The metabolic clock of ketamine abuse in rats by a machine learning model

Abstract

Abstract Ketamine has recently become an anesthetic drug used in human and veterinary clinical medicine for illicit abuse worldwide, but the detection of illicit abuse and inference of time intervals following ketamine abuse are challenging issues in forensic toxicological investigations. Here, we developed methods to estimate time intervals since ketamine use is based on significant metabolite changes in rat serum over time after a single intraperitoneal injection of ketamine, and global metabolomics was quantified by ultra-performance liquid chromatography-quadrupole-time-of-flight mass spectrometry (UPLC-Q-TOF–MS). Thirty-five rats were treated with saline (control) or ketamine at 3 doses (30, 60, and 90 mg/kg), and the serum was collected at 21 time points (0 h to 29 d). Time-dependent rather than dose-dependent features were observed. Thirty-nine potential biomarkers were identified, including ketamine and its metabolites, lipids, serotonin and other molecules, which were used for building a random forest model to estimate time intervals up to 29 days after ketamine treatment. The accuracy of the model was 85.37% in the cross-validation set and 58.33% in the validation set. This study provides further understanding of the time-dependent changes in metabolites induced by ketamine abuse.

Keywords

• Ketamine
• Inference of time interval
• Metabolomics
• Drug abuse
• Machine learning