Using a manifold-based approach to extract clinical codes associated with winter respiratory viruses at an emergency department

Every winter, respiratory viruses put most Emergency Departments (ED) around the world under intense pressure. To reduce the consequent stress for hospitals, anticipation of the massive increase of intakes for illness-based symptoms is essential. As the Covid-19 2020 pandemic clearly illustrates, patients are not systematically tested. The ED staff therefore has no real-time knowledge of the presence of the virus in the patients flow. To address this issue, we propose here to use the hospital's laboratory-confirmed database as an attractor for the manifold-based approach for clustering the clinical codes associated with respiratory viruses. We propose a new framework based on the embedding of time series onto the Stiefel manifold, coupled with a density-based clustering algorithm (HDBSCAN) enhanced by a reduction of dimension (UMAP) for the clustering on that manifold. In particular, we show, based on real data sets of two academic hospitals in France, the significant benefits of using geometrical approaches for time series clustering as compared to traditional methods.

Prospective evaluation of the point-of-care use of a rapid antigenic SARS-CoV-2 immunochromatographic test in a paediatric emergency department.

OBJECTIVES: This study aimed to evaluate the immunochromatographic coronavirus disease 2019 (COVID-19) speed antigen test (BioSpeedia, France) as an antigen point-of-care test (AgPOCT) to detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection at the paediatric emergency department of the University Hospital of Saint-Etienne in France. METHODS: Between 15 January and 28 May, 2021, children presenting with respiratory symptoms compatible with COVID-19 infection (symptomatic group) or those requiring hospitalization for any reason (asymptomatic group) were included prospectively and received a nasopharyngeal aspiration to carry out both AgPOCT and quantitative reverse transcription (RT) PCR (RT-qPCR) tests, with the latter being used as the reference standard, for the diagnosis of SARS-CoV-2 infection. RESULTS: Among the 1009 enrolled children, we obtained a result from both techniques for 990: 33 (3.3%) tested positive with AgPOCT and 46 (4.6%) with RT-qPCR. The overall sensitivity and specificity of the AgPOCT were 69.6% (95% confidence interval (CI), 54.3-82.3) and 99.9% (95% CI, 99.4-100), respectively, compared with the RT-qPCR. Sensitivity increased to 82.9% (95% CI, 66.4-93.4) in symptomatic children. The mean cycle threshold value was significantly lower in positive samples for AgPOCT than in negative samples in the overall population and in both the symptomatic and asymptomatic groups. DISCUSSION: The use of the COVID-19 speed antigen test at the bedside in the emergency department has satisfactory performance for diagnosing SARS-CoV-2 infection in symptomatic children.