Relapses in Illicit Drug Use Among Probationers: Results in a Risk Group of Public Health Services in Bavaria

Objective: We aimed to identify in this study time trends of relapses in the illicit consumption of narcotics in a special at-risk population of former drug users under a public health perspective. Methods: In a pooled dataset of 14 consecutive calendar years (2006-2019), the use of seven different narcotic substances was studied in 380 persons with a total of 2,928 urine samples which were analyzed using a valid marker system for narcotic residues. Results: During the entire observation period, the relapse rate for cannabinoids and opiates was the highest despite abstinence requirements. It was noticeable that the relapses across all narcotics groups occurred primarily during the first 3 years of the probation period (90%) with a decrease in illegal consumption during the following years of the observation period. Conclusion: Special attention should be paid to probationers at the beginning of the probation period to develop more effective prevention strategies for substance abstinence by all involved actors in public health services.

Interpretable machine learning model to detect chemically adulterated urine samples analyzed by high resolution mass spectrometry

OBJECTIVES

Urine sample manipulation including substitution, dilution, and chemical adulteration is a continuing challenge for workplace drug testing, abstinence control, and doping control laboratories. The simultaneous detection of sample manipulation and prohibited drugs within one single analytical measurement would be highly advantageous. Machine learning algorithms are able to learn from existing datasets and predict outcomes of new data, which are unknown to the model.

METHODS

Authentic human urine samples were treated with pyridinium chlorochromate, potassium nitrite, hydrogen peroxide, iodine, sodium hypochlorite, and water as control. In total, 702 samples, measured with liquid chromatography coupled to quadrupole time-of-flight mass spectrometry, were used. After retention time alignment within Progenesis QI, an artificial neural network was trained with 500 samples, each featuring 33,448 values. The feature importance was analyzed with the local interpretable model-agnostic explanations approach.

RESULTS

Following 10-fold cross-validation, the mean sensitivity, specificity, positive predictive value, and negative predictive value was 88.9, 92.0, 91.9, and 89.2%, respectively. A diverse test set (n=202) containing treated and untreated urine samples could be correctly classified with an accuracy of 95.4%. In addition, 14 important features and four potential biomarkers were extracted.

CONCLUSIONS

With interpretable retention time aligned liquid chromatography high-resolution mass spectrometry data, a reliable machine learning model could be established that rapidly uncovers chemical urine manipulation. The incorporation of our model into routine clinical or forensic analysis allows simultaneous LC-MS analysis and sample integrity testing in one run, thus revolutionizing this field of drug testing.