Raman hyperspectroscopy of saliva and machine learning for Sjögren's disease diagnostics

Area of Science:

• Biomedical Engineering
• Spectroscopy
• Machine Learning

Background:

• Sjögren's disease is an autoimmune disorder causing dry eyes and mouth.
• Underdiagnosis is common due to non-specific symptoms and diagnostic challenges.
• Current diagnostic methods are limited by cost, invasiveness, and accuracy.

Purpose of the Study:

• To develop a novel screening test for Sjögren's disease.
• To overcome limitations of current diagnostic procedures.
• To enable earlier detection and treatment of Sjögren's disease.

Main Methods:

• Utilized Raman hyperspectroscopy combined with machine learning.
• Developed a novel screening test for Sjögren's disease.
• Applied the technique to distinguish patients from controls.

Main Results:

• The method effectively distinguished Sjögren's disease patients from healthy and radiation patients.
• Demonstrated potential for a rapid and non-invasive screening test.
• Identified a unique Raman hyper-spectral signature for Sjögren's disease.

Conclusions:

• Raman hyperspectroscopy and machine learning offer a promising approach for Sjögren's disease screening.
• This technique could lead to an efficient, rapid, and inexpensive diagnostic tool.
• Early detection through this method may improve patient outcomes.