Unlocking the complete blood count as a risk stratification tool for breast cancer using machine learning: a large scale retrospective study.

Optimizing early breast cancer (BC) detection requires effective risk assessment tools. This retrospective study from Brazil showcases the efficacy of machine learning in discerning complex patterns within routine blood tests, presenting a globally accessible and cost-effective approach for risk evaluation. We analyzed complete blood count (CBC) tests from 396,848 women aged 40-70, who underwent breast imaging or biopsies within six months after their CBC test. Of these, 2861 (0.72%) were identified as cases: 1882 with BC confirmed by anatomopathological tests, and 979 with highly suspicious imaging (BI-RADS 5). The remaining 393,987 participants (99.28%), with BI-RADS 1 or 2 results, were classified as controls. The database was divided into modeling (including training and validation) and testing sets based on diagnostic certainty. The testing set comprised cases confirmed by anatomopathology and controls cancer-free for 4.5-6.5 years post-CBC. Our ridge regression model, incorporating neutrophil-lymphocyte ratio, red blood cells, and age, achieved an AUC of 0.64 (95% CI 0.64-0.65). We also demonstrate that these results are slightly better than those from a boosting machine learning model, LightGBM, plus having the benefit of being fully interpretable. Using the probabilistic output from this model, we divided the study population into four risk groups: high, moderate, average, and low risk, which obtained relative ratios of BC of 1.99, 1.32, 1.02, and 0.42, respectively. The aim of this stratification was to streamline prioritization, potentially improving the early detection of breast cancer, particularly in resource-limited environments. As a risk stratification tool, this model offers the potential for personalized breast cancer screening by prioritizing women based on their individual risk, thereby indicating a shift from a broad population strategy.

O efeito do ácido ascórbico tópico na cicatrização cutânea / The effect of topical ascorbic acid on cutaneous healing

Introdução: A ferida cirúrgica apresenta altos níveis de radicais livres em resposta ao dano cutâneo, o que gera a hipótese de um possível benefício do uso de antioxidantes no reparo destas feridas, tal como a aplicação tópica do ácido ascórbico. No entanto, pesquisas recentes obtiveram conclusões discrepantes para este tipo de tratamento. O objetivo é avaliar o efeito do ácido ascórbico tópico na cicatrização cutânea por meio de uma revisão de escopo. Métodos: A revisão de escopo foi realizada na base de dados Medline, Lilacs e Cochrane, com os descritores: ácido ascórbico, creme para a pele e cicatrização de feridas. Foram definidos como critérios de inclusão: ensaios clínicos randomizados, observacionais e revisões sistemáticas, em humanos, com data de publicação de até 5 anos, nas línguas inglesa, portuguesa ou espanhola. Foram excluídas: revisões narrativas, dissertações, teses, editoriais, estudos in vitro e em animais. Por fim, foi realizada a classificação dos estudos através da metodologia GRADE. Resultados: Foram encontrados 83 estudos e, após triagem, seis artigos foram selecionados. Destacou-se o uso do ácido ascórbico na concentração de 5 a 20% e de seus derivados (0,075% a 9,55%). Apresentaram a qualidade GRADE moderada os desfechos: aumento da firmeza cutânea e redução da vermelhidão, e alta qualidade: melhora na hidratação, elasticidade, colorometria das manchas e melhora do fechamento das feridas. Conclusão: O ácido ascórbico promove melhor elasticidade cutânea, diminuição do eritema e melhor fechamento das feridas. Apesar destes fortes indícios, ensaios clínicos randomizados com menor risco de viés de aferição e com maior casuística ainda se fazem necessários.

