Towards Rapid and Low-Cost Stroke Detection Using SERS and Machine Learning
Biosensors · 2025
DOI: 10.3390/bios15030136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors, 2025. Verfasst von Cristina Freitas und 11 weiteren Autor:innen. Beteiligte Einrichtung: Associate Laboratory i4HB-Institute for Health and Bioeconomy, Faculdade de Ciências e Tecnologia, Universidade NOVA de Lisboa, 2819-516 Caparica, Po…. Hauptthemen laut MEDLINE: Machine Learning, Spectrum Analysis, Raman, Stroke. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e Tecnologia, Laboratório Associado para a Química Verde, Fundação para a Ciência e a Tecnologia, I.P..
Abstract (Originalsprache)
Stroke affects approximately 12 million individuals annually, necessitating swift diagnosis to avert fatal outcomes. Current hospital imaging protocols often delay treatment, underscoring the need for portable diagnostic solutions. We have investigated silver nanostars (AgNS) incubated with human plasma, deposited on a simple aluminum foil substrate, and utilizing Surface-Enhanced Raman Spectroscopy (SERS) combined with machine learning (ML) to provide a proof-of-concept for rapid differentiation of stroke types. These are the seminal steps for the development of low-cost pre-hospital diagnostics at point-of-care, with potential for improving patient outcomes. The proposed SERS assay aims to classify plasma from stroke patients, differentiating hemorrhagic from ischemic stroke. Silver nanostars were incubated with plasma and spiked with glial fibrillary acidic protein (GFAP), a biomarker elevated in hemorrhagic stroke. SERS spectra were analyzed using ML to distinguish between hemorrhagic and ischemic stroke, mimicked by different concentrations of GFAP. Key innovations include optimized AgNS–plasma incubates formation, controlled plasma-to-AgNS ratios, and a low-cost aluminum foil substrate, enabling results within 15 min. Differential analysis revealed stroke-specific protein profiles, while ML improved classification accuracy through ensemble modeling and feature engineering. The integrated ML model achieved rapid and precise stroke predictions within seconds, demonstrating the assay’s potential for immediate clinical decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Associate Laboratory i4HB-Institute for Health and Bioeconomy, Faculdade de Ciências e Tecnologia, Universidade NOVA de Lisboa, 2819-516 Caparica, Portugal.
- UCIBIO-Applied Molecular Biosciences Unit, Departamento de Química, Faculdade de Ciências e Tecnologia, Universidade NOVA de Lisboa, 2819-516 Caparica, Portugal.
- COPELABS-Departamento de Engenharia Informática e Sistemas de Informação, Universidade Lusófona, Centro Universitário de Lisboa, 1749-024 Lisboa, Portugal.
- LAQV/REQUIMTE-Laboratório Associado para a Química Verde/Rede de Química e Tecnologia, Departamento de Química e Bioquímica, Faculdade de Ciências, Universidade do Porto, 4169-007 Porto, Portugal.
- Associate Laboratory i3N, Departamento de Ciência dos Materiais, Faculdade de Ciências e Tecnologia, Universidade NOVA de Lisboa, and CEMOP/UNINOVA, 2829-516 Caparica, Portugal.
ORCID-Profile: Cristina Freitas, Maria Enea, Daniela Nunes, Hugo Águas, Eulália Pereira, Helena L A Vieira, Lúcio Studer Ferreira, Ricardo Franco
Förderung
- Fundação para a Ciência e Tecnologia
- Laboratório Associado para a Química Verde
- Fundação para a Ciência e a Tecnologia, I.P.
- Laboratory Institute of Nanostructures, Nanomodelling and Nanofabrication—i3N
Zitieren
APA
Freitas, C., Eleutério, J., Soares, G., Enea, M., Nunes, D., Fortunato, E., Martins, R., Águas, H., Pereira, E., Vieira, H. L. A., Ferreira, L. S., & Franco, R. (2025). Towards Rapid and Low-Cost Stroke Detection Using SERS and Machine Learning. Biosensors. https://doi.org/10.3390/bios15030136
Vancouver
Freitas C, Eleutério J, Soares G, Enea M, Nunes D, Fortunato E, et al. Towards Rapid and Low-Cost Stroke Detection Using SERS and Machine Learning. Biosensors. 2025. doi:10.3390/bios15030136
BibTeX
@article{Freitas2025,
author = {Freitas, Cristina and Eleutério, João and Soares, Gabriela and Enea, Maria and Nunes, Daniela and Fortunato, Elvira and Martins, Rodrigo and Águas, Hugo and Pereira, Eulália and Vieira, Helena L A and Ferreira, Lúcio Studer and Franco, Ricardo},
title = {Towards Rapid and Low-Cost Stroke Detection Using SERS and Machine Learning},
journal = {Biosensors},
year = {2025},
doi = {10.3390/bios15030136}
}
EUVIMED