Title: Machine Learning-Enhanced Clinical Decision Support for Diagnosing Sinusitis With Nasal Endoscopy
Journal: International Forum of Allergy & Rhinology
Institutions: UL Lafayette, Ochsner Health, Tulane University
Authors: Dipesh Gyawali, Thomas Mundy, Majid Hosseini, Morteza Bodaghi, Akio Fujiwara, Sejal Shyam Bhatia, Kayla Baker, Elena Bartolone, Dhara Patel, Henry Chu, Raju Gottumukkala, Jonathan Bidwell, Edward D. McCoul
Background:
Sinusitis is a common condition where nasal endoscopy (NE) is considered the optimal diagnostic tool. However, NE accuracy can vary due to differences in identifying anatomical landmarks and mucus localization.
Innovation:
The team developed a multi-class machine learning framework that detects anatomical landmarks and structures to support sinusitis diagnosis, aligning with clinical best practices.
Link to the article– https://onlinelibrary.wiley.com/doi/epdf/10.1002/alr.70045
