Outlier detection of vital sign trajectories from COVID-19 patients.

In this work, we present a novel trajectory comparison algorithm to identify abnormal vital sign trends, with the aim of improving recognition of deteriorating health.There is growing interest in continuous wearable vital sign sensors for monitoring patients remotely at home. These monitors are usually coupled to an alerting system, which is triggered when vital sign measurements fall outside a predefined normal range. Trends in vital signs, such as increasing heart rate, are often indicative of deteriorating health, but are rarely incorporated into alerting systems.We introduce a dynamic time warp distance-based measure to compare time series trajectories. We split each multi-variable sign time series into 180 minute, non-overlapping epochs. We then calculate the distance between all pairs of epochs. Each epoch is characterized by its mean pairwise distance (average link distance) to all other epochs, with clusters forming with nearby epochs.We demonstrate in synthetically generated data that this method can identify abnormal epochs and cluster epochs with similar trajectories. We then apply this method to a real-world data set of vital signs from 8 patients who had recently been discharged from hospital after contracting COVID-19. We show how outlier epochs correspond well with the abnormal vital signs and identify patients who were subsequently readmitted to hospital.

Equipping tomorrow's doctors for the patients of today.

As the proportion of older patients with frailty presenting to health services increases, so does the need for doctors to be adequately trained to meet their needs. The presentations seen in such patients, the evidence-based models of care and skillsets required to deliver them are different than for younger patient groups-so specific training is required. Several research programmes have used detailed and explicit methods to establish evidence-based expert-validated curricula outlining learning outcomes for undergraduates in geriatric medicine-there is now broad-consensus on what newly qualified doctors need to know. There are, despite this, shortcomings in the teaching of undergraduates about geriatric medicine. National and international surveys from the UK, EU, USA, Canada, Austria and the Netherlands have all shown shortcomings in the content and amount of undergraduate teaching. Mechanisms to improve this situation, aside from specifying curricula, include developing academic departments and professorships in geriatric medicine, providing grants to develop teaching in geriatric medicine and developing novel teaching interventions to make the best of existing resources. Under the last of these headings, innovations have been shown to improve outcomes by: using technology to ensure the most effective allocation of teaching time and resources; using inter-professional education as a means of improving attitudes towards care of older patients; focusing teaching specifically on attitudes towards older patients and those who work with them; and trying to engage patients in teaching. Research areas going forward include how to incentivise medical schools to deliver specified curricula, how to choose from an ever-expanding array of teaching technologies, how to implement interprofessional education in a sustainable way and how to design teaching interventions using a qualitative understanding of attitudes towards older patients and the teams that care for them.