Introduction: The surgical wound has high levels of free radicals in response to skin damage, which raises the hypothesis of a possible benefit from using antioxidants in repairing these wounds, such as the topical application of ascorbic acid. However, recent research has found conflicting conclusions about this type of treatment. The objective is to evaluate the effect of topical ascorbic acid on skin healing through a scope review. Methods: The scope review was carried out in the Medline, Lilacs and Cochrane databases, with the descriptors: ascorbic acid, skin cream, and wound healing. Inclusion criteria were defined as randomized clinical trials, observational and systematic reviews, in humans, with a publication date of up to 5 years, in English, Portuguese or Spanish. The following were excluded: narrative reviews, dissertations, theses, editorials, in vitro and animal studies. Finally, the studies were classified using the GRADE methodology. Results: 83 studies were found, and six articles were selected after screening. The use of ascorbic acid in the concentration of 5 to 20% and its derivatives (0.075% to 9.55%) stood out. The outcomes presented a moderate GRADE quality: increased skin firmness and reduced redness, and high quality: improved hydration, elasticity, colorimetry of the stains and improved wound closure. Conclusion: Ascorbic acid promotes better skin elasticity, reduced erythema and better wound closure. Despite these strong indications, randomized clinical trials with a lower risk of measurement bias and greater casuistry are still necessary.

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

Early-stage detection of cutaneous melanoma can vastly increase the chances of cure. Excision biopsy followed by histological examination is considered the gold standard for diagnosing the disease, but requires long high-cost processing time, and may be biased, as it involves qualitative assessment by a professional. In this paper, we present a new machine learning approach using raw data for skin Raman spectra as input. The approach is highly efficient for classifying benign versus malignant skin lesions (AUC 0.98, 95% CI 0.97-0.99). Furthermore, we present a high-performance model (AUC 0.97, 95% CI 0.95-0.98) using a miniaturized spectral range (896-1039 cm-1), thus demonstrating that only a single fragment of the biological fingerprint Raman region is needed for producing an accurate diagnosis. These findings could favor the future development of a cheaper and dedicated Raman spectrometer for fast and accurate cancer diagnosis.

Differential diagnosis in primary and metastatic cutaneous melanoma by FT-Raman spectroscopy / Diagnóstico diferencial no melanoma primário e metastático por espectroscopia FT-Raman

PURPOSE: To qualify the FT-Raman spectral data of primary and metastatic cutaneous melanoma in order to obtain a differential diagnosis. METHODS: Ten normal human skin samples without any clinical or histopathological alterations, ten cutaneous melanoma fragments, and nine lymph node metastasis samples were used; 105, 140 and 126 spectra were obtained respectively. Each sample was divided into 2 or 3 fragments of approximately 2 mm³ and positioned in the Raman spectrometer sample holder in order to obtain the spectra; a monochrome laser light Nd:YAG at 1064 nm was used to excite the inelastic effect. RESULTS: To differentiate the three histopathological groups according to their characteristics extracted from the spectra, data discriminative analysis was undertaken. Phenylalanine, DNA, and Amide-I spectral variables stood out in the differentiation of the three groups. The percentages of correctly classified groups based on Phenylalanine, DNA, and Amide-I spectral features was 93.1 percent. CONCLUSION: FT-Raman spectroscopy is capable of differentiating melanoma from its metastasis, as well as from normal skin.

OBJETIVO: Qualificar os dados espectrais FT-Raman do melanoma cutâneo primário e metastático e assim realizar o diagnóstico diferencial. MÉTODOS: Foram utilizadas amostras de 10 fragmentos de pele sem alterações clínicas ou histopatológicas, 10 de melanomas cutâneos e 9 de metástases linfonodais; 105, 140 and 126 espectros foram obtidos respectivamente. Cada amostra foi dividida em 2 ou 3 frações de 2 mm³ e posicionada no porta amostras do espectrômetro Raman para obtenção dos espectros, por meio da excitação do espalhamento inelástico pelo laser de Nd:YAG em 1064 nm incididos na amostra. RESULTADOS: Para diferenciar os três grupos formados de acordo com as características fornecidas pelos espectros, realizamos a análise discriminante dos dados. As variáveis espectrais Fenilalanina, DNA e Amida-I se destacaram na capacidade de diferenciação dos três grupos histológicos. A porcentagem de classificação correta utilizando estes critérios foi de 93,1 por cento; o que mostra a eficiência da análise realizada. CONCLUSÃO: A espectroscopia FT-Raman é capaz de diferenciar o melanoma de sua metástase, assim como da pele normal.

Differential diagnosis in primary and metastatic cutaneous melanoma by FT-Raman spectroscopy.

