Logo do repositório
 
Publicação

Risk phenotyping before graft implantation: FTIR spectroscopy and machine learning for complementary risk stratification in kidney transplantation

2026-06-27Artigo de investigação Acesso aberto
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Química
datacite.subject.sdg03:Saúde de Qualidade
dc.contributor.authorRamalhete, Luís
dc.contributor.authorAraújo, Rúben Alexandre Dinis
dc.contributor.authorVigia, Emanuel
dc.contributor.authorBigotte Vieira, Miguel
dc.contributor.authorAntunes Ferreira, Manuel Aníbal
dc.contributor.authorCalado, Cecília
dc.date.accessioned2026-10-20T09:58:57Z
dc.date.available2026-10-20T09:58:57Z
dc.date.issued2026-06-27
dc.description.abstractBackground: Rejection remains a major barrier to long-term kidney allograft survival, and pre-transplant risk stratification remains incomplete. This study evaluated whether pre-transplant serum Fourier-transform infrared (FTIR) spectra, analyzed using machine learning methods, could identify kidney transplant recipients at increased risk of subsequent biopsy-proven rejection. Methods: In this retrospective single-center study, 80 pre-transplant serum samples collected on the day of transplantation were initially evaluated; after spectral quality control, 79 samples were retained for analysis. FTIR spectra were acquired in transmission mode and analyzed in the 600–1900 cm−1 and 2800–3400 cm−1 regions. Multiple preprocessing strategies were assessed, including Rubber Band baseline correction, vector normalization, and first- and second-derivative transformation, with and without normalization. Naïve Bayes classifiers with Leave-One-Out Cross-Validation and Fast Correlation-Based Filter feature selection were applied. Results: Exploratory analysis showed broad overlap between groups, indicating a subtle multivariate spectral signal. In the initial exploratory workflow, classifier performance depended strongly on preprocessing and feature selection. Because non-nested feature selection may produce optimistic estimates, the main supervised analysis was repeated using FCBF nested within each LOOCV training fold. The best-performing nested model was obtained using second derivative transformation followed by normalization in the combined 600–1900 and 2800–3400 cm−1 regions, achieving an AUC of 0.837, accuracy of 0.747, sensitivity of 0.675, specificity of 0.821, balanced accuracy of 0.748, and F1-score of 0.730. Permutation testing with 1000 label-randomized repetitions supported performance above chance expectation, with no permuted model reaching the observed AUC (empirical p = 0.000999). Conclusions: Pre-transplant serum FTIR spectroscopy combined with leakage-aware nested machine learning analysis identified an internally validated spectral signal associated with subsequent biopsy-proven rejection. These findings support FTIR as a promising complementary and hypothesis-generating approach for pre-transplant biochemical risk phenotyping, requiring external multicenter validation before clinical application.eng
dc.identifier.citationRamalhete, L., Araújo, R., Vigia, E., Vieira, M. B., Ferreira, A., & Calado, C. R. C. (2026). Risk Phenotyping Before Graft Implantation: FTIR Spectroscopy and Machine Learning for Complementary Risk Stratification in Kidney Transplantation. Medical Sciences, 14(3), 353. https://doi.org/10.3390/medsci14030353
dc.identifier.doi10.3390/medsci14030353
dc.identifier.eissn2076-3271
dc.identifier.urihttp://hdl.handle.net/10400.21/23232
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI
dc.relation.hasversionhttps://www.mdpi.com/2076-3271/14/3/353
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectKidney transplantation
dc.subjectRejection
dc.subjectFTIR spectroscopy
dc.subjectSerum
dc.subjectMachine learning
dc.titleRisk phenotyping before graft implantation: FTIR spectroscopy and machine learning for complementary risk stratification in kidney transplantationeng
dc.typeresearch article
dspace.entity.typePublication
oaire.citation.issue3
oaire.citation.titleMedical Sciences
oaire.citation.volume14
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameRamalhete
person.familyNameAraújo
person.familyNameVigia
person.familyNameBigotte Vieira
person.familyNameAntunes Ferreira
person.familyNameCalado
person.givenNameLuís
person.givenNameRúben Alexandre Dinis
person.givenNameEmanuel
person.givenNameMiguel
person.givenNameManuel Aníbal
person.givenNameCecília
person.identifier2296066
person.identifier591378
person.identifier130332
person.identifier.ciencia-idDF19-022D-AA10
person.identifier.ciencia-id9A18-BFDC-ED95
person.identifier.ciencia-idE918-DF3E-1A17
person.identifier.ciencia-idFF17-2C76-E2CC
person.identifier.ciencia-id2E10-C387-4982
person.identifier.ciencia-id9418-E320-3177
person.identifier.orcid0000-0002-8911-3380
person.identifier.orcid0000-0002-9369-6486
person.identifier.orcid0000-0002-4525-9062
person.identifier.orcid0000-0003-0528-2716
person.identifier.orcid0000-0002-3300-6033
person.identifier.orcid0000-0002-5264-9755
person.identifier.ridV-4629-2018
person.identifier.ridE-2102-2014
person.identifier.scopus-author-id57208672678
person.identifier.scopus-author-id57192837006
person.identifier.scopus-author-id6603163260
relation.isAuthorOfPublication7846e088-851e-47b6-a7bd-d02c9d8f047d
relation.isAuthorOfPublication9998e940-5e65-4661-8308-afcb56d5df01
relation.isAuthorOfPublicationb5171a62-8862-4ff8-b855-f6b165a95b89
relation.isAuthorOfPublication64821681-4391-45e3-a4da-2ef3869a6ead
relation.isAuthorOfPublication14da9d0c-6486-42be-be91-5fc6a965533f
relation.isAuthorOfPublicatione8577257-c64c-4481-9b2b-940fedb360cc
relation.isAuthorOfPublication.latestForDiscoverye8577257-c64c-4481-9b2b-940fedb360cc

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Risk phenotyping_CRCCalado.pdf
Tamanho:
1.42 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ISEL - Eng. Quim. Biol. - Artigos