logo
ResearchBunny Logo
Screening COVID-19 by Swaasa AI platform using cough sounds: a cross-sectional study

Medicine and Health

Screening COVID-19 by Swaasa AI platform using cough sounds: a cross-sectional study

P. Pentakota, G. Rudraraju, et al.

Discover the innovative Swaasa AI platform that utilizes cough sounds and symptoms for COVID-19 screening. Achieving a remarkable 75.54% accuracy with high sensitivity and specificity, this cost-effective tool offers valuable remote monitoring for preliminary assessment. Developed by a team of experts including Padmalatha Pentakota, Gowrisree Rudraraju, and more.

00:00
00:00
Playback language: English
Abstract
This study introduces and validates the Swaasa AI platform, which uses cough sounds and symptoms to screen for COVID-19. The platform, employing a combined Convolutional Neural Network (CNN) and Feedforward Artificial Neural Network (FFANN) model, achieved a 75.54% accuracy rate in detecting COVID-19 during clinical validation, with 95.45% sensitivity and 73.46% specificity. Pilot testing showed a Positive Predictive Value of 70.73%. The Swaasa platform offers a cost-effective and remote monitoring tool for preliminary COVID-19 screening.
Publisher
Scientific Reports
Published On
Oct 16, 2023
Authors
Padmalatha Pentakota, Gowrisree Rudraraju, Narayana Rao Sripada, Baswaraj Mamidgi, Charishma Gottipulla, Charan Jalukuru, Shubha Deepti Palreddy, Nikhil Kumar Reddy Bhoge, Priyanka Firmal, Venkat Yechuri, Manmohan Jain, Venkata Sudhakar Peddireddi, Devi Madhavi Bhimarasetty, S Sreenivas, Kesava Lakshmi, Niranjan Joshi, Shibu Vijayan, Sanchit Turaga, Vardhan Avasarala
Tags
Swaasa AI
COVID-19 screening
cough sounds
Convolutional Neural Network
remote monitoring
clinical validation
cost-effective
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny