Breathing, Mouth, Breathing Sound, Cough, COVID-19, COVID-19 Respiratory Infection
Conditions
Keywords
COVID-19, artificial intelligence, machine learning, sound, cough, breath, voice, diagnosis, automation, AI, ML, pneumonia, symptoms, airways, SARS-CoV-2
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.
Interventions
None listed
Sponsors
IRCCS San Raffaele
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
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
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| 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 |
Countries
Italy
Contacts
Primary ContactMarco Montagna, Medicine
Outcome results
None listed