Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: Comparative Study.

BACKGROUND: To date, performance comparisons between men and machines have been carried out in many health domains. Yet machine learning (ML) models and human performance comparisons in audio-based respiratory diagnosis remain largely unexplored. OBJECTIVE: The primary objective of this study was to compare human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. METHODS: In this study, we compared human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. Prediction performance on 24 audio samples (12 tested positive) made by 36 clinicians with experience in treating COVID-19 or other respiratory illnesses was compared with predictions made by an ML model trained on 1162 samples. Each sample consisted of voice, cough, and breathing sound recordings from 1 subject, and the length of each sample was around 20 seconds. We also investigated whether combining the predictions of the model and human experts could further enhance the performance in terms of both accuracy and confidence. RESULTS: The ML model outperformed the clinicians, yielding a sensitivity of 0.75 and a specificity of 0.83, whereas the best performance achieved by the clinicians was 0.67 in terms of sensitivity and 0.75 in terms of specificity. Integrating the clinicians' and the model's predictions, however, could enhance performance further, achieving a sensitivity of 0.83 and a specificity of 0.92. CONCLUSIONS: Our findings suggest that the clinicians and the ML model could make better clinical decisions via a cooperative approach and achieve higher confidence in audio-based respiratory diagnosis.

Supervised and Self-Supervised Pretraining Based Covid-19 Detection Using Acoustic Breathing/Cough/Speech Signals

A rapid-accurate detection method for COVID-19 is rather important for avoiding its pandemic. In this work, we propose a bi-directional long short-term memory (BiLSTM) network based COVID-19 detection method using breath/speech/cough signals. Three kinds of acoustic signals are taken to train the network and individual models for three tasks are built, respectively, whose parameters are averaged to obtain an average model, which is then used as the initialization for the BiLSTM model training of each task. It is shown that such an initialization method can significantly improve the detection performance on three tasks. This is called supervised pre-training based detection. Besides, we utilize an existing pre-trained wav2vec2.0 model and pre-train it using the DiCOVA dataset, which is utilized to extract a high-level representation as the model input to replace conventional mel-frequency cepstral coefficients (MFCC) features. This is called self-supervised pre-training based detection. To reduce the information redundancy contained in the recorded sounds, silent segment removal, amplitude normalization and time-frequency masking are also considered. The proposed detection model is evaluated on the DiCOVA dataset and results show that our method achieves an area under curve (AUC) score of 88.44% on blind test in the fusion track. It is shown that using high-level features together with MFCC features is helpful for diagnosing accuracy.

COVID-19 Detection Exploiting Self-Supervised Learning Representations of Respiratory Sounds

In this work, we focus on the automatic detection of COVID-19 patients from the analysis of cough, breath, and speech samples. Our goal is to investigate the suitability of Self-Supervised Learning (SSL) representations extracted using Wav2Vec 2.0 for the task at hand. For this, in addition to the SSL representations, the models trained exploit the Low-Level Descriptors (LLD) of the eGeMAPS feature set, and Mel-spectrogram coefficients. The extracted representations are analysed using Convolutional Neural Networks (CNN) reinforced with contextual attention. Our experiments are performed using the data released as part of the Second Diagnosing COVID-19 using Acoustics (DiCOVA) Challenge, and we use the Area Under the Curve (AUC) as the evaluation metric. When using the CNNs without contextual attention, the multi-type model exploiting the SSL Wav2Vec 2.0 representations from the cough, breath, and speech sounds scores the highest AUC, 80.37 %. When reinforcing the embedded representations learnt with contextual attention, the AUC obtained using this same model slightly decreases to 80.01 %. The best performance on the test set is obtained with a multi-type model fusing the embedded representations extracted from the LLDs of the cough, breath, and speech samples and reinforced using contextual attention, scoring an AUC of 81.27 %. © 2022 IEEE.

Considerations and Challenges for Real-World Deployment of an Acoustic-Based COVID-19 Screening System.

