Machine learning-driven SERS analysis platform for rapid and accurate detection of precancerous lesions of gastric cancer.

A novel approach is proposed leveraging surface-enhanced Raman spectroscopy (SERS) combined with machine learning (ML) techniques, principal component analysis (PCA)-centroid displacement-based nearest neighbor (CDNN). This label-free approach can identify slight abnormalities between SERS spectra of gastric lesions at different stages, offering a promising avenue for detection and prevention of precancerous lesion of gastric cancer (PLGC). The agaric-shaped nanoarray substrate was prepared using gas-liquid interface self-assembly and reactive ion etching (RIE) technology to measure SERS spectra of serum from mice model with gastric lesions at different stages, and then a SERS spectral recognition model was trained and constructed using the PCA-CDNN algorithm. The results showed that the agaric-shaped nanoarray substrate has good uniformity, stability, cleanliness, and SERS enhancement effect. The trained PCA-CDNN model not only found the most important features of PLGC, but also achieved satisfactory classification results with accuracy, area under curve (AUC), sensitivity, and specificity up to 100%. This demonstrated the enormous potential of this analysis platform in the diagnosis of PLGC.

Source Tracing of Kidney Injury via the Multispectral Fingerprint Identified by Machine Learning-Driven Surface-Enhanced Raman Spectroscopic Analysis.

Early diagnosis of drug-induced kidney injury (DIKI) is essential for clinical treatment and intervention. However, developing a reliable method to trace kidney injury origins through retrospective studies remains a challenge. In this study, we designed ordered fried-bun-shaped Au nanocone arrays (FBS NCAs) to create microarray chips as a surface-enhanced Raman scattering (SERS) analysis platform. Subsequently, the principal component analysis (PCA)-two-layer nearest neighbor (TLNN) model was constructed to identify and analyze the SERS spectra of exosomes from renal injury induced by cisplatin and gentamycin. The established PCA-TLNN model successfully differentiated the SERS spectra of exosomes from renal injury at different stages and causes, capturing the most significant spectral features for distinguishing these variations. For the SERS spectra of exosomes from renal injury at different induction times, the accuracy of PCA-TLNN reached 97.8% (cisplatin) and 93.3% (gentamicin). For the SERS spectra of exosomes from renal injury caused by different agents, the accuracy of PCA-TLNN reached 100% (7 days) and 96.7% (14 days). This study demonstrates that the combination of label-free exosome SERS and machine learning could serve as an innovative strategy for medical diagnosis and therapeutic intervention.