Serum Raman spectroscopy as a blood-based triage test for bladder cancer: a retrospective proof-of-concept study

Dried-serum Raman spectroscopy with supervised machine learning distinguishes bladder cancer from symptomatic controls with AUC about 0.90, improving slightly to about 0.91 when age is included.

• Why it matters: Cystoscopy is invasive and resource-intensive, so a rapid blood-based triage test could better stratify patients before proceeding to invasive diagnostics.
• What they did: Archived serum from 49 histologically confirmed bladder cancer patients and 97 symptomatic controls was measured by dried-serum Raman spectroscopy, then spectra were used in classification models with ROC-based evaluation.
• The result: Predicted probabilities were substantially higher in cancer patients, and the Raman classifier’s discrimination suggests feasibility for a minimally invasive triage test pending prospective validation.

AI summary of the abstract · may contain errors · not medical advice · read the paper.