Artificial intelligence enabled preliminary diagnosis for COVID-19 from voice cues and questionnaires

Abstract

The COVID-19 outbreak was announced as a global pandemic by the World Health Organization in March 2020 and has affected a growing number of people in the past few months. In this context, advanced artificial intelligence techniques are brought to the forefront as a response to the ongoing fight toward reducing the impact of this global health crisis. In this study, potential use-cases of intelligent speech analysis for COVID-19 identification are being developed. By analyzing speech recordings from COVID-19 positive and negative patients, we constructed audio- and symptomatic-based models to automatically categorize the health state of patients, whether they are COVID-19 positive or not. For this purpose, many acoustic features were established, and various machine learning algorithms are being utilized. Experiments show that an average accuracy of 80% was obtained estimating COVID-19 positive or negative, derived from multiple cough and vowel /a/ recordings, and an average accuracy of 83% was obtained estimating COVID-19 positive or negative patients by evaluating six symptomatic questions. We hope that this study can foster an extremely fast, low-cost, and convenient way to automatically detect the COVID-19 disease.

Knowledge graph analysis and visualization of AI technology applied in COVID-19

“…AI4COVID-19 app records for 2-s coughs of the subject and then analyzes the cough sample by AI running in the cloud, and the preliminary diagnostic result will be returned in 1 min (Imran et al 2020). COVID-19 identification method based on intelligent speech analysis is being developed (Shimon et al 2021), which can automatically classify the health status of patients by an audio and symptom model.…”

Machine Learning-based Voice Assessment for the Detection of Positive and Recovered COVID-19 Patients

“…On the other hand, RASTA is sensitive to eventual other background voices, which we were very careful not to include in our recordings. Pinkas [51] and Shimon [52] also obtained encouraging results through their preliminary analyses on proper speech tasks (vowel /a/, counting from 50 to 80). However, data was gathered from smaller populations of positive COVID-19 subjects and their analyses yielded lower AUC and accuracy values.…”

“…Pre-COVID-19 ML studies demonstrated the relevance of cough samples for detecting multiple respiratory conditions [86,87]. However, it is conceivable that proper speech tasks may provide additional valuable features for MLVA, potentially even more representative of the multifaceted interactions between phonatory subsystems [36,52] and their impairment in COVID-19 [53][54][55]57]. Indeed, the vowel task proved higher accuracy and AUC values than cough when discriminating between groups P and H and between groups P and R, demonstrating lower performances only when discriminating between groups R and H, thus confirming that speech tasks may have at least similar informative contents.…”

“…Thirdly, to the best of our knowledge, only two studies included vocal samples other than cough in the analyses [50,51]. Specifically, in our opinion, proper speech tasks could provide valuable additional features for MLVA implementation, in reason of the complex interactions between voice-production subsystems [36,52] and their peculiar impairments in COVID-19 [53][54][55]57]. Lastly, no ML study enrolled recovered COVID-19 patients to date, even though they may represent a crucial population for multiple reasons, including potential residual viral spreading [58][59][60] and severe long-term disabilities [61][62][63].…”

Do you have COVID-19? An artificial intelligence-based screening tool for COVID-19 using acoustic parameters

“… Biswas et al (2020) used cough and vowel /a/ samples to investigate the possibility of using intelligent speech analysis to identify COVID-19 in individuals with and without the coronavirus. Shimon et al (2021) used cough and vowel /a/ samples to investigate the possibility of using intelligent speech analysis for the identification of COVID-19 in individuals with and without the coronavirus. They developed audio-symptomatic models to automatically discriminate between COVID-19 patients and healthy individuals and reported an average of 80% accuracy in detecting the disease based on analyzing coughs and the vowel and 83% accuracy based on the symptomatic questions.…”