This article is a Preprint
Preprints are preliminary research reports that have not been certified by peer review. They should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Preprints posted online allow authors to receive rapid feedback and the entire scientific community can appraise the work for themselves and respond appropriately. Those comments are posted alongside the preprints for anyone to read them and serve as a post publication assessment.
Screening COVID-19 by Swaasa AI Platform using cough sounds: A cross-sectional study
Preprint
in English
| medRxiv
| ID: ppmedrxiv-22281821
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 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.
cc_by_nd
Full text:
Available
Collection:
Preprints
Database:
medRxiv
Type of study:
Diagnostic study
/
Observational study
/
Prognostic study
/
Rct
Language:
English
Year:
2022
Document type:
Preprint