Diagnosis of COVID-19 and non-COVID-19 patients by classifying only a single cough sound

Abstract

In the last month of 2019, a new virus emerged in China, spreading rapidly and affecting the whole world. This virus, which is called corona, is the most contagious type of virus that humanity has ever encountered. The virus has caused a huge crisis worldwide as it leads to severe infections and eventually death in humans. On March 11, 2020, it was announced by the World Health Organization that a COVID-19 outbreak has occurred. Computer-aided digital technologies, which eliminate many problems and provide convenience in people's lives, did not leave humanity alone in this regard and rushed to provide a solution for this unfortunate event. One of the important aspects in which computer-aided digital technologies can be effective is the diagnosis of the disease. Reverse transcription-polymerase chain reaction (RT-PCR), which is a standard and precise technique for diagnosing the disease, is an expensive and time-consuming method. Moreover, its availability is not the same all over the world. For this reason, it can be very attractive and important to distinguish the COVID-19 disease from a cold or flu through a cough sound analysis via smartphones which have entered into the lives of many people in recent years. In this study, we proposed a machine learning-based system to distinguish patients with COVID-19 from non-COVID-19 patients by analyzing only a single cough sound. Two different data sets were used, one accessible for the public and the other available on request. After combining the data sets, the features were obtained from the cough sounds using the mel-frequency cepstral coefficients (MFCCs) method, and then, they were classified with seven different machine learning classifiers. To determine the optimum values of hyperparameters for MFCCs and classifiers, the leave-one-out cross-validation (LOO-CV) strategy was implemented. Based on the results, the k-nearest neighbors classifier based on the Euclidean distance (kNN Euclidean) with the accuracy rate, sensitivity of COVID-19, sensitivity of non-COVID-19, F-measure, and area under the ROC curve (AUC) of 0.9833, 1.0000, 0.9720, 0.9799, and 0.9860, respectively, is more successful than other classifiers. Finally, the best and most effective features were determined for each classifier using the sequential forward selection (SFS) method. According to the results, the proposed system is excellent compared with similar studies in the literature and can be easily used in smartphones and facilitate the diagnosis of COVID-19 patients. In addition, since the used data set includes reflex and unconscious coughs, the results showed that conscious or unconscious coughing has no effect on the diagnosis of COVID-19 patients based on the cough sound.Keywords Cough sound Á Classification Á Machine learning Á COVID-19 Á Coronavirus Á Computer-aided digital technologies This paper is dedicated to the memory of the late Dr. Mohsen MALEKI, who passed away from COVID-19 in November 2020.

Smart technologies for COVID-19 indoor monitoring

“…However, our future plan is to focus on adoption of embedded artificial intelligence for indoor monitoring, especially in light of new generation AI-enabled embedded hardware, such as Arduino Nano 33 BLE Sense. m These new models of small-size microcontrollers are compatible with lightweight machine learning frameworks, such as TinyML and TensorFlow Lite n ( Warden & Situnayake, 2019 ), opening new horizons of innovative usage scenarios relevant to coronavirus pandemic leveraging other environment data sources than images (which is one of the main topics covered in this chapter), such as cough classification ( Bansal, Pahwa, & Kannan, 2020 ; Melek, 2021 , Pahar, Klopper, Warren, & Niesler, 2021 ).…”

The Use of Audio Signals for Detecting COVID-19: A Systematic Review

“…The evaluation was performed with a leave-one-out cross-validation technique. Melek [ 71 ] employed a slightly larger but still small dataset and used a Euclidean k-NN classifier with leave-one-out cross-validation to determine the hyperparameters for feature extraction and evaluate their proposed method. In the case of the k-NN classifier, feature selection using a sequential forward search technique did not improve the results.…”

Clinically Relevant Sound-Based Features in COVID-19 Identification: Robustness Assessment With a Data-Centric Machine Learning Pipeline

“…Melek [18] implemented an ML-based system to detect COVID-19 patients based on a single cough sound. The data includes recordings from Virufy and NoCoCoDa datasets, comprising a total of 107 COVID-19 positive and 73 negative participants.…”