Carboxyl-PEG modified Fe3O4 nanoparticles as an ultrasensitive SERS substrate for multiplex detection of exogenous hormones related to endometrial cancer.

Traditional surface-enhanced Raman scattering (SERS) technology often struggles to achieve high-precision discrimination in the simultaneous detection of multiple exogenous hormones due to complex spectral overlap and matrix interference, limiting its application in trace analyte analysis within complex matrices (e.g., biological samples). This study developed a SERS substrate based on carboxyl-terminal polyethylene glycol (PEG)-modified iron oxide (Fe3O4) nanoparticles (Fe3O4@PEG), integrated with artificial intelligence (AI)-driven high-throughput spectral analysis algorithms. This approach successfully enabled ultrasensitive detection and precise discrimination of multiple typical exogenous hormonal drugs, including tamoxifen, drospirenone, cyproterone acetate, medroxyprogesterone acetate, estradiol ester derivatives, and dydrogesterone. By optimizing the surface enhancement effect of Fe3O4@PEG nanocomposites and employing machine learning models (e.g., convolutional neural networks, CNN) for collaborative analysis, the weak Raman fingerprint features of target hormones in complex mixtures were effectively extracted and classified, achieving a detection limit at the corresponding to 10-7-10-8 mg/mL level. In matrix-spiked serum and urine samples, which mimic complex biological matrices validations, the AI-SERS platform demonstrated exceptional performance in the identification and quantitative analysis of target exogenous hormones. This research provides an intelligent analytical strategy for rapid and highly sensitive detection of multiple trace exogenous hormones in complex matrices.