Por favor, use este identificador para citar o enlazar este ítem: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1188896
Registro completo de metadatos
Campo DCValorLengua/Idioma
dc.contributor.authorDOMINGOS, E. L.
dc.contributor.authorZEIN, A. K. el
dc.contributor.authorSUREK, M.
dc.contributor.authorGRECA JUNIOR, H.
dc.contributor.authorSANTOS‑WEISS, I. C. R. dos
dc.contributor.authorFEIRREIRA, L. M.
dc.contributor.authorPONTAROLO, P.
dc.date.accessioned2026-08-04T14:49:23Z-
dc.date.available2026-08-04T14:49:23Z-
dc.date.created2026-08-04
dc.date.issued2026
dc.identifier.citationAnalytical and Bioanalytical Chemistry, Jul. 2026.
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1188896-
dc.descriptionFeline sporotrichosis is a zoonotic subcutaneous mycosis of major relevance in endemic regions of Latin America, particu- larly in Brazil. Current diagnostic methods are limited by turnaround time, specificity, and cost. In this context, spectros- copy combined with machine learning has emerged as a promising alternative. This study aimed to develop and validate predictive models for the rapid and minimally invasive diagnosis of feline sporotrichosis using ATR-FTIR spectroscopy applied to plasma samples. Seventy-five cats were included and classified by fungal culture as the reference standard. Plasma samples were analyzed by ATR-FTIR (4000–400 cm⁻1 ), with 20 spectra acquired per animal. Data were evaluated using six machine learning algorithms under three validation frameworks: spectral-level internal testing, Leave-One-Patient-Out (LOPO) cross-validation, and independent external validation (n = 15 animals). On the internal test set, Random Forest, KNN, and LightGBM showed similarly strong discriminative ability (AUC ≥ 0.998), with no significant differences among them. The LOPO cross-validation confirmed biological generalization, with SVM achieving the highest AUC (0.896). External validation confirmed consistent performance, with Random Forest and LightGBM achieving an AUC of 1.000 and excellent probabilistic calibration (low Brier scores). Spectral variable importance and SHAP analyses revealed that discrimination was primarily driven by regions associated with carbohydrates (1040–1050 cm⁻1 ) and lipids (1746–1751 cm⁻1 ), reflecting the host’s systemic metabolic and immunological response to the infection. These findings suggest that ATR-FTIR combined with machine learning provides consistent and generalizable diagnostic performance, representing a rapid and minimally invasive approach within the One Health framewor.
dc.language.isoeng
dc.rightsopenAccess
dc.subjectEsporotricose felina
dc.subjectEspectroscopia ATR-FTIR
dc.subjectModelo de diagnóstico
dc.subjectAprendizado de máquina
dc.subjectSaúde Única
dc.subjectAmostras de plasma
dc.titleRapid identification of feline sporotrichosis by ATR‑FTIR spectroscopy coupled with machine learning.
dc.typeArtigo de periódico
dc.subject.thesagroGato
dc.subject.thesagroDoença Animal
dc.subject.nalthesaurusAnimal diseases
dc.description.notesOn-line
riaa.ainfo.id1188896
riaa.ainfo.lastupdate2026-08-04
dc.identifier.doihttps://doi.org/10.1007/s00216-026-06671-3
dc.contributor.institutionERIC LUIZ DOMINGOS, UNIVERSIDADE FEDERAL DO PARANÁ
dc.contributor.institutionAHMAD KASSEM EL ZEIN, UNIVERSIDADE FEDERAL DO PARANÁeng
dc.contributor.institutionMONICA SUREK, CPATSAeng
dc.contributor.institutionHAROLDO GRECA JUNIOR, SECRETARIA MUNICIPAL DE SAÚDE DE SÃO JOSÉ DOS PINHAISeng
dc.contributor.institutionIZABELLA CASTILHOS RIBEIRO DOS SANTOS‑WEISS, UNIVERSIDADE FEDERAL DO PARANÁeng
dc.contributor.institutionLUANA MOTA FERREIRA, UNIVERSIDADE FEDERAL DO PARANÁeng
dc.contributor.institutionROBERTO PONTAROLO, UNIVERSIDADE FEDERAL DO PARANÁ.eng
Aparece en las colecciones:Artigo em periódico indexado (CPATSA)

Ficheros en este ítem:
Fichero TamañoFormato 
Rapid-identification-of-feline-sporotrichosis-by-ATRFTIR-spectroscopy-coupled-with-machine-learning..pdf2,97 MBAdobe PDFVisualizar/Abrir
Mostrar el registro sencillo del ítem

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace