@article{ref1,
title="Toward a personal drug detection assistant: machine learning for detection of synthetic cannabinoid receptor agonists",
journal="Clinical chemistry",
year="2022",
author="Haymond, Shannon",
volume="ePub",
number="ePub",
pages="ePub-ePub",
abstract="Detection of novel psychoactive substances such as synthetic cannabinoid receptor agonists (SCRAs) is a worldwide problem with serious clinical and public health implications. Rapid, low-cost, and accurate screening methods are needed but are fraught with challenges. Activity-based bioassays coupled with machine learning (ML) to automate profile interpretation may be a promising approach.ML is a type of artificial intelligence that enables a computer program to identify a mathematical model to accurately describe the relationship between input data and desired outputs, without human intervention or programming. It is particularly promising for revealing complex and nonlinear relationships that may exceed human capacity for recognition. That said, it is important to note that the recent progress in the development and uptake of ML is relegated to solving specific, targeted problems, for which algorithms are expressly designed and validated.<p /> <p>Language: en</p>",
language="en",
issn="0009-9147",
doi="10.1093/clinchem/hvac071",
url="http://dx.doi.org/10.1093/clinchem/hvac071"
}