</i></b> Sound collection: the application demonstrated the ability to continuously record sounds using the phone’s internal microphone; the technical verification informed the configuration of the technical and user experience parameters. Cough detection: our cough recognition sensitivity to cough as determined by human listeners was 90 at 99.5% specificity preset and 75 at 99.9% specificity preset for a dataset created from publicly available data. <b><i>Conclusions:</i></b> Sound collection: the application reliably collects sound data and uploads them securely to a remote server for subsequent analysis; the developed sound data collection application is a critical first step toward future incorporation in clinical trials. Cough detection: initial experiments with cough detection techniques yielded encouraging results for application to patient-collected data from future studies.<b><i>背景：</i></b> 尽管多个研究团队已致力于开发并落地至少部分自动化方案，但咳嗽计数仍难以实际应用。24小时咳嗽频率（24-h cough frequency）分析是一项成熟的监管终点指标（regulatory endpoint），若能以自动化方式实现该指标的测算，便可依托以患者为中心的模式，在多个24小时周期内简化咳嗽症状评估，从而助力慢性咳嗽（chronic cough）新型治疗手段的开发——而慢性咳嗽正是一项尚未被满足的临床需求。 <b><i>研究目标：</i></b> 鉴于近年来的技术进步，我们提出一种基于智能手机的客观连续声音采集系统，可用于自动化咳嗽检测（cough detection）与分析。针对自然场景下的咳嗽评估，我们明确了两项必备功能：(1) 持续录制声音（sound collection）；(2) 从录制的音频中检测咳嗽事件（cough detection）。 <b><i>研究方法：</i></b> 本研究未涉及任何人体受试者测试或临床试验。在声音采集（sound collection）环节，我们设计、开发并验证了一款用于声音采集的智能手机应用程序的技术参数。咳嗽检测部分则阐述了用于声音分析与咳嗽识别的数学模型的开发流程。我们将该模型的性能与已发表的商用解决方案，以及人工评分者的结果进行了对比。上述对比方案采用以下方式实现咳嗽的自动或半自动评估：使用搭载多麦克风的可穿戴动态监测设备（ambulatory device）进行24小时音频录制、自动去除静音片段，以及人工审阅录制音频以统计咳嗽次数。 <b><i>研究结果：</i></b> 声音采集：该应用程序可通过手机内置麦克风持续录制声音，技术验证工作为技术参数与用户体验参数的配置提供了依据。咳嗽检测：基于公开数据集开展的测试显示，在预设特异性（specificity）为99.5%的情况下，我们的咳嗽识别模型对人工标注咳嗽的敏感度（sensitivity）为90；在预设特异性为99.9%的情况下，敏感度为75。 <b><i>研究结论：</i></b> 声音采集：该应用程序可稳定采集声音数据，并将数据安全上传至远程服务器以供后续分析；本次开发的声音采集应用程序是未来将其纳入临床试验的关键第一步。咳嗽检测：针对咳嗽检测技术的初步实验结果令人振奋，为将其应用于未来研究中的患者采集数据奠定了基础。