ABSTRACT
The Advent of Artificial Intelligence (AI) has led to the use of auditory data for detecting various diseases, including COVID-19. SARS-CoV-2 infection has claimed more than six million lives to date and therefore, needs a robust screening technique to control the disease spread. In the present study we created and validated the Swaasa AI platform, which uses the signature cough sound and symptoms presented by patients to screen and prioritize COVID-19 patients. We collected cough data from 234 COVID-19 suspects to validate our Convolutional Neural Network (CNN) architecture and Feedforward Artificial Neural Network (FFANN) (tabular features) based algorithm. The final output from both models was combined to predict the likelihood of having the disease. During the clinical validation phase, our model showed a 75.54% accuracy rate in detecting the likely presence of COVID-19, with 95.45% sensitivity and 73.46% specificity. We conducted pilot testing on 183 presumptive COVID subjects, of which 58 were truly COVID-19 positive, resulting in a Positive Predictive Value of 70.73%. Due to the high cost and technical expertise required for currently available rapid screening methods, there is a need for a cost-effective and remote monitoring tool that can serve as a preliminary screening method for potential COVID-19 subjects. Therefore, Swaasa would be highly beneficial in detecting the disease and could have a significant impact in reducing its spread.
Subject(s)
COVID-19ABSTRACT
The Advent of Artificial Intelligence (AI) has led to the use of auditory data for detecting various diseases, including COVID-19. SARS-CoV-2 infection has claimed more than 6 million lives till date and hence, needs a robust screening technique to control the disease spread. In the present study we developed and validated the Swaasa AI platform for screening and prioritizing COVID-19 patients based on the signature cough sound and the symptoms presented by the subjects. The cough data records collected from 234 COVID-19 suspects were subjected to validate the convolutional neural network (CNN) architecture and tabular features-based algorithm. The likelihood of the disease was predicted by combining the final output obtained from both the models. In the clinical validation phase, Swaasa was found to be 75.54% accurate in detecting the likely presence of COVID-19 with 95.45% sensitivity and 73.46% specificity. The pilot testing of Swaasa was carried out on 183 presumptive COVID subjects, out of which 82 subjects were found to be positive for the disease by Swaasa. Among them, 58 subjects were truly COVID-19 positive, which corresponds to a Positive Predictive Value of 70.73%. The currently available rapid screening methods are very costly and require technical expertise, therefore a cost effective, remote monitoring tool would be very beneficial for preliminary screening of the potential COVID-19 subject.