Random forest models accurately classify synthetic opioids using high-dimensionality mass spectrometry datasets

Analytical Methods 2026 Open access

Read full text
Authors: Kourosh Arasteh, Steven Magana-Zook, Colin Ponce, Roald N. Leif, A. Carsin Vu, Mark L. Dreyer, Brian P. Mayer, Audrey M. Williams, Carolyn L. Fisher
DOI: 10.1039/d5ay01677k
Cited by: 0
References: 23

Abstract

non-opioids, with low false positive and false negative rates. The RF models were then used to successfully predict the classification of 10 compounds-five opioids and five non-opioids not part of the training and validation analysis. This application of ML is a critical step towards the development of field-deployable nominal mass spectrometers with ML-driven analyses for classification of emergent threats.

Fields of Study & Subjects

Mass Spectrometry Techniques and Applications Forensic Toxicology and Drug Analysis Computational Drug Discovery Methods

Publication details

Journal / source
Analytical Methods
Volume
18
Issue
9
Pages
1804–1814
Publication date
1 January 2026
Language
EN