CC BY
3*
ALT'23 The 30th International Conference on Advanced Laser Technologies
B-I-20
Optical and liquid biopsy in combination with machine learning for non-communicable diseases identification
L. Bartchenko1, Yu. Khrisoforova1, A. Matveeva1, S. Al-Sammarrae1, E. Typikova1, P. Lebedev2, M. Skuratova3, I. Bratchenko1
1- Samara National Research University, Samara, Russia 2- Samara state medical university, Samara, Russia 3- Samara regional clinical hospital named after VD Seredavin
Main author email address: [email protected]
In modern world practice, promising diagnostic methods are emerging, such as "optical biopsy" [1] and "liquid biopsy" [2], which are used for specific diseases biomarkers detection in biological tissues and fluids. Optical methods have the potential to overcome the limitations of traditional methods of clinical analysis. One of the most promising methods of optical analysis (and optical biopsy) is a Raman spectroscopy, which can contribute to understanding of molecular basis of diseases and creation of new bioanalytical tools for the diagnosis of diseases. Since each type of biological tissue and biofluid has an individual molecular composition and, thus, a unique spectral profile resulting from the transition of a molecule from one vibrational-rotational state to another, a set of such individual states of functional groups of nucleic acids, proteins, lipids and carbohydrates makes it possible to characterize component composition of tissues, which ultimately makes it possible to isolate disease markers [3]. Along with the use of optical biopsy methods, it is possible to apply a supersensitive technique for analyzing biofluids based on surface-enhanced Raman spectroscopy, which will be most effective for detecting low concentrations of disease markers in biological fluids. In the last decade, the development of nanotechnology has led to the creation of promising tools for solving new problems in the study of various human diseases, which is especially important for effective and targeted treatment and a deeper fundamental understanding of the biochemistry of diseases [2]. In this study we demonstrate application of conventional Raman spectroscopy for the analysis of skin tissues and application of SERS for serum analysis to determine the presence of non-communicable diseases. In this study, the in vitro analysis of human serum was performed for more than 400 subjects, and more than 300 skin samples were analyzed in vivo for the detection of chronic heart failure (CHF), chronic heart failure and other non-communicable diseases. Analyzed groups separation based on deep learning was implemented using a separate one-dimensional convolutional neural network (CNN). Application of Raman spectroscopy to investigate the forearm skin has yielded the accuracy of 0.96, sensitivity of 0.94 and specificity of 0.99 in terms of identifying the target subjects with kidney failure. When classifying subjects by the presence of kidney failure using the PLS-DA method, the most informative Raman spectral bands are 1315 to 1330, 1450 to 1460, 1700 to 1800 cm-1. The performed study demonstrates that for in vivo skin analysis, the conventional Raman spectroscopy can provide the basis for cost-effective and accurate detection of CHF and associated metabolic changes in the skin.
The results of the SERS data for CHF demonstrates that CNN significantly outperforms standard methods of analysis as projection on latent structures and allows for detection of CHF with 95-100% accuracy. By means of multivariate analysis, the informative spectral bands associated with the CHF during disease progression were identified. In addition, the analysis of the correlation between the serum spectral characteristics and urea, creatinine has made it possible to determine the spectral bands correlated with levels of creatinine and urea into the complex spectral characteristics of serum. In general, the reported approach may form the basis for monitoring the health status of CHF patients and find application in studying other pathological conditions of the human body [3]. Raman-based optical and liquid biopsy may be promising in non-communicable diseases identification, as it provides fast and rapid diagnosis.
[1] I Bratchenko, Y Khristoforova, L Bratchenko, et al. Optical biopsy of amelanotic melanoma with Raman and autofluorescence spectra stimulated by 785 nm laser excitation, Journal of Biomedical Photonics & Engineering, 7., pp. 020308, (2021).
[2] L.A. Bratchenko, S.Z. Al-Sammarraie, I.A. Bratchenko, et al. Analyzing the serum of hemodialysis patients with end-stage chronic kidney disease by means of the combination of SERS and machine learning, Biomedical Optics Express, 13., pp. 4926-4938, (2022).
[3] A Bratchenko, LA Bratchenko, YA Khristoforova, et al. Classification of skin cancer using convolutional neural networks analysis of Raman spectra, Computer Methods and Programs in Biomedicine, 219, 106755 (2022).
