SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

Abstract

Surface‐enhanced Raman spectroscopy (SERS) has shown strength in non‐invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi‐quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed.

AI-Enhanced Visual-Spectral Synergy for Fast and Ultrasensitive Biodetection of Breast Cancer-Related miRNAs

“…According to previous work, , the FND@GNP-SH-probes that had been previously prepared were sprayed onto the binding pad in an amount of 15 μL/Pad. 2.5 μL of 5 mg/mL streptavidin (SA) and 2.5 μL of 100 μM Biotin-probe/Biotin-C probe were taken, and 15 μL of 10 mM pH 7.4 PBS buffer was added.…”

“…According to the previous work, , 2.5 μL of 5 mg/mL digoxin antibody (Anti-Dig) and 2.5 μL of 100 μM digoxin-modified Dig probe/Biotin-C probe were taken, and 15 μL of 10 mM pH 7.4 PBS buffer was added. The remaining steps followed the same procedure as that described earlier.…”

“…While the FND-based LFA platform presents a strategy for biomolecular detection, the mentioned studies rely on large optical and microwave equipment for achieving ultrasensitive detection. Nowadays, artificial intelligence (AI) is gradually advancing in the fields of biomolecular recognition and rapid disease diagnosis. , It can analyze complex data more efficiently and accurately, effectively addressing the drawbacks of traditional testing such as time-consuming processes, high costs, and the need for extensive expertise from testing personnel. AI-enhanced methods based on regression models have been applied to the analysis of LFAs .…”

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

“…With the ease of data collection and availability of open source Raman spectroscopy data, SERS has also seen a surge in machine learning models [ 49 , 351 , 352 ]. The trend is welcoming and desirable as the nature of existing challenges in SERS involving trace detection, signal fluctuations, quantification and identification are complex with many variables calling for an analytical tool that has the ability to capture the patterns devoid of experts [ 353 ]. Trace detection implies identifying signal from a noisy background where ML could be aided.…”

Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a Comparative Study of Interpretable Machine Learning Algorithms

“…Surface-enhanced Raman spectroscopy (SERS) is continually impacted by the ongoing machine learning (ML) revolution. 25 Dimensionality reduction techniques such as principal component analysis (PCA) and partial least squares are standard in spectral analysis. 26 However, as the degree of multiplexing continues to increase, accurate spectral unmixing becomes more crucial to accurate data interpretation.…”