Furman Gregory, Furman Evgeny, Charushin Artem, Eirikh Ekaterina, Malinin Sergey, Sheludko Valery, Sokolovsky Vladimir, Shtivelman David
Physics Department, Ben-Gurion University of the Negev, Beer-Sheva, Israel.
Department of Pediatric, EA Vagner Perm State Medical University, Perm, Russian Federation.
JMIR Form Res. 2022 Jul 19;6(7):e31200. doi: 10.2196/31200.
Respiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate characteristic sound changes caused by COVID-19 and can be used for diagnostics of this illness.
The aim of the study is to develop 2 fast, remote computer-assisted diagnostic methods for specific acoustic phenomena associated with COVID-19 based on analysis of respiratory sounds.
Fast Fourier transform (FFT) was applied for computer analysis of respiratory sound recordings produced by hospital doctors near the mouths of 14 patients with COVID-19 (aged 18-80 years) and 17 healthy volunteers (aged 5-48 years). Recordings for 30 patients and 26 healthy persons (aged 11-67 years, 34, 60%, women), who agreed to be tested at home, were made by the individuals themselves using a mobile telephone; the records were passed for analysis using WhatsApp. For hospitalized patients, the illness was diagnosed using a set of medical methods; for outpatients, polymerase chain reaction (PCR) was used. The sampling rate of the recordings was from 44 to 96 kHz. Unlike usual computer-assisted diagnostic methods for illnesses based on respiratory sound analysis, we proposed to test the high-frequency part of the FFT spectrum (2000-6000 Hz).
Comparing the FFT spectra of the respiratory sounds of patients and volunteers, we developed 2 computer-assisted methods of COVID-19 diagnostics and determined numerical healthy-ill criteria. These criteria were independent of gender and age of the tested person.
The 2 proposed computer-assisted diagnostic methods, based on the analysis of the respiratory sound FFT spectra of patients and volunteers, allow one to automatically diagnose specific acoustic phenomena associated with COVID-19 with sufficiently high diagnostic values. These methods can be applied to develop noninvasive screening self-testing kits for COVID-19.
呼吸音已被视为行为和健康的一种可能指标。对这些声音进行计算机分析可显示由新冠病毒引起的特征性声音变化，并可用于该疾病的诊断。
本研究的目的是基于呼吸音分析，开发两种针对与新冠病毒相关的特定声学现象的快速、远程计算机辅助诊断方法。
应用快速傅里叶变换（FFT）对14名新冠病毒患者（年龄18 - 80岁）和17名健康志愿者（年龄5 - 48岁）在靠近嘴巴处由医院医生采集的呼吸音记录进行计算机分析。30名患者和26名健康人（年龄11 - 67岁，34人，60%为女性）同意在家中进行检测，他们使用移动电话自行录制声音；记录通过WhatsApp发送用于分析。对于住院患者，采用一套医学方法进行疾病诊断；对于门诊患者，使用聚合酶链反应（PCR）。录音的采样率为44至96千赫兹。与基于呼吸音分析的常规疾病计算机辅助诊断方法不同，我们提议测试FFT频谱的高频部分（2000 - 6000赫兹）。
通过比较患者和志愿者呼吸音的FFT频谱，我们开发了两种新冠病毒诊断的计算机辅助方法，并确定了数值化的健康 - 患病标准。这些标准与被检测者的性别和年龄无关。
所提出的两种计算机辅助诊断方法，基于对患者和志愿者呼吸音FFT频谱的分析，能够以足够高的诊断价值自动诊断与新冠病毒相关的特定声学现象。这些方法可用于开发新冠病毒的无创筛查自检试剂盒。
