Early detection of heart failure using in-patient longitudinal electronic health records.

Heart Failure (HF) is common, with worldwide prevalence of 1%-3% and a lifetime risk of 20% for individuals 40 years or older. Despite its considerable health economic burden, techniques for early detection of HF in the general population are sparse. In this work we tested the hypothesis that a simple Transformer neural network, trained on comprehensive collection of secondary care data across the general population, can be used to prospectively (three-year predictive window) identify patients at an increased risk of first hospitalisation due to HF (HHF).

Supporting long-term condition management: a workflow framework for the co-development and operationalization of machine learning models using electronic health record data insights.

The prevalence of long-term conditions such as cardiovascular disease, chronic obstructive pulmonary disease (COPD), asthma, and diabetes mellitus is rising. These conditions are leading sources of premature mortality, hospital admission, and healthcare expenditure. Machine learning approaches to improve the management of these conditions have been widely explored, with data-driven insights demonstrating the potential to support earlier diagnosis, triage, and treatment selection.

Near real-time severe acute respiratory illness surveillance characterising influenza and COVID-19 epidemiology in hospitalised adults, 2021-22.

Objectives: We report the findings of a novel enhanced syndromic surveillance that characterised influenza- and SARS-CoV-2-associated severe acute respiratory illness (SARI) in the 2021/2022 winter season.

Methods: Prospective cohort study of adults admitted to the Queen Elizabeth University Hospital, Glasgow, with a severe acute respiratory illness. Patient demographics, clinical history, admission details, and outcomes were recorded.

Radiograph accelerated detection and identification of cancer in the lung (RADICAL): a mixed methods study to assess the clinical effectiveness and acceptability of Qure.ai artificial intelligence software to prioritise chest X-ray (CXR) interpretation.

Introduction: Diagnosing and treating lung cancer in early stages is essential for survival outcomes. The chest X-ray (CXR) remains the primary screening tool to identify lung cancers in the UK; however, there is a shortfall of radiologists, while demand continues to increase. Image analysis by machine-learning software has the potential to support radiology workflows with a focus on immediate triage of suspicious X-rays.

Implementation of major trauma app: usability and data completeness.

Background: The current UK standard for major trauma patients is to record notes in a paper trauma booklet. Through an innovative collaboration between a major trauma centre and a digital transformation industry partner, a TraumaApp was developed. Electronic notes have been shown to have fewer errors, granular data collection and enable time stamped contemporaneous record keeping.

Views of emergency care providers in providing healthcare for asylum seekers and refugees.

Background: The number of asylum seekers awaiting decisions on their claims in the UK has more than tripled since 2014. How we meet international obligations to provide appropriate healthcare to asylum seekers and refugees (ASRs) is therefore an increasingly important issue. The views of frontline healthcare workers are vital to ensure the development of sustainable and effective health policy when it comes to caring for this group.

Assessing the effectiveness of artificial intelligence (AI) in prioritising CT head interpretation: study protocol for a stepped-wedge cluster randomised trial (ACCEPT-AI).

Introduction: Diagnostic imaging is vital in emergency departments (EDs). Accessibility and reporting impacts ED workflow and patient care. With radiology workforce shortages, reporting capacity is limited, leading to image interpretation delays.

Exploring the impact of traumatic injury on mortality: An analysis of the certified cause of death within one year of serious injury in the Scottish population.

Background: Few studies effectively quantify the long-term incidence of death following injury. The absence of detailed mortality and underlying cause of death data results in limited understanding and a potential underestimation of the consequences at a population level. This study takes a nationwide approach to identify the one-year mortality following injury in Scotland, evaluating survivorship in relation to pre-existing comorbidities and incidental causes of death.

Socioeconomic deprivation and illness trajectory in the Scottish population after COVID-19 hospitalization.

Background: The associations between deprivation and illness trajectory after hospitalisation for coronavirus disease-19 (COVID-19) are uncertain.

Methods: A prospective, multicentre cohort study was conducted on post-COVID-19 patients, enrolled either in-hospital or shortly post-discharge. Two evaluations were carried out: an initial assessment and a follow-up at 28-60 days post-discharge.

AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study.

Introduction: A non-contrast CT head scan (NCCTH) is the most common cross-sectional imaging investigation requested in the emergency department. Advances in computer vision have led to development of several artificial intelligence (AI) tools to detect abnormalities on NCCTH. These tools are intended to provide clinical decision support for clinicians, rather than stand-alone diagnostic devices.

True prevalence of long-COVID in a nationwide, population cohort study.

Long-COVID prevalence estimates vary widely and should take account of symptoms that would have occurred anyway. Here we determine the prevalence of symptoms attributable to SARS-CoV-2 infection, taking account of background rates and confounding, in a nationwide population cohort study of 198,096 Scottish adults. 98,666 (49.

Evaluation of video review tools for assessing non-technical skills in emergency department resuscitation teams: a systematic review.

Background And Importance: Use of video review in medicine is established in contexts such as surgery. Although not widely used in the emergency department (ED), some centres use it to evaluate non-technical skills (NTS) to support teaching and quality improvement.