PURPOSE: To qualify the FT-Raman spectral data of primary and metastatic cutaneous melanoma in order to obtain a differential diagnosis. METHODS: Ten normal human skin samples without any clinical or histopathological alterations, ten cutaneous melanoma fragments, and nine lymph node metastasis samples were used; 105, 140 and 126 spectra were obtained respectively. Each sample was divided into 2 or 3 fragments of approximately 2 mm³ and positioned in the Raman spectrometer sample holder in order to obtain the spectra; a monochrome laser light Nd:YAG at 1064 nm was used to excite the inelastic effect. RESULTS: To differentiate the three histopathological groups according to their characteristics extracted from the spectra, data discriminative analysis was undertaken. Phenylalanine, DNA, and Amide-I spectral variables stood out in the differentiation of the three groups. The percentages of correctly classified groups based on Phenylalanine, DNA, and Amide-I spectral features was 93.1%. CONCLUSION: FT-Raman spectroscopy is capable of differentiating melanoma from its metastasis, as well as from normal skin.

Spectral region optimization for Raman-based optical biopsy of inflammatory lesions.

OBJECTIVE: The biochemical alterations between inflammatory fibrous hyperplasia (IFH) and normal tissues of buccal mucosa were probed by using the FT-Raman spectroscopy technique. The aim was to find the minimal set of Raman bands that would furnish the best discrimination. BACKGROUND: Raman-based optical biopsy is a widely recognized potential technique for noninvasive real-time diagnosis. However, few studies had been devoted to the discrimination of very common subtle or early pathologic states as inflammatory processes that are always present on, for example, cancer lesion borders. METHODS: Seventy spectra of IFH from 14 patients were compared with 30 spectra of normal tissues from six patients. The statistical analysis was performed with principal components analysis and soft independent modeling class analogy cross-validated, leave-one-out methods. RESULTS: Bands close to 574, 1,100, 1,250 to 1,350, and 1,500 cm(-1) (mainly amino acids and collagen bands) showed the main intragroup variations that are due to the acanthosis process in the IFH epithelium. The 1,200 (C-C aromatic/DNA), 1,350 (CH(2) bending/collagen 1), and 1,730 cm(-1) (collagen III) regions presented the main intergroup variations. This finding was interpreted as originating in an extracellular matrix-degeneration process occurring in the inflammatory tissues. The statistical analysis results indicated that the best discrimination capability (sensitivity of 95% and specificity of 100%) was found by using the 530-580 cm(-1) spectral region. CONCLUSIONS: The existence of this narrow spectral window enabling normal and inflammatory diagnosis also had useful implications for an in vivo dispersive Raman setup for clinical applications.

Role of cervicitis in the Raman-based optical diagnosis of cervical intraepithelial neoplasia.

The Raman-based optical diagnosis of normal cervix, inflammative cervix (cervicitis), and cervical intraepithelial neoplasia was investigated on samples of 63 patients. The main alterations were found in the 857 cm(-1) (CCH deformation aromatic); 925 cm(-1) (C-C stretching); approximately 1247 cm(-1) (CN stretch, NH bending of Amide III); 1370 cm(-1) (CH2 bending); and 1525 cm(-1) (C=CC=N stretching) vibrational bands in accordance with previously reported in the literature comparing normal and malignant cervical tissue. The statistical analysis (principal components analysis, clustering, and logistic regression models) applied to the spectral data indicated that the full discrimination among normal and neoplastic tissues of cervix by Raman optical biopsy is seriously affected by the presence of inflammatory infiltrates, which increases the false-positive rate. This fact is specially relevant once cervicitis is a very common state (noncancerous) of the cervix of sexually active woman. The results suggest that, for the correct Raman-based diagnosis of normal cervix from cervical intraepithelial neoplasia, it is necessary to use an auxiliary way to discriminate the contribution from the inflammatory infiltrates.

DNA Extraction Systematics for Spectroscopic Studies.

