Multi-Modal Point-of-Care Diagnostics for COVID-19 Based on Acoustics and Symptoms

Abstract

Background: The COVID-19 pandemic has highlighted the need to invent alternative respiratory health diagnosis methodologies which provide improvement with respect to time, cost, physical distancing and detection performance. In this context, identifying acoustic bio-markers of respiratory diseases has received renewed interest. Objective: In this paper, we aim to design COVID-19 diagnostics based on analyzing the acoustics and symptoms data. Towards this, the data is composed of cough, breathing, and speech signals, and health symptoms record, collected using a web-application over a period of twenty months. Methods: We investigate the use of time-frequency features for acoustic signals and binary features for encoding different health symptoms. We experiment with use of classifiers like logistic regression, support vector machines and long-short term memory (LSTM) network models on the acoustic data, while decision tree models are proposed for the symptoms data. Results: We show that a multi-modal integration of inference from different acoustic signal categories and symptoms achieves an area-under-curve (AUC) of 96.3%, a statistically significant improvement when compared against any individual modality (p < 0.05). Experimentation with different feature representations suggests that the mel-spectrogram acoustic features performs relatively better across the three kinds of acoustic signals. Further, a score analysis with data recorded from newer SARS-CoV-2 variants highlights the generalization ability of the proposed diagnostic approach for COVID-19 detection. Conclusion: The proposed method shows a promising direction for COVID-19 detection using a multi-modal dataset, while generalizing to new COVID variants.

A Framework on Combining the Symptoms With Dissimilar Features to Predict Multiple Diseases Using Machine Learning Algorithms

“…Among these algorithms, Random Tree and Naïve Bayes demonstrated the most successful performance in predicting CVD. Chetupalli, S. R. et al [15], introduced a prediction model for COVID-19 based on acoustic signals and patient symptoms, employing different algorithms. The model utilizes breathing audio, speech audio, and cough audio as inputs for logistic regression and support vector machine (SVM) algorithms to generate results.…”

Acoustic and Text Features Analysis for Adult ADHD Screening: A Data-Driven Approach Utilizing DIVA Interview

“…In contrast to most chronic conditions diagnosed through lab tests, mental disorders rely on self-disclosure through specialized methods, highlighting the intricate nature of mental health data. In the past decades, machine learning (ML) and deep learning (DL) have provided a new paradigm for gaining knowledge from complex data [10] , [11] and numerous ML and DL-based techniques have been developed for healthcare applications including mental healthcare and achieved considerable success [12] , [13] , [14] , [15] , [16] . Specifically, studies are using adjunctive data for the detection of ADHD, including magnetic resonance imaging (MRI) [17] , electroencephalography (EEG) [18] and electrocardiograms (ECG) [19] .…”

COVID-19 Detection from Cough Sounds Using XGBoost and LSTM Networks

“…A classification was made between a dry cough and wet cough by applying some modern and traditional machine learning methods to the COUGHVID database, where it has been shown that the decision tree models are superior to the rest of the models in terms of overall performance [15]. Based on logistic regression and support vector machines for acoustic data, and decision tree models for symptoms data, the researchers [16] proposed a multi-modal diagnostic for COVID-19. Using Coswara dataset, an AUC of 0.92 has been reached.…”