A study led by researchers from the University of Oxford describes the first method that can distinguish between genuine and counterfeit vaccines by applying machine learning to mass spectral data. The method proved effective in distinguishing between a range of genuine and “fake” vaccines seen entering the supply chain so far.
The results of the study are: npj vaccineprovides a proof-of-concept method that can be scaled to address the urgent need for more effective global vaccine supply chain screening. A key advantage is that it uses clinical mass spectrometers that are already distributed worldwide for medical diagnostics.
The paper is titled, “Using matrix-assisted laser desorption ionization mass spectrometry combined with machine learning for vaccine authenticity screening.”
People around the world are increasingly reliant on vaccines to keep their populations healthy, with billions of doses of vaccines used each year in immunization programs around the world. The vast majority of vaccines are of excellent quality. However, the rise of substandard and counterfeit vaccines poses a threat to global public health.
Not only do these fail to treat the disease they are intended to treat, but they can also cause serious health problems, including death, and undermine confidence in vaccines. Unfortunately, there is currently no global infrastructure to monitor the supply chain using screening methods developed to identify ineffective vaccines.
In the new study, researchers developed and tested a method that can distinguish genuine from counterfeit vaccines, using equipment developed to identify bacteria in hospital microbiology labs.
The method is based on matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS), a technique that identifies components of a sample by separating their constituent molecules through electrical charge. The MALDI-MS analysis is then combined with open-source machine learning.
This provides a reliable multi-component model that can distinguish genuine from counterfeit vaccines without relying on a single marker or chemical component.
The method successfully distinguished between a range of genuine vaccines, including those for influenza, hepatitis B virus and meningococcal infection, and solutions commonly used in counterfeit vaccines, such as sodium chloride.
Study co-leader Professor James McCullagh, Professor of Biochemistry in the Department of Chemistry at the University of Oxford, said: “We're really excited to see the effectiveness of this method and its potential for deployment in screening real-world vaccines for authenticity.”
“This marks an important milestone for the Vaccine Identity Evaluation (VIE) Consortium, which is supported by multiple research partners, including the World Health Organization (WHO), medicines regulators and vaccine manufacturers, and is focused on developing and evaluating innovative devices to detect counterfeit and substandard vaccines.”
More information:
Rebecca Clark et al. “Using Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Combined with Machine Learning for Vaccine Authenticity Screening” npj vaccine (2024). DOI: 10.1038/s41541-024-00946-5
Courtesy of University of Oxford
Citation: Proof-of-concept method uses machine learning to detect fake vaccines in the supply chain (August 29, 2024) Retrieved August 29, 2024 from https://medicalxpress.com/news/2024-08-proof-concept-method-machine-fake.html
This document is subject to copyright. It may not be reproduced without written permission, except for fair dealing for the purposes of personal study or research. The content is provided for informational purposes only.