Sci Adv. 2026 Jul 3;12(27):eaee3487. doi: 10.1126/sciadv.aee3487. Epub 2026 Jul 1.
ABSTRACT
Achieving noninvasive high-frequency monitoring of ischemic stroke (IS) remains a major clinical challenge for timely intervention and precise secondary prevention. Establishing precise correlations between patients' systemic microscopic molecular fingerprints and localized macroscopic organ pathological events is essential to overcome the limitations of single-modal detection and enhance the efficacy of clinical risk assessment. However, because of the complexity of heterogeneous data, effectively integrating the cross-dimensional "molecular imaging" data remains a critical bottleneck in achieving this goal. Here, we present a proof-of-concept method to distinguish patients with confirmed IS from healthy controls (HCs) that used machine learning (ML)-based methods to surface-enhanced Raman spectroscopy (SERS) of urine (one-dimensional) and carotid artery B-ultrasound imaging (CBI) (two-dimensional). In an exploratory cohort of 101 participants, this approach analyzed 10,100 SERS spectra and 481 CBI images, achieving 92% classification accuracy and an area under the curve (AUC) of 0.95. Furthermore, by combined SERS spectra and liquid chromatography-mass spectrometry technology, this study preliminarily explored the urinary biomarker differences between HC/IS groups. The multidimensional data fusion strategy proposed in this study effectively bridges the information gap between traditional molecular detection and clinical phenotypes by systematically correlating microfluidic biomarkers with macro-organ imaging features. This approach provides a previously unexplored, noninvasive, and highly accurate tool for risk stratification and clinical decision-making in classifying HC/IS groups.
PMID:42384817 | DOI:10.1126/sciadv.aee3487