Machine Learning Assisted Handheld Confocal Raman Micro-Spectroscopy for Identification of Clinically Relevant Atopic Eczema Biomarkers

Abstract

Atopic dermatitis (AD) is a common chronic inflammatory skin dermatosis condition due to skin barrier dysfunction that causes itchy, red, swollen, and cracked skin. Currently, AD severity clinical scores are subjected to intra- and inter-observer differences. There is a need for an objective scoring method that is sensitive to skin barrier differences. The aim of this study was to evaluate the relevant skin chemical biomarkers in AD patients. We used confocal Raman micro-spectroscopy and advanced machine learning methods as means to classify eczema patients and healthy controls with sufficient sensitivity and specificity. Raman spectra at different skin depths were acquired from subjects’ lower volar forearm location using an in-house developed handheld confocal Raman micro-spectroscopy system. The Raman spectra corresponding to the skin surface from all the subjects were further analyzed through partial least squares discriminant analysis, a binary classification model allowing the classification between eczema and healthy subjects with a sensitivity and specificity of 0.94 and 0.85, respectively, using stratified K-fold (K = 10) cross-validation. The variable importance in the projection score from the partial least squares discriminant analysis classification model further elucidated the role of important stratum corneum proteins and lipids in distinguishing two subject groups.

Electromagnetic Sensing Techniques for Monitoring Atopic Dermatitis—Current Practices and Possible Advancements: A Review

“…This review covers methods demonstrated in the literature as viable skin hydration sensors and in some cases that have been used on skins with eczema. Raman spectroscopy focuses on the scattering of light, and it measures the intensity of scattering events occurring at specific wavelengths, thereby estimating the concentration of molecules with known scattering effects at these frequencies [96]. Near-Infrared Spectroscopy (NIRS) monitors the absorption intensity from the reflectance spectrum of an exposed tissue or material within the near-infrared band (wavelengths of 0.8 to 2.5 mm).…”

“…Confocal Raman Micro-Spectroscopy (CRM) is a type of Raman spectroscopy widely used to perform non-invasive in vivo measurements on the SC and EP layers of the skin, as it can determine the biomolecular composition at depths up to several hundred micrometers [96]. The method uses the variance in scattered protons depending on the chemical content to provide a unique signature Raman spectrum for each material measured.…”

“…AD affects the chemical composition of the skin not only by reducing the free water molecules inside but also eliciting other molecular biomarkers. Dev et al explored the Raman intensity at different wavebands from 400 to 1800 cm −1 to classify the differences between atopic and healthy skin [96]. The probe used was handheld and portable, but the light source and the spectrograph required for the measurements are bench top equipment, and therefore, this approach is not portable, as visualized in Figure 11.…”

“…The probe used was handheld and portable, but the light source and the spectrograph required for the measurements are bench top equipment, and therefore, this approach is not portable, as visualized in Figure 11. They record differences in the Raman spectra at the wavebands corresponding to water, ceramide and urocanic acid, the latter of which features the highest separation at the wavelength of 6098 nm [96]. This is an important metric for the discovery of other biomarkers of AD.…”

Atopic Dermatitis: Molecular Alterations between Lesional and Non-Lesional Skin Determined Noninvasively by In Vivo Confocal Raman Microspectroscopy

“…CRM has been widely used in the past to examine HS [51][52][53][54], the effects of ageing [55], and psoriatic skin [56][57][58]. So far, CRM has already been applied in AD to study the impact of filaggrin mutations [59][60][61], to compare sensitive skin with atopic and non-sensitive skin [62], to compare HS with lesional atopic and psoriatic skin [63], and to create an objective classification score for AD [64]. Janssens et al have focussed on the lipid analysis of atopic skin [65], and Verzeaux et al studied several molecular SBF-related parameters comparing LAS and HS up to a depth of 12.5 µm in the SC [66].…”