Procalcitonin to Guide Antibacterial Prescribing in Patients Hospitalised with COVID- 19 (preprint)

Background: Antibacterial prescribing in patients presenting with COVID-19 remains discordant to rates of bacterial co-infection. Implementing diagnostic tests to exclude bacterial infection may aid reduction in antibacterial prescribing. Method: A retrospective observational analysis was undertaken of all hospitalised patients with COVID-19 across a single-site NHS acute Trust (London, UK) from 01/12/20-28/2/21. Electronic patient records were used to identify patients, clinical data, and outcomes. Procalcitonin (PCT) serum assays, where available on admission, were analysed against electronic prescribing records for antibacterial prescribing to determine relationships with a negative PCT result (<0.25mg/L) and antibacterial course length. Results: Antibacterial agents were initiated on admission in 310/624 (49.7%) of patients presenting with COVID-19. 33/74 (44.5%) patients with a negative PCT on admission had their treatment stopped within 24 hours. 6/49 (12.2%) patients who had antibacterials started but a positive PCT had their treatment stopped. Microbiologically confirmed bacterial infection was low (19/594; 3.2%); no correlation was seen with PCT and culture positivity (p=1). Lower mortality (15.6% vs 31.4%;p=0.049), length of hospital stay (7.9days vs 10.1days;p=0.044), and intensive care unit (ICU) admission (13.9% vs 40.8%;p=0.001) were seen among patients with low PCT. Conclusion: This retrospective analysis of community acquired COVID-19 patients demonstrates the potential role of PCT in excluding bacterial co-infection. A negative PCT on admission correlates with shorter antimicrobial courses, early cessation of therapy and predicts lower frequency of ICU admission. Low PCT may support decision making in cessation of antibacterials at the 48-72 hour review.

Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes (preprint)

Background: Accurately predicting patient outcomes in Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) could aid patient management and allocation of healthcare resources. There are a variety of methods which can be used to develop prognostic models, ranging from logistic regression and survival analysis to more complex machine learning algorithms and deep learning. Despite several models having been created for SARS-CoV-2, most of these have been found to be highly susceptible to bias. We aimed to develop and compare two separate predictive models for death during admission with SARS-CoV-2.MethodBetween March 1 - April 24, 2020, 398 patients were identified with laboratory confirmed SARS-CoV-2 in a London teaching hospital. Data from electronic health records were extracted and used to create two predictive models using: 1) a Cox regression model and 2) an artificial neural network (ANN). Model performance profiles were assessed by validation, discrimination, and calibration.Results Both the Cox regression and ANN models achieved high accuracy (83.8%, 95% confidence interval (CI): 73.8 - 91.1 and 90.0%, 95% CI: 81.2 - 95.6, respectively). The area under the receiver operator curve (AUROC) for the ANN (92.6%, 95% CI: 91.1 - 94.1) was significantly greater than that of the Cox regression model (86.9%, 95% CI: 85.7 - 88.2), p=0.0136. Both models achieved acceptable calibration with Brier scores of 0.13 and 0.11 for the Cox model and ANN, respectively. ConclusionWe demonstrate an ANN which is non-inferior to a Cox regression model but with potential for further development such that it can learn as new data becomes available. Deep learning techniques are particularly suited to complex datasets with non-linear solutions, which make them appropriate for use in conditions with a paucity of prior knowledge. Accurate prognostic models for SARS-CoV-2 can provide benefits at the patient, departmental and organisational level.