Rapid FTIR Spectral Fingerprinting of Kidney Allograft Perfusion Fluids Distinguishes DCD from DBD Donors: A Pilot Machine Learning Study
Performance in this 10-sample pilot should be interpreted cautiously, as perfect leave-one-out cross-validation (LOOCV) estimates are vulnerable to overfitting. The findings are preliminary and hypothesis-generating, and they require confirmation in larger, multicenter cohorts with a pre-registered analysis pipeline and external validation.
Authors
- Miguel Bigotte Vieira (ORCID: https://orcid.org/0000-0003-0528-2716)
- Aníbal Ferreira (ORCID: https://orcid.org/0000-0002-3300-6033)
- Luís Ramalhete (ORCID: https://orcid.org/0000-0002-8911-3380)
- Sofia Carrelha
- Cecília R. C. Calado (ORCID: https://orcid.org/0000-0002-5264-9755)
- Ruben Araújo (ORCID: https://orcid.org/0000-0002-9369-6486)
- Emanuel Vigia (ORCID: https://orcid.org/0000-0002-4525-9062)
- Ana Pena
Institutions
- University of Lisbon (PT)
- Universidade Politécnica de Lisboa (PT)
- Portuguese Army (PT)
- Unidade Local de Saúde de São José (PT)
- Nova Medical (United States) (US)
- Centro Hospitalar Lisboa Norte (PT)
- Hospital Curry Cabral (PT)
- Instituto Superior de Tecnologias Avançadas (PT)
- Institute for Biotechnology and Bioengineering (PT)
- Instituto Superior Técnico (PT)
- Universidade Nova de Lisboa (PT)
Publication Details
- Journal
- Metabolites
- Published
- 2025-10-29
- DOI
- https://doi.org/10.3390/metabo15110702
- Primary Topic
- Spectroscopy Techniques in Biomedical and Chemical Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00