Semi-Quantitative Estimation of MDMA Tablet Dosage and Cocaine/Ketamine Purity Using a Simple to Operate Field-Portable Device
Matthew Gardner, Alexander Power, Anca Frinculescu, Molly F. Millea, Gyles Cozier, Stephen Husbands, Oliver B. Sutcliffe, Christopher R. Pudney
ChemRxiv June 9, 2026 Peer reviewed DOI: 10.26434/chemrxiv.15004519/v1 via OpenAlex
Summary
A new field-portable device using Hybridized Spectral Fingerprinting and deep learning models can accurately assess MDMA tablet dosages and the purity of cocaine and ketamine samples. The device achieved 98% accuracy in classifying MDMA dosages from 62 samples and 96% accuracy in estimating the purity of cocaine and ketamine from 47 samples. This technology could enhance harm reduction efforts and assist police in drug screening.
Study at a glance
| Sample size | 62 |
|---|---|
| Population | MDMA tablet samples and cocaine/ketamine samples |
| Key finding | The device demonstrated 98% accuracy for MDMA dosage classification and 96% accuracy for cocaine and ketamine purity estimation. |
Abstract
High-dose MDMA tablets and variable-purity cocaine and ketamine samples are commonly encountered by drug checking services and police forces in the United Kingdom and Europe. At the time of writing, there are few simpleto-operate field-portable technologies that provide semi-quantitative information on MDMA tablet dosage or cocaine and ketamine purity at the point of sampling. We previously reported on the development of a low-cost, fieldportable device that can be used to rapidly screen illicit drug samples through Hybridized Spectral Fingerprinting (HSF); the combined measurement of fluorescence emission and diffuse LED reflectance. Here, we describe the development and testing of deep learning models for both MDMA tablet dosage and cocaine/ketamine purity that can be used in on this device in the field. We used 62 GC-EI-MS quantified MDMA tablet samples to train a convolutional neural network model to classify tablet samples in either 1–170 mg or 170–300 mg MDMA HCl dosage brackets. External testing on 195 positive and negative MDMA samples yielded a 98% device accuracy. We used 1H NMR quantified cocaine and ketamine samples to train a second convolutional neural network model for presumptive identification and semi-quantitative purity estimation of cocaine and ketamine samples, yielding an accuracy of 96% on an external test set of 47 samples. These findings demonstrate that Hybridized Spectral Fingerprinting paired with deep learning can be reliably used to alert on potentially harmful MDMA tablets and estimate the purity of cocaine and ketamine samples, supporting harm reduction activities and police screening or intelligence gathering workflows.