Coronavirus disease 2019 (COVID-19) has led to countless deaths and widespread global disruptions. Acoustic-based artificial intelligence (AI) tools could provide a simple, scalable, and prompt method to screen for COVID-19 using easily acquirable physiological sounds. These systems have been demonstrated previously and have shown promise but lack robust analysis of their deployment in real-world settings when faced with diverse recording equipment, noise environments, and test subjects. The primary aim of this work is to begin to understand the impacts of these real-world deployment challenges on the system performance. Using Mel-Frequency Cepstral Coefficients (MFCC) and RelAtive SpecTrAl-Perceptual Linear Prediction (RASTA-PLP) features extracted from cough, speech, and breathing sounds in a crowdsourced dataset, we present a baseline classification system that obtains an average receiver operating characteristic area under the curve (AUC-ROC) of 0.77 when discriminating between COVID-19 and non-COVID subjects. The classifier performance is then evaluated on four additional datasets, resulting in performance variations between 0.64 and 0.87 AUC-ROC, depending on the sound type. By analyzing subsets of the available recordings, it is noted that the system performance degrades with certain recording devices, noise contamination, and with symptom status. Furthermore, performance degrades when a uniform classification threshold from the training data is subsequently used across all datasets. However, the system performance is robust to confounding factors, such as gender, age group, and the presence of other respiratory conditions. Finally, when analyzing multiple speech recordings from the same subjects, the system achieves promising performance with an AUC-ROC of 0.78, though the classification does appear to be impacted by natural speech variations. Overall, the proposed system, and by extension other acoustic-based diagnostic aids in the literature, could provide comparable accuracy to rapid antigen testing but significant deployment challenges need to be understood and addressed prior to clinical use.

Detecting COVID-19 from audio recording of coughs using Random Forests and Support Vector Machines

The detection of COVID-19 is and will remain in the foreseeable future a crucial challenge, making the development of tools for the task important. One possible approach, on the confines of speech and audio processing, is detecting potential COVID-19 cases based on cough sounds. We propose a simple, yet robust method based on the well-known ComParE 2016 feature set, and two classical machine learning models, namely Random Forests, and Support Vector Machines (SVMs). Furthermore, we combine the two methods, by calculating the weighted average of their predictions. Our results in the DiCOVA challenge show that this simple approach leads to a robust solution while producing competitive results. Based on the Area Under the Receiver Operating Characteristic Curve (AUC ROC) score, both classical machine learning methods we applied markedly outperform the baseline provided by the challenge organisers. Moreover, their combination attains an AUC ROC score of 85:21, positioning us at fourth place on the leaderboard (where the second team attained a similar, 85:43 score). Here, we would describe this system in more detail, and analyse the resulting models, drawing conclusions, and determining future work directions.

Recognising Covid-19 from Coughing using Ensembles of SVMs and LSTMs with Handcrafted and Deep Audio Features

As the Covid-19 pandemic continues, digital health solutions can provide valuable insights and assist in diagnosis and prevention. Since the disease affects the respiratory system, it is hypothesised that sound formation is changed, and thus, an infection can be automatically recognised through audio analysis. We present an ensemble learning approach used in our entry to Track 1 of the DiCOVA 2021 Challenge, which aims at binary classification of Covid-19 infection on a crowd-sourced dataset of 1 040 cough sounds. Our system is based on a combination of hand-crafted features for paralinguistics with deep feature extraction from spectrograms using pre-trained CNNs. We extract features both at segment level and with a sliding window approach, and process them with SVMs and LSTMs, respectively. We then perform least-squares weighted late fusion of our classifiers. Our system surpasses the challenge baseline, with a ROC-AUC on the test set of 78.18 %.

DiCOVA Challenge: Dataset, task, and baseline system for COVID-19 diagnosis using acoustics

The DiCOVA challenge aims at accelerating research in diagnosing COVID-19 using acoustics (DiCOVA), a topic at the intersection of speech and audio processing, respiratory health diagnosis, and machine learning. This challenge is an open call for researchers to analyze a dataset of sound recordings, collected from COVID-19 infected and non-COVID-19 individuals, for a two-class classification. These recordings were collected via crowdsourcing from multiple countries, through a website application. The challenge features two tracks, one focusing on cough sounds, and the other on using a collection of breath, sustained vowel phonation, and number counting speech recordings. In this paper, we introduce the challenge and provide a detailed description of the task, and present a baseline system for the task.

