Search

Information technology (IT) usability is the degree to which software can be used by specified consumers (eg, doctors) to achieve quantified objectives (eg, manage emergency patients in an emergency department (ED)) with effectiveness, efficiency and satisfaction with each interaction.1 Usability is relevant to new learners, infrequent users and regular users, and for people with a wide variety of capabilities. The software should minimise the risk and consequences of errors, and be straightforward to use for routine tasks. Hence an IT system with high usability is simple, guides users through the least labour-intensive route, and does not require expert knowledge for use. Bloom et al present an important study on the usability of electronic health record (EHR) systems in British EDs.2 The large survey clearly demonstrates the poor usability of all systems currently deployed throughout the UK, with none of them meeting the international minimum standards required for IT in any industry. The study was not able to tell us which aspects of usability are poor. The issue of EHR usability is not new, with articles published over the years calling for improvements, describing how large sums of health money has been spent on unproven IT systems without any evidence of improvements in safety, quality or efficiency.3 The authors mention that some may feel that the concept of usability is nebulous, however, usability is well defined.2 The computer science discipline, known as Human Computer Interaction, has studied the science and developed the practice of creating usable systems for decades.4 In industry, user-centred design is a well-established engineering practice, with widely accepted protocols for delivering effective interactive systems and improving the user experience. Solutions for developing user-friendly software to manage electronic records efficiently exist and we need to ensure they are incorporated into our software. While the …

ObjectivePatients, families and community members would like emergency department wait time visibility. This would improve patient journeys through emergency medicine. The study objective was to derive, internally and externally validate machine learning models to predict emergency patient wait times that are applicable to a wide variety of emergency departments.MethodsTwelve emergency departments provided 3 years of retrospective administrative data from Australia (2017–2019). Descriptive and exploratory analyses were undertaken on the datasets. Statistical and machine learning models were developed to predict wait times at each site and were internally and externally validated. Model performance was tested on COVID-19 period data (January to June 2020).ResultsThere were 1 930 609 patient episodes analysed and median site wait times varied from 24 to 54 min. Individual site model prediction median absolute errors varied from±22.6 min (95% CI 22.4 to 22.9) to ±44.0 min (95% CI 43.4 to 44.4). Global model prediction median absolute errors varied from ±33.9 min (95% CI 33.4 to 34.0) to ±43.8 min (95% CI 43.7 to 43.9). Random forest and linear regression models performed the best, rolling average models underestimated wait times. Important variables were triage category, last-k patient average wait time and arrival time. Wait time prediction models are not transferable across hospitals. Models performed well during the COVID-19 lockdown period.ConclusionsElectronic emergency demographic and flow information can be used to approximate emergency patient wait times. A general model is less accurate if applied without site-specific factors.

Cancer is a common illness with a prevalence of 1.8 million new cases and 600 000 deaths per annum in the USA alone.1 Approximately 10% of patients with cancer will attend an emergency department (ED) within 30 days of diagnosis or treatment,2 and 4.5 million sufferers from active cancer visit EDs in the USA annually, with 14%–20% of emergency visits related to fevers.3 4 Chemotherapy patients with fevers are highly likely to be treated with antibiotics during their ED visit, often shortly after arrival, prior to haematology results, to avoid a subset of patients deteriorating with sepsis or neutropaenic sepsis. In multicentre USA cohorts, antibiotics were administered to 26.5% of adult emergency oncology patients with fevers,3 and some paediatric oncology protocols recommend that all oncology patients with a fever receive antibiotics.5 Immune checkpoint inhibitor therapies are now widely indicated in numerous cancer types, particularly those whose tumours are inflammatory.6 For those with …