Comment on "Infrared spectroscopy for fast screening of diabetes and periodontitis".

This article discusses a recent research paper by da Silva et al [12] on screening diabetes and periodontitis by means of the in vitro infrared spectroscopic analysis of human saliva which was published in the Photodiagnosis and Photodynamic Therapy journal. Despite the reported high performance of the suggested approach, the demonstrated findings could be treated as unclear due to possible drawbacks in classification models validation. The data need to be provided both for the training set and for the validation set to make sure that there is no repeated data from the same sample in the training and validation sets.

Comment on "Raman spectroscopy combined with multivariate statistical algorithms for the simultaneous screening of cervical and breast cancers".

This article discusses current research on the detection of cervical and breast cancer using in vitro Raman spectral analysis of human serum by Cao et al. (2024) which was published in the Lasers in Medical Science journal. Despite the high accuracy of the suggested approach (93%), the demonstrated findings could be treated unclear due to possible overestimation of the classification models.

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

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.

Comment on "Feasibility of Raman spectroscopy as a potential in vivo tool to screen for pre-diabetes and diabetes".

This paper comments recent findings about Raman spectroscopy application for in vivo noninvasive diabetes detection, published in the Journal of Biophotonics by E. Guevara et al. (J. Biophotonics 2022, 15, e202200055). The proposed results may be not entirely correct due to possible overestimation of classification models and absence of additional information regarding age of tested volunteers.

Comment on "Serum Raman spectroscopy combined with multiple classification models for rapid diagnosis of breast cancer".

This paper comments recent findings about Raman spectroscopy application for breast cancer detection published in the Photodiagnosis and Photodynamic Therapy journal by Li et al. Despite the high performance of the proposed approach for breast cancer detection by means of Raman spectroscopy analysis of serum, the proposed results may be ambiguous due to overestimation of classification models.

Analyzing the serum of hemodialysis patients with end-stage chronic kidney disease by means of the combination of SERS and machine learning.

The aim of this paper is a multivariate analysis of SERS characteristics of serum in hemodialysis patients, which includes constructing classification models (PLS-DA, CNN) by the presence/absence of end-stage chronic kidney disease (CKD) with dialysis and determining the most informative spectral bands for identifying dialysis patients by variable importance distribution. We found the spectral bands that are informative for detecting the hemodialysis patients: the 641 cm-1, 724 cm-1, 1094 cm-1 and 1393 cm-1 bands are associated with the degree of kidney function inhibition; and the 1001 cm-1 band is able to demonstrate the distinctive features of hemodialysis patients with end-stage CKD.

Classification of skin cancer using convolutional neural networks analysis of Raman spectra.

BACKGROUND AND OBJECTIVE: Skin cancer is the most common malignancy in whites accounting for about one third of all cancers diagnosed per year. Portable Raman spectroscopy setups for skin cancer "optical biopsy" are utilized to detect tumors based on their spectral features caused by the comparative presence of different chemical components. However, low signal-to-noise ratio in such systems may prevent accurate tumors classification. Thus, there is a challenge to develop methods for efficient skin tumors classification. METHODS: We compare the performance of convolutional neural networks and the projection on latent structures with discriminant analysis for discriminating skin cancer using the analysis of Raman spectra with a high autofluorescence background stimulated by a 785 nm laser. We have registered the spectra of 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable Raman setup and created classification models both for convolutional neural networks and projection on latent structures approaches. To check the classification models stability, a 10-fold cross-validation was performed for all created models. To avoid models overfitting, the data was divided into a training set (80% of spectral dataset) and a test set (20% of spectral dataset). RESULTS: The results for different classification tasks demonstrate that the convolutional neural networks significantly (p<0.01) outperforms the projection on latent structures. For the convolutional neural networks implementation we obtained ROC AUCs of 0.96 (0.94 - 0.97; 95% CI), 0.90 (0.85-0.94; 95% CI), and 0.92 (0.87 - 0.97; 95% CI) for classifying a) malignant vs benign tumors, b) melanomas vs pigmented tumors and c) melanomas vs seborrheic keratosis respectively. CONCLUSIONS: The performance of the convolutional neural networks classification of skin tumors based on Raman spectra analysis is higher or comparable to the accuracy provided by trained dermatologists. The increased accuracy with the convolutional neural networks implementation is due to a more precise accounting of low intensity Raman bands in the intense autofluorescence background. The achieved high performance of skin tumors classifications with convolutional neural networks analysis opens a possibility for wide implementation of Raman setups in clinical setting.

