Complete characterization of RNA biomarker fingerprints using a multi-modal ATR-FTIR and SERS approach for label-free early breast cancer diagnosis

• Published in: RSC advances Vol. 14; no. 5; pp. 3599 - 361
• Main Authors: Zhang, Shuyan, Wu, Steve Qing Yang, Hum, Melissa, Perumal, Jayakumar, Tan, Ern Yu, Lee, Ann Siew Gek, Teng, Jinghua, Dinish, U. S, Olivo, Malini
• Format: Journal Article
• Language: English
• Published: England Royal Society of Chemistry 17.01.2024; The Royal Society of Chemistry
• Subjects: Algorithms; Biomarkers; Blood circulation; Breast cancer; Chemical fingerprinting; Chemistry; Diagnosis; Diamonds; Fourier transforms; Infrared reflection; Infrared spectroscopy; Labels; Machine learning; Mammography; Medical diagnosis; MicroRNAs; Modal data; Principal components analysis; Raman spectra; Raman spectroscopy; Sensitivity; Spectrum analysis; Support vector machines
• ISSN: 2046-2069; 2046-2069
• DOI: 10.1039/d3ra05723b

Breast cancer is a prevalent form of cancer worldwide, and the current standard screening method, mammography, often requires invasive biopsy procedures for further assessment. Recent research has explored microRNAs (miRNAs) in circulating blood as potential biomarkers for early breast cancer diagnosis. In this study, we employed a multi-modal spectroscopy approach, combining attenuated total reflection Fourier transform infrared (ATR-FTIR) and surface-enhanced Raman scattering (SERS) to comprehensively characterize the full-spectrum fingerprints of RNA biomarkers in the blood serum of breast cancer patients. The sensitivity of conventional FTIR and Raman spectroscopy was enhanced by ATR-FTIR and SERS through the utilization of a diamond ATR crystal and silver-coated silicon nanopillars, respectively. Moreover, a wider measurement wavelength range was achieved with the multi-modal approach than with a single spectroscopic method alone. We have shown the results on 91 clinical samples, which comprised 44 malignant and 47 benign cases. Principal component analysis (PCA) was performed on the ATR-FTIR, SERS, and multi-modal data. From the peak analysis, we gained insights into biomolecular absorption and scattering-related features, which aid in the differentiation of malignant and benign samples. Applying 32 machine learning algorithms to the PCA results, we identified key molecular fingerprints and demonstrated that the multi-modal approach outperforms individual techniques, achieving higher average validation accuracy (95.1%), blind test accuracy (91.6%), specificity (94.7%), sensitivity (95.5%), and F -score (94.8%). The support vector machine (SVM) model showed the best area under the curve (AUC) characterization value of 0.9979, indicating excellent performance. These findings highlight the potential of the multi-modal spectroscopy approach as an accurate, reliable, and rapid method for distinguishing between malignant and benign breast tumors in women. Such a label-free approach holds promise for improving early breast cancer diagnosis and patient outcomes. With the multi-modal approach combining ATR-FTIR and SERS, we achieved an extended spectral range for molecular fingerprint detection of RNA biomarkers. Machine learning results shows 91.6% blind test accuracy for label-free breast cancer diagnosis.