AI Evaluation of COVID-19 Sounds (AI-EChOS)

Sponsor

IRCCS San Raffaele (Other)

Overall Status

Recruiting

CT.gov ID

NCT05115097

Collaborator

(none)

100

Enrollment

Location

14.4

Anticipated Duration (Months)

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

In this study the investigators record sounds of voice, breaths and cough of subjects who tested positive for COVID19. The investigators then feed these sounds into an artificial intelligence and see if it can learn to recognise features to make COVID19 diagnosis from these sounds in order to avoid to use swabs to test the general population.

Condition or Disease	Intervention/Treatment	Phase
COVID-19 COVID-19 Respiratory Infection Cough Breathing Sound Breathing, Mouth

Study Design

Study Type:

Observational

Anticipated Enrollment :

100 participants

Observational Model:

Cohort

Time Perspective:

Prospective

Official Title:

AI Evaluation of COVID-19 Sounds

Actual Study Start Date :

Sep 20, 2021

Anticipated Primary Completion Date :

Sep 1, 2022

Anticipated Study Completion Date :

Dec 1, 2022

Outcome Measures

Primary Outcome Measures

Accuracy evaluation [September 2022-December 2022]
The investigators will evaluate the accuracy of the ML algorithm in terms of sensitivity and specificity and ROC-AUC

Eligibility Criteria

Criteria

Ages Eligible for Study:

18 Years and Older

Sexes Eligible for Study:

All

Accepts Healthy Volunteers:

Yes

Inclusion Criteria:

Adults who tested positive for SARS-CoV-2 currently admitted to hospital at the study site
Adults who tested negative for SARS-CoV-2 and are admitted for any respiratory condition (eg COPD or asthma flare-up, pneumonia..)
Healthy volunteers

Exclusion Criteria:

Patients under the age of 18.
Patients unable to read in Italian.
Patients unable to give informed consent to participate.
Patients requiring life support (including, but not limited to, mechanical cardiac support, ventilation, etc.)
Patients who are pregnant