Analysis of Wastewater Samples to Explore Community Substance Use in the United States: Pilot Correlative and Machine Learning Study

Abstract

Background Substance use disorder and associated deaths have increased in the United States, but methods for detecting and monitoring substance use using rapid and unbiased techniques are lacking. Wastewater-based surveillance is a cost-effective method for monitoring community drug use. However, the examination of the results often focuses on descriptive analysis. Objective The objective of this study was to explore community substance use in the United States by analyzing wastewater samples. Geographic differences and commonalities of substance use were explored. Methods Wastewater was sampled across the United States (n=12). Selected drugs with misuse potential, prescriptions, and over-the-counter drugs and their metabolites were tested across geographic locations for 7 days. Methods used included wastewater assessment of substances and metabolites paired with machine learning, specifically discriminant analysis and cluster analysis, to explore similarities and differences in wastewater measures. Results Geographic variations in the wastewater drug or metabolite levels were found. Results revealed a higher use of methamphetamine (z=–2.27, P=.02) and opioids-to-methadone ratios (oxycodone-to-methadone: z=–1.95, P=.05; hydrocodone-to-methadone: z=–1.95, P=.05) in states west of the Mississippi River compared to the east. Discriminant analysis suggested temazepam and methadone were significant predictors of geographical locations. Precision, sensitivity, specificity, and F1-scores were 0.88, 1, 0.80, and 0.93, respectively. Finally, cluster analysis revealed similarities in substance use among communities. Conclusions These findings suggest that wastewater-based surveillance has the potential to become an effective form of surveillance for substance use. Further, advanced analytical techniques may help uncover geographical patterns and detect communities with similar needs for resources to address substance use disorders. Using automated analytics, these advanced surveillance techniques may help communities develop timely, tailored treatment and prevention efforts.