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 M. Husbands, Oliver B Sutcliffe, Christopher R. Pudney
ChemRxiv June 9, 2026 preprint DOI: 10.26434/chemrxiv.15004519/v1 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Observational study with machine learning model development and validation |
|---|---|
| Sample size | 62 |
| Population | GC-EI-MS quantified MDMA tablet samples |
| Topics | Ketamine MDMA Esketamine |
| Keywords | Convolutional neural network Drug detection Illicit drug Pattern recognition psychology Artificial intelligence Artificial neural network Drugs of abuse |
| Key findings | Deep learning models paired with Hybridized Spectral Fingerprinting achieved 98% accuracy for MDMA dosage classification and 96% accuracy for cocaine/ketamine purity estimation on external test sets. |
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.
Comparable studies
Other observational and cohort studies on MDMA, most cited first.
| Study | Year | Design | Participants |
|---|---|---|---|
| Subjective Reports of the Effects of MDMA in a Clinical Setting Individuals who took MDMA in a clinical setting | 1986 | Observational study | |
| Memory impairment in abstinent MDMA ("Ecstasy") users Abstinent MDMA users | 1998 | Observational cohort | |
| Impaired cognitive performance in drug free users of recreational ecstasy (MDMA) Otherwise healthy young people | 2000 | Observational | |
| The Psychological and Physiological Effects of MDMA on Normal Volunteers Older, more educated, drug-experienced individuals | 1986 | Observational cohort | |
| Cognitive performance in recreational users of MDMA or 'ecstasy': evidence for memory deficits Young people who were regular or novice MDMA users, or non-users | 1998 | Observational cohort | n = 30 |