Raman spectroscopy in chronic heart failure diagnosis based on human skin analysis

• Published in: Journal of biophotonics Vol. 16; no. 7; pp. e202300016 - n/a
• Main Authors: Khristoforova, Yulia A., Bratchenko, Lyudmila A., Skuratova, Maria A., Lebedeva, Elena A., Lebedev, Petr A., Bratchenko, Ivan A.
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.07.2023; Wiley Subscription Services, Inc
• Subjects: Algorithms; Biochemical composition; chemometrics; chronic heart failure; Congestive heart failure; Discriminant analysis; In vivo methods and tests; Optical analysis; optical biopsy; PLS‐DA; Raman spectroscopy; Skin; Spectra; Spectroscopy; chemometrics; PLS-DA; chronic heart failure; Raman spectroscopy; optical biopsy
• ISSN: 1864-063X; 1864-0648; 1864-0648
• DOI: 10.1002/jbio.202300016

This work aims at studying Raman spectroscopy in combination with chemometrics as an alternative fast noninvasive method to detect chronic heart failure (CHF) cases. Optical analysis is focused on the changes in the spectral features associated with the biochemical composition changes of skin tissues. A portable spectroscopy setup with the 785 nm excitation wavelength was used to record skin Raman features. In this in vivo study, 127 patients and 57 healthy volunteers were involved in measuring skin spectral features by Raman spectroscopy. The spectral data were analyzed with a projection on the latent structures and discriminant analysis. 202 skin spectra of patients with CHF and 90 skin spectra of healthy volunteers were classified with 0.888 ROC AUC for the 10‐fold cross validated algorithm. To identify CHF cases, the performance of the proposed classifier was verified by means of a new test set that is equal to 0.917 ROC AUC. This study has demonstrated utilizing Raman spectroscopy on human skin to differentiate the patients with chronic heart failure (CHF) and the healthy subjects using portable spectroscopy setup. The built PLS classifier discriminates the 202 spectra of CHF patients skin and 90 spectra of healthy volunteers' skin with 0.888 (0.840–0.930, 95% CI) ROC AUC when a 10‐fold cross validation was applied. The performance of the proposed classifier was estimated using separate experimental data with 0.917 (0.85%–1.95% CI) ROC AUC.