Objective: There is no consensus on assessment of NTS using video review in the ED and the purpose of this review was to identify tools used in this context.

High-Sensitivity Cardiac Troponin for Risk Assessment in Patients With Chronic Coronary Artery Disease.

Background: Cardiac troponin is used for risk stratification of patients with acute coronary syndromes; however, the role of testing in other settings remains unclear.

Objectives: The aim of this study was to evaluate whether cardiac troponin testing could enhance risk stratification in patients with chronic coronary artery disease independent of disease severity and conventional risk measures.

Methods: In a prospective cohort of consecutive patients with symptoms suggestive of stable angina attending for outpatient coronary angiography, high-sensitivity cardiac troponin I was measured before angiography, and clinicians were blinded to the results.

Long-Term Usage and Improved Clinical Outcomes with Adoption of a COPD Digital Support Service: Key Findings from the RECEIVER Trial.

Purpose: Digital tools may improve chronic obstructive pulmonary disease (COPD) management, but further evidence of significant, persisting benefits are required. The RECEIVER trial was devised to evaluate the Lenus COPD support service by determining if people with severe COPD would continue to utilize the co-designed patient web application throughout study follow-up and to explore the impact of this digital service on clinical outcomes with its adoption alongside routine care.

Patients And Methods: The prospective observational cohort hybrid implementation-effectiveness study began in September 2019 and included 83 participants.

Natural history of long-COVID in a nationwide, population cohort study.

Previous studies on the natural history of long-COVID have been few and selective. Without comparison groups, disease progression cannot be differentiated from symptoms originating from other causes. The Long-COVID in Scotland Study (Long-CISS) is a Scotland-wide, general population cohort of adults who had laboratory-confirmed SARS-CoV-2 infection matched to PCR-negative adults.

An Artificial Neural Network for Nasogastric Tube Position Decision Support.

Purpose: To develop and validate a deep learning model for detection of nasogastric tube (NGT) malposition on chest radiographs and assess model impact as a clinical decision support tool for junior physicians to help determine whether feeding can be safely performed in patients (feed/do not feed).

Materials And Methods: A neural network ensemble was pretrained on 1 132 142 retrospectively collected (June 2007-August 2019) frontal chest radiographs and further fine-tuned on 7081 chest radiographs labeled by three radiologists. Clinical relevance was assessed on an independent set of 335 images.

Adjudicated myocarditis and multisystem illness trajectory in healthcare workers post-COVID-19.

Background: We investigated the associations of healthcare worker status with multisystem illness trajectory in hospitalised post-COVID-19 individuals.

Methods And Results: One hundred and sixty-eight patients were evaluated 28-60 days after the last episode of hospital care. Thirty-six (21%) were healthcare workers.

Multimorbidity, disease count, mortality and emergency care use in persons attending the emergency department: a cross-sectional data-linkage study.

Background: Multimorbidity (two or more concurrent chronic conditions) is associated with poorer health outcomes and increased healthcare utilisation in primary care and general populations. Less is known about the prevalence of multimorbidity in emergency department attenders, or its association with poor outcomes in this population.

Aim: This study sought to explore the relationship between multimorbidity, mortality and health-care utilisation in a large urban cohort of persons attending emergency departments.

Outcomes among confirmed cases and a matched comparison group in the Long-COVID in Scotland study.

With increasing numbers infected by SARS-CoV-2, understanding long-COVID is essential to inform health and social care support. A Scottish population cohort of 33,281 laboratory-confirmed SARS-CoV-2 infections and 62,957 never-infected individuals were followed-up via 6, 12 and 18-month questionnaires and linkage to hospitalization and death records. Of the 31,486 symptomatic infections,1,856 (6%) had not recovered and 13,350 (42%) only partially.

Widening or narrowing inequalities? The equity implications of digital tools to support COVID-19 contact tracing: A qualitative study.

Background: As digital tools are increasingly used to support COVID-19 contact tracing, the equity implications must be considered. As part of a study to understand the public's views of digital contact tracing tools developed for the national 'Test and Protect' programme in Scotland, we aimed to explore the views of groups often excluded from such discussions. This paper reports on their views about the potential for contact tracing to exacerbate inequalities.

Duration of External Neck Stabilisation (DENS) following odontoid fracture in older or frail adults: protocol for a randomised controlled trial of collar versus no collar.

Introduction: Fractures of the odontoid process frequently result from low impact falls in frail or older adults. These are increasing in incidence and importance as the population ages. In the UK, odontoid fractures in older adults are usually managed in hard collars to immobilise the fracture and promote bony healing.

The influence of heatwave temperatures on fracture patient presentation to hospital.

Introduction: As global warming continues at its current rate, heatwaves are likely to become an increasing phenomenon. At present, knowledge of the influence of heatwave temperatures on fracture patient presentation to hospital remains limited.

Methods: This was a retrospective descriptive epidemiology study performed through hospital database review, linked to meteorological data.