Choosing between quantum cascade lasers (QCL) equipping a new holow fiber infrared scanner designed to detect new psychoactive substances (NPS)

Disorders related to the use of new psychoactive drugs (NPS) such as amphetamines account for a considerable share of the hospital admissions and fatalities attributable to drug use disorders, second only to those related to the abuse of opioids. According to the World Drug Report 2017 elaborated by the United Nations Office on Drugs and Crime (UNODC), amphetamine-like stimulants (ATS) such as methamphetamine represent the greatest global health threat. Hallucinogenic amphetamines, such as 3,4-methylenedioxyamphetamine (MDA) and its analogues, account for an even larger number of fatalities. The latter compounds have no medical use and are controlled substances in most countries. However, despite their high toxicity, they are abused during rave parties for their euphoriant effect. Hence, new analytical instruments, allowing a more effective in-situ screening for NPS are highly needed. The most important challenge for such forensic instruments is their capacity to scan not only for the known NPS, but also for any compound having a molecular structure (hence a pharmacological activity) similar to the already known and controlled drugs of abuse. Such a new instrument, built within the DIRAC EU funded project, consists of a hollow fiber infrared spectrometer. In order to maximize its compactivity, the radiation source of this spectrometer is a quantum cascade laser (QCL). On the other hand, the use of a laser source of infrared radiation raises another challenge, i.e. obtaining the same detection efficiency as in the case of spectrometers generating the full infrared spectrum, despite the narrow spectral window in which QCLs are emitting. In this paper we are presenting the results obtained for two experimental setups, which were compared in order to find the most appropriate infrared source. Two QCLs, emitting in the spectral windows of 1550-1330 cm⁻¹ (UT7) and 1405-1150 cm⁻¹ (UT8) respectively, have been evaluated by using Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA). The initial database consisted of normalized spectra of the main ATS, hallucinogenic amphetamines and a similar number of negatives, representing miscellaneous substances of forensic interest. The dataset obtained by preprocessing these spectra with a w²_MT feature weight has been used for the training process. The PCA plots have indicated the QCL generating the best clustering and which are the main absorptions that ensure a high quality class identity assignment. The potential cluster overlap has been assessed based on the estimated density distributions calculated with a normal kernel function. The results have been validated by using HCA, the quality of the clustering trees being assessed based on the cophenetic correlation coefficient.