Toward automated infrared spectral analysis in community drug checking
| dc.contributor.author | Gozdzialski, Lea | |
| dc.contributor.author | Hutchison, Abby | |
| dc.contributor.author | Wallace, Bruce | |
| dc.contributor.author | Gill, Chris | |
| dc.contributor.author | Hore, Dennis | |
| dc.date.accessioned | 2024-03-21T15:54:03Z | |
| dc.date.available | 2024-03-21T15:54:03Z | |
| dc.date.issued | 2023 | |
| dc.description | High performance computing support and server resource allocation was provided by the University of Victoria. We also acknowledge all the Substance staff and service users as the driving force of this work. Many people have contributed to acquiring and interpreting this dataset. We are extremely grateful for the trust of community members in their donation of drug samples. | |
| dc.description.abstract | The body of knowledge surrounding infrared spectral analysis of drug mixtures continues to grow alongside the physical expansion of drug checking services. Technicians trained in the analysis of spectroscopic data are essential for reasons that go beyond the accuracy of the analytical results. Significant barriers faced by people who use drugs in engaging with drug checking services include the speed and accuracy of the results, and the availability and accessibility of the service. These barriers can be overcome by the automation of interpretations. A random forest model for the detection of two compounds, MDA and fluorofentanyl, was trained and optimized with drug samples acquired at a community drug checking site. This resulted in a 79% true positive and 100% true negative rate for MDA, and 61% true positive and 97% true negative rate for fluorofentanyl. The trained models were applied to selected drug samples to demonstrate a proposed workflow for interpreting and validating model predictions. The detection of MDA was demonstrated on three mixtures: (1) MDMA and MDA, (2) MDA and dimethylsulfone, and (3) fentanyl, etizolam, and benzocaine. The classification of fluorofentanyl was applied to a drug mixture containing fentanyl, fluorofentanyl, 4-anilino-N-phenethylpiperidine, caffeine, and mannitol. Feature importance was calculated using shapely additive explanations to better explain the model predictions and k-nearest neighbors was used for visual comparison to labelled training data. This is a step toward building appropriate trust in computer-assisted interpretations in order to promote their use in a harm reduction context. | |
| dc.description.reviewstatus | Reviewed | |
| dc.description.scholarlevel | Faculty | |
| dc.description.sponsorship | This project was funded by a grant from Health Canada's Substance Use and Addictions Program (SUAP), with additional support from the Vancouver Foundation. | |
| dc.identifier.citation | Gozdzialski, L., Hutchison, A., Wallace, B., Gill, C. G., & Hore, D. K. (2023). Toward automated infrared spectral analysis in community drug checking. Drug Testing and Analysis. https://doi.org/10.1002/dta.3520 | |
| dc.identifier.uri | https://doi.org/10.1002/dta.3520 | |
| dc.identifier.uri | https://hdl.handle.net/1828/16259 | |
| dc.language.iso | en | |
| dc.publisher | Drug Testing and Analysis | |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | Canadian Institute for Substance Use Research (CISUR) | |
| dc.subject.department | Department of Chemistry | |
| dc.subject.department | School of Public Health and Social Policy | |
| dc.subject.department | School of Social Work | |
| dc.subject.department | Department of Computer Science | |
| dc.title | Toward automated infrared spectral analysis in community drug checking | |
| dc.type | Article |