Study of genetic material allows the comprehension the origin of the many biochemical changes that follow diseases, like cancer, promoting the development of early preventive inquiry and more efficient individual treatments. Raman spectroscopy can be an important tool in DNA study, since it allows probe molecular vibrations of genetic material in a fast way. The present work established a systematic way for extract DNA in suitable concentrations and structural integrity allowing studies by Raman spectroscopy or other spectroscopic technique, including bio-analytical sensors for probing genetic alterations.

FT-raman spectra of the border of infiltrating ductal carcinoma lesions.

OBJECTIVE: The characterization of the FT-Raman spectra of the borders of lesions is of great importance in guiding the surgeon during surgical intervention. BACKGROUND DATA: The main goals of this study were to investigate spectra of the borders of lesions of samples of infiltrating ductal carcinoma (IDC) and to determine the characteristics of these spectra. METHODS: A total of 93 spectra were collected from five samples of healthy tissues and from 13 samples of IDC breast tissues using FT-Raman spectroscopy. Cluster analysis was used to separate the spectra into different groups. The results obtained from the statistical analysis were confirmed by a histopathological analysis. RESULTS: The results showed that 17 out of the 67 spectra collected from the IDC samples demonstrated wide variety. The only significant difference between the peaks of the spectra of normal tissues and those of lesion borders is a peak at 538 cm(1) . This peak is related to disulfide bridges in cysteine, and it seems to be the main factor for the FT-Raman determination of the boundaries between healthy and pathological tissue. CONCLUSIONS: These results serve as a foundation for future studies and application of Raman spectroscopy for optical diagnosis to guide biopsy and surgical intervention.

Biochemical analysis of human breast tissues using Fourier-transform Raman spectroscopy.

We employ Fourier-transform Raman spectroscopy to study normal and tumoral human breast tissues, including several subtypes of cancers. We analyzed 194 Raman spectra from breast tissues that were separated into 9 groups according to their corresponding histopathological diagnosis. The assignment of the relevant Raman bands enabled us to connect the several kinds of breast tissues (normal and pathological) to their corresponding biochemical moieties alterations and distinguish among 7 groups: normal breast, fibrocystic condition, duct carcinoma in situ, duct carcinoma in situ with necrosis, infiltrating duct carcinoma not otherwise specified, colloid infiltrating duct carcinoma, and invasive lobular carcinomas. We were able to establish the biochemical basis for each spectrum, relating the observed peaks to specific biomolecules that play a special role in the carcinogenesis process. This work is very useful for the premature optical diagnosis of a broad range of breast pathologies. We noticed that we were not able to differentiate inflammatory and medullary duct carcinomas from infiltrating duct carcinoma not otherwise specified.

Near-infrared Raman spectroscopy for oral carcinoma diagnosis.

OBJECTIVE: Fourier-transform (FT)-Raman spectroscopy has been used to explore the changes in the vibrational bands of normal, dysplastic (DE) and squamous cell carcinoma (SCC) tissues. BACKGROUND DATA: Raman spectroscopy has been applied as a diagnostic tool for the detection of cancers, due to its sensitivity to the changes in molecular composition and conformation that occurs in malignant tissues. The detection of weak Raman signals from biotissues becomes easier by FT-Raman due to fluorescence suppression. METHODS: A carcinogen (7,12-dimethybenz[a]anthracene [DMBA]) was applied daily in the oral pouch of 21 hamster to induce oral carcinoma. After 14 weeks, the fragments of squamous cell carcinomas and oral normal tissue were collected and analyzed by FT-Raman spectroscopy, using a 1064-nm Nd:YAG laser line as an excitation source. A total of 123 spectra were obtained and divided in normal and malignant tissue groups, and analyzed statistically through principal components analysis (PCA) and classified using Mahalanobis distance. RESULTS: Major differences between normal and malignant spectra seem to arise from the composition, conformational, and structural changes of proteins, and possible increase of its content in malignant epithelia. An algorithm based on PCA was able to separate the samples into two groups--normal and carcinoma. For the algorithm training group, 91% sensitivity and 69% specificity were observed, while the prospective group had 100% sensitivity and 55% specificity. CONCLUSION: The algorithm based on PCA has the potential for classifying Raman spectra and can be useful for detection of dysplastic and malign oral lesion.