Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 873.29 KB
Add to list
  1. Search results
  2. Machine learning to assist in large-s...

Machine learning to assist in large-scale, activity-based synthetic cannabinoid receptor agonist screening of serum samples

Liesl Janssens (UGent) , Dimitri Boeckaerts (UGent) , Simon Hudson, Daria Morozova, Annelies Cannaert (UGent) , David M. Wood, Caitlin Wolfe, Bernard De Baets (UGent) , Michiel Stock (UGent) , Paul, I Dargan, et al.
(2022) CLINICAL CHEMISTRY. 68(7). p.906-916
Author
Organization
Project
Abstract
Background Synthetic cannabinoid receptor agonists (SCRAs) are amongst the largest groups of new psychoactive substances (NPS). Their often high activity at the CB1 cannabinoid receptor frequently results in intoxication, imposing serious health risks. Hence, continuous monitoring of these compounds is important, but challenged by the rapid emergence of novel analogues that are missed by traditional targeted detection strategies. We addressed this need by performing an activity-based, universal screening on a large set (n = 968) of serum samples from patients presenting to the emergency department with acute recreational drug or NPS toxicity. Methods We assessed the performance of an activity-based method in detecting newly circulating SCRAs compared with liquid chromatography coupled to high-resolution mass spectrometry. Additionally, we developed and evaluated machine learning models to reduce the screening workload by automating interpretation of the activity-based screening output. Results Activity-based screening delivered outstanding performance, with a sensitivity of 94.6% and a specificity of 98.5%. Furthermore, the developed machine learning models allowed accurate distinction between positive and negative patient samples in an automatic manner, closely matching the manual scoring of samples. The performance of the model depended on the predefined threshold, e.g., at a threshold of 0.055, sensitivity and specificity were both 94.0%. Conclusion The activity-based bioassay is an ideal candidate for untargeted screening of novel SCRAs. The combination of this universal screening assay and a machine learning approach for automated sample scoring is a promising complement to conventional analytical methods in clinical practice.
Keywords
computers, drugs of abuse, clinical toxicology, luminescence assays, mass spectrometry, data processing, EMERGENCY-DEPARTMENT, TOXICITY

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 873.29 KB

Citation

Please use this url to cite or link to this publication:

MLA
Janssens, Liesl, et al. “Machine Learning to Assist in Large-Scale, Activity-Based Synthetic Cannabinoid Receptor Agonist Screening of Serum Samples.” CLINICAL CHEMISTRY, vol. 68, no. 7, 2022, pp. 906–16, doi:10.1093/clinchem/hvac027.
APA
Janssens, L., Boeckaerts, D., Hudson, S., Morozova, D., Cannaert, A., Wood, D. M., … Stove, C. (2022). Machine learning to assist in large-scale, activity-based synthetic cannabinoid receptor agonist screening of serum samples. CLINICAL CHEMISTRY, 68(7), 906–916. https://doi.org/10.1093/clinchem/hvac027
Chicago author-date
Janssens, Liesl, Dimitri Boeckaerts, Simon Hudson, Daria Morozova, Annelies Cannaert, David M. Wood, Caitlin Wolfe, et al. 2022. “Machine Learning to Assist in Large-Scale, Activity-Based Synthetic Cannabinoid Receptor Agonist Screening of Serum Samples.” CLINICAL CHEMISTRY 68 (7): 906–16. https://doi.org/10.1093/clinchem/hvac027.
Chicago author-date (all authors)
Janssens, Liesl, Dimitri Boeckaerts, Simon Hudson, Daria Morozova, Annelies Cannaert, David M. Wood, Caitlin Wolfe, Bernard De Baets, Michiel Stock, Paul Dargan I, and Christophe Stove. 2022. “Machine Learning to Assist in Large-Scale, Activity-Based Synthetic Cannabinoid Receptor Agonist Screening of Serum Samples.” CLINICAL CHEMISTRY 68 (7): 906–916. doi:10.1093/clinchem/hvac027.
Vancouver
1.
Janssens L, Boeckaerts D, Hudson S, Morozova D, Cannaert A, Wood DM, et al. Machine learning to assist in large-scale, activity-based synthetic cannabinoid receptor agonist screening of serum samples. CLINICAL CHEMISTRY. 2022;68(7):906–16.
IEEE
[1]
L. Janssens et al., “Machine learning to assist in large-scale, activity-based synthetic cannabinoid receptor agonist screening of serum samples,” CLINICAL CHEMISTRY, vol. 68, no. 7, pp. 906–916, 2022.
@article{8760366,
  abstract     = {{Background Synthetic cannabinoid receptor agonists (SCRAs) are amongst the largest groups of new psychoactive substances (NPS). Their often high activity at the CB1 cannabinoid receptor frequently results in intoxication, imposing serious health risks. Hence, continuous monitoring of these compounds is important, but challenged by the rapid emergence of novel analogues that are missed by traditional targeted detection strategies. We addressed this need by performing an activity-based, universal screening on a large set (n = 968) of serum samples from patients presenting to the emergency department with acute recreational drug or NPS toxicity. Methods We assessed the performance of an activity-based method in detecting newly circulating SCRAs compared with liquid chromatography coupled to high-resolution mass spectrometry. Additionally, we developed and evaluated machine learning models to reduce the screening workload by automating interpretation of the activity-based screening output. Results Activity-based screening delivered outstanding performance, with a sensitivity of 94.6% and a specificity of 98.5%. Furthermore, the developed machine learning models allowed accurate distinction between positive and negative patient samples in an automatic manner, closely matching the manual scoring of samples. The performance of the model depended on the predefined threshold, e.g., at a threshold of 0.055, sensitivity and specificity were both 94.0%. Conclusion The activity-based bioassay is an ideal candidate for untargeted screening of novel SCRAs. The combination of this universal screening assay and a machine learning approach for automated sample scoring is a promising complement to conventional analytical methods in clinical practice.}},
  author       = {{Janssens, Liesl and Boeckaerts, Dimitri and Hudson, Simon and Morozova, Daria and Cannaert, Annelies and Wood, David M. and Wolfe, Caitlin and De Baets, Bernard and Stock, Michiel and Dargan, Paul, I and Stove, Christophe}},
  issn         = {{0009-9147}},
  journal      = {{CLINICAL CHEMISTRY}},
  keywords     = {{computers,drugs of abuse,clinical toxicology,luminescence assays,mass spectrometry,data processing,EMERGENCY-DEPARTMENT,TOXICITY}},
  language     = {{eng}},
  number       = {{7}},
  pages        = {{906--916}},
  title        = {{Machine learning to assist in large-scale, activity-based synthetic cannabinoid receptor agonist screening of serum samples}},
  url          = {{http://doi.org/10.1093/clinchem/hvac027}},
  volume       = {{68}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: