表面増強ラマン散乱（SERS）を用いた薬剤耐性検出：進歩、課題、および将来展望

Antimicrobial resistance (AMR) has emerged as one of the most critical global public health crises, causing an estimated 700,000 deaths annually according to the World Health Organization. Achieving early, rapid, and accurate detection and identification of drug-resistant bacteria is essential to addressing this challenge. Surface-enhanced Raman scattering (SERS), a highly sensitive, label-free, and non-invasive optical detection technology, has demonstrated great potential in bacterial identification and antimicrobial resistance analysis. In recent years, the integration of SERS with artificial intelligence (AI) technologies particularly machine learning (ML) and deep learning (DL) methods has enabled unprecedented accuracy and efficiency in resistance detection. This review systematically summarizes recent advances in SERS-AI combined strategies for AMR detection, analyzes the strengths and limitations of various approaches, and explores their potential applications in clinical and surveillance settings. Finally, the importance of continuous technological innovation and interdisciplinary collaboration in this field is emphasized to promote the translational application of SERS-AI strategies in the global fight against AMR.