THE SECOND DICOVA CHALLENGE: DATASET AND PERFORMANCE ANALYSIS FOR DIAGNOSIS OF COVID-19 USING ACOUSTICS

The Second Diagnosis of COVID-19 using Acoustics (DiCOVA) Challenge aimed at accelerating the research in acoustics based detection of COVID-19, a topic at the intersection of acoustics, signal processing, machine learning, and healthcare. This paper presents the details of the challenge, which was an open call for researchers to analyze a dataset of audio recordings consisting of breathing, cough and speech signals. This data was collected from individuals with and without COVID-19 infection, and the task in the challenge was a two-class classification. The development set audio recordings were collected from 965 (172 COVID-19 positive) individuals, while the evaluation set contained data from 471 individuals (71 COVID-19 positive). The challenge featured four tracks, one associated with each sound category of cough, speech and breathing, and a fourth fusion track. A baseline system was also released to benchmark the participants. In this paper, we present an overview of the challenge, the rationale for the data collection and the baseline system. Further, a performance analysis for the systems submitted by the 21 participating teams in the leaderboard is also presented. © 2022 IEEE

Towards sound based testing of COVID-19-Summary of the first Diagnostics of COVID-19 using Acoustics (DiCOVA) Challenge.

The technology development for point-of-care tests (POCTs) targeting respiratory diseases has witnessed a growing demand in the recent past. Investigating the presence of acoustic biomarkers in modalities such as cough, breathing and speech sounds, and using them for building POCTs can offer fast, contactless and inexpensive testing. In view of this, over the past year, we launched the "Coswara" project to collect cough, breathing and speech sound recordings via worldwide crowdsourcing. With this data, a call for development of diagnostic tools was announced in the Interspeech 2021 as a special session titled "Diagnostics of COVID-19 using Acoustics (DiCOVA) Challenge". The goal was to bring together researchers and practitioners interested in developing acoustics-based COVID-19 POCTs by enabling them to work on the same set of development and test datasets. As part of the challenge, datasets with breathing, cough, and speech sound samples from COVID-19 and non-COVID-19 individuals were released to the participants. The challenge consisted of two tracks. The Track-1 focused only on cough sounds, and participants competed in a leaderboard setting. In Track-2, breathing and speech samples were provided for the participants, without a competitive leaderboard. The challenge attracted 85 plus registrations with 29 final submissions for Track-1. This paper describes the challenge (datasets, tasks, baseline system), and presents a focused summary of the various systems submitted by the participating teams. An analysis of the results from the top four teams showed that a fusion of the scores from these teams yields an area-under-the-receiver operating curve (AUC-ROC) of 95.1% on the blind test data. By summarizing the lessons learned, we foresee the challenge overview in this paper to help accelerate technological development of acoustic-based POCTs.

COVID-19 diagnosis system by deep learning approaches.

The novel coronavirus disease 2019 (COVID-19) has been a severe health issue affecting the respiratory system and spreads very fast from one human to other overall countries. For controlling such disease, limited diagnostics techniques are utilized to identify COVID-19 patients, which are not effective. The above complex circumstances need to detect suspected COVID-19 patients based on routine techniques like chest X-Rays or CT scan analysis immediately through computerized diagnosis systems such as mass detection, segmentation, and classification. In this paper, regional deep learning approaches are used to detect infected areas by the lungs' coronavirus. For mass segmentation of the infected region, a deep Convolutional Neural Network (CNN) is used to identify the specific infected area and classify it into COVID-19 or Non-COVID-19 patients with a full-resolution convolutional network (FrCN). The proposed model is experimented with based on detection, segmentation, and classification using a trained and tested COVID-19 patient dataset. The evaluation results are generated using a fourfold cross-validation test with several technical terms such as Sensitivity, Specificity, Jaccard (Jac.), Dice (F1-score), Matthews correlation coefficient (MCC), Overall accuracy, etc. The comparative performance of classification accuracy is evaluated on both with and without mass segmentation validated test dataset.