Sci Data June 2023 PMID 37349364

Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection.

Debarpan Bhattacharya, Neeraj Kumar Sharma, Debottam Dutta, Srikanth Raj Chetupalli, Pravin Mote, Sriram Ganapathy, C Chandrakiran, Sahiti Nori, K K Suhail, Sadhana Gonuguntla, Murali Alagesan

Full text PDF Download social card

Mentions

Peak: 3 in Jun 2023

across 2 sources since May 2023

Extended reach

9,586

potential audience

Total likes

Video views

Mentions per month

May 2023 – Sep 2023

Where it's discussed

X / Twitter4 posts
YouTube1 videos

AI synopsis

What people are saying

The overall tone reflects cautious interest, highlighted by mentions of the dataset's relevance to ongoing health issues like long COVID, with phrases like 'potential of the dataset' and references to related broad studies, which demonstrate a general acknowledgment of its importance but without strong enthusiasm or critique.

AgreementNeither agree nor disagree

The discussions show a moderate level of agreement, with some appreciation for the dataset's potential but also references to related broader studies, indicating cautious support.

InterestModerate interest

The interest level is modest; posts mention the publication and its focus but do not delve deeply into technical details or implications.

EngagementNeutral engagement

Engagement appears neutral; discussions include mentions of the dataset and related topics like long COVID, but lack detailed analysis or critique.

ImpactModerate impact

The perceived impact is moderate, with some recognition of the dataset's utility for remote screening, yet it seems to be viewed as part of ongoing research rather than a transformative breakthrough.

Abstract in brief

The Coswara dataset includes respiratory sounds (like breathing, coughs, and speech) and detailed metadata from over 2600 individuals collected between April 2020 and February 2022, with data on COVID-19 status, demographics, and health history.
The dataset was manually annotated for audio quality, totaling 65 hours of recordings, to ensure reliability, and a COVID-19 detection model using a bidirectional LSTM architecture was trained and tested across different demographic groups to analyze bias and fairness.
The study provides insights into how factors like gender, location, recording date, and language influence the accuracy of COVID-19 detection from respiratory sounds, highlighting considerations for remote screening tools.

Read the full abstract

All mentions

Respiratory Sounds Dataset for Remote SARS-CoV-2 Screening

The Coswara dataset includes respiratory sounds and metadata from over 2600 individuals, used to develop a COVID-19 detection model. The study analyzes factors affecting detection accuracy, enhancing remote screening…

STEM RTCL TV · Sep 19, 2023 23 views

Stigmabase | UNITWO

@StigmabaseU · X

Jun 23, 2023 · 2,576 followers View post →

oldfshndanne

@oldfshndanne · X

RT @LongCovidPapers: Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection #LongCovid #pwLC https…

Jun 23, 2023 · 1 share · 4,290 followers View post →

LongCovidPapers

@LongCovidPapers · X

Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection #LongCovid #pwLC https://t.co/mryYngrYUZ

Jun 23, 2023 · 1 like · 1 share · 2,146 followers View post →

Semisance

@semisance · X

Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection https://t.co/LfiLgQ7T3c https://t.co/AGIMTo20GK

May 23, 2023 · 548 followers View post →