Background and aims Novel psychoactive substances are compounds intended to mimic the effects of illicit drugs. They provide a unique challenge to healthcare, as complications of their use and their impact on services are relatively unknown. This study aims to determine nature of presentations, patient demographics and impact on healthcare. Methods Novel psychoactive substances users who presented to a large urban emergency department over 4 weeks were prospectively identified and followed for 1 year. Patients over 13 years old were eligible for inclusion. Information regarding patient demographics and presentations was collected. Results During the study period, 53 patients (39 male), mean age 32.6 ± 8.9 (±standard deviation), presented 148 times with complaints relating to novel psychoactive substances use. Study population characteristics included history of illicit drug use (83.0%), intravenous drug use (64.2%), psychiatric diagnosis or symptoms (56.6%), methadone prescription (52.8%) and having no fixed abode (37.7%). Injection was the most common method of use (72.3%), Burst the most commonly named agent (19.6%) and behavioural change the most common presenting complaint (31.1%). Patients collectively spent 10,620 h in hospital over 1 year. Conclusion This study highlights differences between the young population targeted by government campaigns regarding novel psychoactive substances use and the presenting population to hospital, and the associated burden on the National Health Service.

Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid.