Fusion of Raman and ATR FTIR spectral data combined with artificial intelligence for the diagnostics of Sjögren’s disease

Fusion of multimodal spectral data offers great potential as a screening test for Sjögren’s disease

Abstract Text:

Sjögren’s disease is an autoimmune disorder affecting exocrine glands, causing dry eyes and mouth and other morbidities. Polypharmacy or a history of radiation to the head and neck can also lead to dry mouth. Sjögren’s disease is often underdiagnosed due to its non-specific symptoms, limited awareness among healthcare professionals, and the complexity of diagnostic criteria, limiting the ability to provide therapy early. Current diagnostic methods suffer from the absence of a single diagnostic marker, the low sensitivity and specificity, high cost, complexity, and invasiveness.

Vibrational spectroscopy (Raman- and IR spectroscopy) combined with artificial intelligence is a promising novel and universal approach for disease diagnostics. Raman and FTIR spectroscopies provide complimentary information because they are based on different physical phenomena and obey different selection rules. Here, we will report on a combined Raman and AT FTIR spectroscopic screening of saliva for Sjögren’s disease. It will be shown that a combined Raman and ATR FTIR spectral dataset acquired from the same samples of dry saliva will significantly improve the accuracy of the screening test for the disease. General advantages, which fusion of multimodal spectral data offers for increasing the accuracy of biomedical diagnostics, will be discussed also on blood and saliva tests for Sjögren’s disease.

Acknowledgments

We gratefully acknowledge financial support from the European Union, the Thüringer Ministry for Economy, Science, and Digital Society, the Thüringer Aufbaubank, the Federal Ministry of Education and Research (Germany), the German Science Foundation, and the Carl-Zeiss Foundation.