Molecular separation-assisted label-free SERS combined with machine learning for nasopharyngeal cancer screening and radiotherapy resistance prediction

• Published in: Journal of photochemistry and photobiology. B, Biology Vol. 257; p. 112968
• Main Authors: Zhang, Jun, Weng, Youliang, Liu, Yi, Wang, Nan, Feng, Shangyuan, Qiu, Sufang, Lin, Duo
• Format: Journal Article
• Language: English
• Published: Switzerland Elsevier B.V 01.08.2024
• Subjects: adsorption; algorithms; discriminant analysis; Machine learning; metastasis; Molecular separation; molecular weight; Nasopharyngeal cancer; neoplasms; patients; photobiology; photochemistry; prediction; principal component analysis; radiation resistance; radiotherapy; Radiotherapy resistance; Raman spectroscopy; Screening; South East Asia; Surface enhanced Raman spectroscopy; surface plasmon resonance; South East Asia; Screening; Nasopharyngeal cancer; Radiotherapy resistance; Molecular separation; Surface enhanced Raman spectroscopy; Machine learning
• ISSN: 1011-1344; 1873-2682; 1873-2682
• DOI: 10.1016/j.jphotobiol.2024.112968

Nasopharyngeal cancer (NPC) is a malignant tumor with high prevalence in Southeast Asia and highly invasive and metastatic characteristics. Radiotherapy is the primary strategy for NPC treatment, however there is still lack of effect method for predicting the radioresistance that is the main reason for treatment failure. Herein, the molecular profiles of patient plasma from NPC with radiotherapy sensitivity and resistance groups as well as healthy group, respectively, were explored by label-free surface enhanced Raman spectroscopy (SERS) based on surface plasmon resonance for the first time. Especially, the components with different molecular weight sizes were analyzed via the separation process, helping to avoid the possible missing of diagnostic information due to the competitive adsorption. Following that, robust machine learning algorithm based on principal component analysis and linear discriminant analysis (PCA-LDA) was employed to extract the feature of blood-SERS data and establish an effective predictive model with the accuracy of 96.7% for identifying the radiotherapy resistance subjects from sensitivity ones, and 100% for identifying the NPC subjects from healthy ones. This work demonstrates the potential of molecular separation-assisted label-free SERS combined with machine learning for NPC screening and treatment strategy guidance in clinical scenario. [Display omitted] •The molecular profile of blood from nasopharyngeal cancer patients with radiotherapy resistance was explored by SERS for the first time.•Components in blood with different molecular weight were separated and analyzed to overcome the problem of informational lost.•This work would provide a non-invasive, convenient and easy-to-operation method for NPC screening and treatment strategy guidance.