Comment on "Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning".

This paper comments on the article "Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning" by D. C. Araújo et al. The authors apply Raman spectroscopy for the classification of benign and malignant skin neoplasms based on their Raman spectra. Despite the high performance of the proposed technique it may provide unreasonably high accuracy because of incorrect cross-validation procedure. To confirm the possibility to discriminate neoplasm skin tissues based on Raman spectra analysis the authors should provide additional data regarding utilized cross-validation procedure.

Raman spectroscopy based diagnosis of dermatofibrosarcoma protuberans: Case report.

Dermatofibrosarcoma protuberans is a rare disease and this pathology provokes insufficient oncological alertness among clinicians. A possible way to increase the accuracy of early diagnosis of rare skin neoplasms is "optical biopsy" using Raman spectroscopy tissue response. This case report of a 32-year-old woman with a dermatofibrosarcoma protuberans demonstrates that Raman spectroscopy based "optical biopsy" can help to diagnose rare tumors.

In vivo diagnosis of skin cancer with a portable Raman spectroscopic device.

In this study, we performed in vivo diagnosis of skin cancer based on implementation of a portable low-cost spectroscopy setup combining analysis of Raman and autofluorescence spectra in the near-infrared region (800-915 nm). We studied 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable setup. The studies considered the patients examined by GPs in local clinics and directed to a specialized Oncology Dispensary with suspected skin cancer. Each sample was histologically examined after excisional biopsy. The spectra were classified with a projection on latent structures and discriminant analysis. To check the classification models stability, a 10-fold cross-validation was performed. We obtained ROC AUCs of 0.75 (0.71-0.79; 95% CI), 0.69 (0.63-0.76; 95% CI) and 0.81 (0.74-0.87; 95% CI) for classification of a) malignant and benign tumors, b) melanomas and pigmented tumors and c) melanomas and seborrhoeic keratosis, respectively. The positive and negative predictive values ranged from 20% to 52% and from 73% to 99%, respectively. The biopsy ratio varied from 0.92:1 to 4.08:1 (at sensitivity levels from 90% to 99%). The accuracy of automatic analysis with the proposed system is higher than the accuracy of GPs and trainees, and is comparable or less to the accuracy of trained dermatologists. The proposed approach may be combined with other optical techniques of skin lesion analysis, such as dermoscopy- and spectroscopy-based computer-assisted diagnosis systems to increase accuracy of neoplasms classification.

Comment on "Combining derivative Raman with autofluorescence to improve the diagnosis performance of echinococcosis".

This paper comments on the article "Combining derivative Raman with autofluorescence to improve the diagnosis performance of echinococcosis" by X. Zheng et al. The authors put forward an idea to apply Raman spectroscopy and autofluorescence to measure spectral characteristics of human serum and diagnose echinococcosis. Despite the high performance of the proposed approach, the demonstrated results may be ambiguous due to the incorrect number of the utilized principal components in classification models for spectral datasets analysis.

Raman spectroscopy of human skin for kidney failure detection.

The object of this paper is in vivo study of skin spectral-characteristics in patients with kidney failure by conventional Raman spectroscopy in near infrared region. The experimental dataset was subjected to discriminant analysis with the projection on latent structures (PLS-DA). Application of Raman spectroscopy to investigate the forearm skin in 85 adult patients with kidney failure (90 spectra) and 40 healthy adult volunteers (80 spectra) 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. The autofluorescence analysis in the near infrared region identified the patients with kidney failure among healthy volunteers of the same age group with specificity, sensitivity, and accuracy of 0.91, 0.84, and 0.88, respectively. 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 . In general, 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 kidney failure and associated metabolic changes in the skin.

Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools: comment.

This paper comments on the article "Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools" by E. Guevara et al. The authors propose an optical method for noninvasive automated screening of type 2 diabetes mellitus. Despite the high performance of the proposed method, results shown by the authors may be ambiguous due to the overestimation of classification models for Raman spectral data analysis.