Advances in machine learning-assisted SERS sensing towards food safety and biomedical analysis

Abstract

Surface-enhanced Raman scattering, has extensive applications in the fields of medicine and food due to its high-sensitivity, speed, non-destructive nature, and cost-effectiveness. The integration of machine learning enhances the practical application of SERS by leveraging its autonomous learning capabilities and exceptional data processing power to achieve accurate and sensitive qualitative and quantitative analysis. This review commences with an introduction to SERS and progresses through discussions on data collection and pre-processing, feature extraction, and algorithms in machine learning models. It then examines the recent application of ML-assisted SERS in food safety, focusing on detecting additives, identifying bacteria, and analyzing internal components. In the realm of biomedical analysis, the review covers advancements in identifying DNA, microorganisms, biomarkers, and analyzing biological fluids and drugs. Finally, it provides a summary of current research and offers perspectives on the future application of ML-assisted SERS in these fields.