Using Cluster Analysis and ICP‐MS to Identify Groups of Ecstasy Tablets in Sao Paulo State,Brazil |
| |
| Authors: | Camila Maione M.Sc. Vanessa Cristina de Oliveira Souza M.Sc. Loraine Rezende Togni M.Sc. José Luiz da Costa Ph.D. Andres Dobal Campiglia Ph.D. Fernando Barbosa Ph.D. Jr. Rommel Melgaço Barbosa Ph.D. |
| |
| Affiliation: | 1. Instituto de Informática, Universidade Federal de Goiás, Goiania, Goiás, Brazil;2. Laboratório de Toxicologia e Essencialidade de Metais, Departamento de Análises Clínicas, Toxicológicas e Bromatológicas, Faculdade de Ciências Farmacêuticas de Ribeir?o Preto‐USP, Ribeir?o Preto, S?o Paulo, Brazil;3. Laboratório de Química e Toxicologia Forense, Instituto de Criminalística de S?o Paulo, S?o Paulo, S?o Paulo, Brazil;4. Centro de Controle de Intoxica??o, Universidade de Campinas, Campinas, S?o Paulo, Brazil;5. Department of Chemistry, University of Central Florida, Orlando, FL;6. National Center for Forensic Science, University of Central Florida, Orlando, FL;7. Additional information and reprint requests:;8. Rommel Melga?o Barbosa, Ph.D.;9. Instituto de Informática;10. Universidade Federal de Goiás;11. Goiania, Goiás;12. Brazil;13. E‐mail: |
| |
| Abstract: | The variations found in the elemental composition in ecstasy samples result in spectral profiles with useful information for data analysis, and cluster analysis of these profiles can help uncover different categories of the drug. We provide a cluster analysis of ecstasy tablets based on their elemental composition. Twenty‐five elements were determined by ICP‐MS in tablets apprehended by Sao Paulo's State Police, Brazil. We employ the K‐means clustering algorithm along with C4.5 decision tree to help us interpret the clustering results. We found a better number of two clusters within the data, which can refer to the approximated number of sources of the drug which supply the cities of seizures. The C4.5 model was capable of differentiating the ecstasy samples from the two clusters with high prediction accuracy using the leave‐one‐out cross‐validation. The model used only Nd, Ni, and Pb concentration values in the classification of the samples. |
| |
| Keywords: | forensic science forensic toxicology ecstasy inductively coupled plasma mass spectrometry chemometrics clustering data mining |
|
|
