Transforming Cheap Spirometers to Estimate Flow-Volume Graph By Deep Learning

Reference #: 01526

The University of South Carolina is offering licensing opportunities for Transforming Cheap Spirometers to Estimate Flow-Volume Graph By Deep Learning

Background:

Respiratory diseases, like Asthma, COPD, have been a significant public health challenge over decades, and the recent COVID-19 pandemic has worsened the situation. Portable, home-use spirometers are effective in continuous monitoring of respiratory syndromes out-of-clinic.

Invention Description: 

The technology designs a deep residual decoder network for curve learning then takes key indicators as the input and generates a complete flow-volume graph as the output.

Potential Applications:

We believe the invention can be a solution to extend the capability of at home spirometers for finer-grained, long-term lung function monitoring in the post-COVID era.

Advantages and Benefits:

Existing systems are either costly or provide limited spirometry information. This invention leverages all key indicators to identify various lung conditions as normal, obstructive, or restrictive, and other respiratory syndromes.

Patent Information:
Title App Type Country Serial No. Patent No. File Date Issued Date Expire Date
Transforming Cheap Spirometers to Estimate Flow-Volume Graph by Deep Learning Utility United States 17/715,561   4/7/2022