BASH-GN: A New Machine Learning–Derived Questionnaire for Screening Obstructive Sleep Apnea

Case ID:
UA24-132
Invention:

BASH-GN is a machine learning-based questionnaire designed to classify the risk of obstructive sleep apnea (OSA) by considering various risk factor subtypes. Compared with other commonly used OSA screening tools, the BASH-GN questionnaire demonstrated superior performance, making it a more effective option for identifying at-risk individuals. This questionnaire makes the diagnostic process easier and helps healthcare providers take timely actions, improving patient outcomes and reducing the long-term health risks associated with untreated sleep apnea.

Background: 
Sleep apnea is a severe sleep disorder characterized by repeated interruptions in breathing during sleep, often resulting in loud snoring and persistent tiredness. Current solutions like the Four-Variable, Epworth Sleepiness Scale, Berlin, and STOP-BANG questionnaires use basic clinical criteria and do not consider various OSA risk factor subtypes. BASH-GN stands out because it uses machine learning to analyze a wider range of risk factors, offering a more customized and precise assessment for overall improved screening accuracy. 

Applications: 

  • Diagnostic for obstructive sleep apnea risk


Advantages: 

  • Outperforms standard screening questionnaires
  • Effective at identifying at-risk individuals for obstructive sleep apnea
  • Rapid delivery of results
  • Easy to use
  • Earlier diagnosis improves patient outcomes
Patent Information:
Contact For More Information:
Lewis Humphreys
Licensing Manager, Eller College of Mngmt & OTT
The University of Arizona
lewish@tla.arizona.edu
Lead Inventor(s):
Ao Li
Jiayan Huo
Stuart Quan
Janet Roveda
Keywords: