Academic Journal
Use of a machine learning approach to estimate pathobiological effects of crack cocaine administration in rats.
| Τίτλος: | Use of a machine learning approach to estimate pathobiological effects of crack cocaine administration in rats. |
|---|---|
| Συγγραφείς: | de Souza DV; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Rosario BDA; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., de Aguiar GC; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Avanci LDS; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Aguiar O Jr; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Viana MB; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Cury PR; Department of Periodontics, Federal University of Bahia, Salvador, BA, Brazil., Fonseca G; Sea Sciences, Federal University of São Paulo, UNIFESP, Santos, SP, Brazil., Ribeiro DA; Departments of Biosciences and Federal University of São Paulo, UNIFESP, Santos, SP, Brazil. |
| Πηγή: | Xenobiotica; the fate of foreign compounds in biological systems [Xenobiotica] 2025 Sep; Vol. 55 (9), pp. 679-686. Date of Electronic Publication: 2025 Nov 14. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Informa Healthcare Country of Publication: England NLM ID: 1306665 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1366-5928 (Electronic) Linking ISSN: 00498254 NLM ISO Abbreviation: Xenobiotica Subsets: MEDLINE |
| Imprint Name(s): | Publication: London : Informa Healthcare Original Publication: London, Taylor & Francis. |
| Ιατρικοί όροι (MeSH): | Crack Cocaine*/toxicity , Crack Cocaine*/administration & dosage , Machine Learning*, Animals ; Rats ; Male ; Administration, Inhalation |
| Περίληψη: | This study aimed to apply a machine learning workflow to identify the most relevant biological parameters for predicting both the dose and the route of crack cocaine administration.Seventeen variables were evaluated in rats exposed to different doses of crack cocaine, either intraperitoneally (18 or 36 mg/kg, i.p.) or via passive inhalation (25, 50, or 100 mg). Random forest (RF) analysis was used to build predictive models, feature importance analysis to identify key variables, and interaction dependence analysis to explore relationships among variables.Eighty percent of the data was used for training and 20% for testing. The model achieved 85% accuracy in the training phase and 100% in the test phase. During training, the highest accuracy was observed for the 100 mg inhaled group, while the lowest was for the 50 mg inhaled group. Notably, 20% of the 50 mg i.p. cases were misclassified as 36 mg i.p. Feature importance analysis highlighted four key predictors: liver karyolysis, kidney Ki-67 expression, liver binucleation, and escape behaviour.These findings demonstrate that machine learning (ML) can accurately predict both dose and route of crack cocaine exposure, and can highlight biologically relevant parameters involved in the drug's systemic and behavioural effects. |
| Contributed Indexing: | Keywords: Crack cocaine; experimental model; holistic approach; rat |
| Substance Nomenclature: | 0 (Crack Cocaine) |
| Entry Date(s): | Date Created: 20251102 Date Completed: 20251217 Latest Revision: 20251217 |
| Update Code: | 20260130 |
| DOI: | 10.1080/00498254.2025.2582125 |
| PMID: | 41176720 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1366-5928 |
|---|---|
| DOI: | 10.1080/00498254.2025.2582125 |