Repository logo
 
Publication

Non-invasive bladder cancer detection: identification of a urinary volatile biomarker panel using GC-MS metabolomics and machine learning

2026-01-01Research article Open access
Simple item page
dc.contributor.authorCarapito, Â.
dc.contributor.authorFerreira, V. S. Fernandes
dc.contributor.authorFerreira, A. C. Silva
dc.contributor.authorTeixeira-Marques, A.
dc.contributor.authorHenrique, R.
dc.contributor.authorJerónimo, C.
dc.contributor.authorRoque, A. C. A.
dc.contributor.authorCarvalho, F.
dc.contributor.authorPinto, J.
dc.contributor.authorPinho, P. Guedes de
dc.date.accessioned2025-09-17T06:47:25Z
dc.date.available2025-09-17T06:47:25Z
dc.date.issued2026-01-01
dc.description.abstractEarly detection of bladder cancer (BC) remains a major clinical challenge due to the limitations of current diagnostic methods, which are often invasive, expensive, or insufficiently sensitive, particularly for early-stage disease. Metabolomics approaches, when integrated with machine learning (ML) techniques, offer a powerful platform for identifying novel, non-invasive biomarkers. In this study, urinary volatile organic compounds (VOCs) were analysed from 87 BC patients and 90 age- and sex-matched cancer-free controls using headspace solid-phase microextraction coupled with gas chromatography–mass spectrometry (HS-SPME/GC-MS). Of the 90 VOCs identified, 27 were selected and used to train five ML algorithms—random forest (RF), support vector machine (SVM), partial least squares-discriminant analysis (PLS-DA), extreme gradient boosting (XGBoost), and k-nearest neighbors (k-NN). Model performance was evaluated using cross-validation and an independent validation set, with metrics including area under the curve (AUC), sensitivity, specificity, and accuracy. RF achieved the highest performance using all 27 features (AUC = 0.913; sensitivity, specificity, and accuracy = 85 %). After feature selection, an eight-VOC panel improved performance on the validation set (AUC = 0.872; sensitivity = 89 %, specificity = 92 %, accuracy = 91 %). The panel included ketones, aldehydes, a short fatty alcohol, and a phenol compound—seven elevated in BC, and one (acetone) decreased. This panel outperformed FDA-approved urinary assays and closely matched the specificity of urine cytology. These findings underscore the promise of VOC-based urinary biomarkers, in combination with ML, for the non-invasive detection of BC. Further large-scale validation studies are essential to confirm diagnostic utility and enable clinical translation.eng
dc.identifier.citationCarapito, Â., Ferreira, V. S. F., Ferreira, A. C. S., & Teixeira-Marques, A. et al. (2026). Non-invasive bladder cancer detection: identification of a urinary volatile biomarker panel using GC-MS metabolomics and machine learning. Talanta, 297, Article 128749. https://doi.org/10.1016/j.talanta.2025.128749
dc.identifier.doi10.1016/j.talanta.2025.128749
dc.identifier.eid105014750654
dc.identifier.issn0039-9140
dc.identifier.other304def1c-2351-4e01-8a5d-397cddd9fe4d
dc.identifier.pmid40907368
dc.identifier.urihttp://hdl.handle.net/10400.14/54992
dc.identifier.wos001567306300001
dc.language.isoeng
dc.peerreviewedyes
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectBladder cancer
dc.subjectEarly detection
dc.subjectGas chromatography-mass spectrometry
dc.subjectMachine learning
dc.subjectMetabolomics
dc.subjectUrinary biomarkers
dc.subjectVolatile organic compounds
dc.titleNon-invasive bladder cancer detection: identification of a urinary volatile biomarker panel using GC-MS metabolomics and machine learningeng
dc.typeresearch article
dspace.entity.typePublication
oaire.citation.titleTalanta
oaire.citation.volume297
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
128643098.pdf
Size:
1.49 MB
Format:
Adobe Portable Document Format
Download

Collections

CBQF - Contribuições em Revistas Científicas / Contribution to Journals