Smartphone-Based Self-Testing of COVID-19 Using Breathing Sounds.

Area of Science:

• Medical Informatics
• Respiratory Medicine
• Artificial Intelligence

Background:

• The COVID-19 pandemic necessitates innovative diagnostic tools beyond traditional methods.
• Current COVID-19 testing requires healthcare facility visits, posing risks during self-quarantine.
• Smartphones offer a platform for developing accessible e-health solutions.

Purpose of the Study:

• To explore the potential of using smartphone microphones to analyze breathing sounds for COVID-19 detection.
• To investigate if distinct acoustic patterns in breathing sounds correlate with COVID-19 infection.
• To propose a telemedicine-based self-testing approach for respiratory health monitoring.

Main Methods:

• Utilizing smartphone microphones to capture respiratory data.
• Applying advanced signal processing and machine learning algorithms for data analysis.
• Classifying breathing sounds to differentiate between healthy and unhealthy respiratory states.

Main Results:

• Breathing sounds may contain unique acoustic signatures indicative of COVID-19.
• Analysis of breathing sounds can aid in assessing lung function and oxygenation.
• Machine learning can effectively classify respiratory data from breathing sounds.

Conclusions:

• Smartphone-based breathing sound analysis is a promising telemedicine strategy for COVID-19.
• This approach could lead to personalized, self-administered testing apps.
• Continuous monitoring of breathing patterns can aid in managing respiratory health during pandemics.