Direct-to-consumer self-tests sold in the UK in 2023: cross sectional review of information on intended use, instructions for use, and post-test decision making.

Objectives: To review the information provided for self-test devices sold in high street shops in the UK and to assess their suitability for informed decision making based on use, interpretation, and post-test actions.

Design: Cross sectional review of information on self-test boxes and instructions for use leaflets.

Setting: Supermarkets, pharmacies, and health and wellbeing shops within a 10 mile radius of the University of Birmingham's campus at Edgbaston in 2023.

Direct-to-consumer self-tests sold in the UK in 2023: cross sectional review of regulation and evidence of performance.

Objectives: To review the evidence base, clinical performance claims, and usability and safety of self-tests available for sale on the UK high street.

Design: Cross sectional review of self-tests-regulation, evidence of performance, usability, and safety.

Setting: Tests were identified from supermarkets, pharmacies, and health and wellbeing shops within a 10 mile radius of the University of Birmingham Edgbaston Campus in 2023.

Extended sample size calculations for evaluation of prediction models using a threshold for classification.

When evaluating the performance of a model for individualised risk prediction, the sample size needs to be large enough to precisely estimate the performance measures of interest. Current sample size guidance is based on precisely estimating calibration, discrimination, and net benefit, which should be the first stage of calculating the minimum required sample size. However, when a clinically important threshold is used for classification, other performance measures are also often reported.

The role of procurement frameworks in responsible AI innovation in the National Health Service: a multi-stakeholder perspective.

Procurement carries legal requirements across public services in the UK but, for stakeholders in clinical Artificial Intelligence (AI) innovation, it is often poorly understood. This perspective piece summarises insights from a cross-sector workshop exploring the role of procurement frameworks in supporting AI innovation in the National Health Service (NHS). The significant characteristics of AI from a procurement perspective are identified and their consequences are explored.

Importance of sample size on the quality and utility of AI-based prediction models for healthcare.

Rigorous study design and analytical standards are required to generate reliable findings in healthcare from artificial intelligence (AI) research. One crucial but often overlooked aspect is the determination of appropriate sample sizes for studies developing AI-based prediction models for individual diagnosis or prognosis. Specifically, the number of participants and outcome events required in datasets for model training and evaluation remains inadequately addressed.

Diversity and Inclusion Within Datasets in Heart Failure: A Systematic Review.

Background: Heart failure (HF) is a life-threatening disease affecting 64 million people worldwide. Artificial intelligence (AI) technologies are being developed for use in HF to support early diagnosis and stratification of treatment. The performance characteristics of AI technologies are influenced by whether the data used during the AI lifecycle reflects the populations for which the AI is used.

Uncertainty of risk estimates from clinical prediction models: rationale, challenges, and approaches.

Clinical prediction models estimate an individual’s risk (probability) of a health related outcome to help guide patient counselling and clinical decision making. Most models provide a single point estimate of risk but without the associated uncertainty. Riley and colleagues argue that this needs to change, as understanding uncertainty of risk estimates helps to inform critical evaluation of a model and may impact shared decision making.

The value of standards for health datasets in artificial intelligence-based applications.

Artificial intelligence as a medical device is increasingly being applied to healthcare for diagnosis, risk stratification and resource allocation. However, a growing body of evidence has highlighted the risk of algorithmic bias, which may perpetuate existing health inequity. This problem arises in part because of systemic inequalities in dataset curation, unequal opportunity to participate in research and inequalities of access.

Intrathecal diamorphine for perioperative analgesia during colorectal surgery: a cross-sectional survey of current UK practice.

Objectives: To describe current UK clinical practice around the use of intrathecal diamorphine as analgesia for major elective laparoscopic colorectal surgery.

Design: Online self-administered survey.

Setting: Acute public hospitals in the UK (National Health Service - NHS) .

Skill decay following Basic Life Support training: a systematic review protocol.

Introduction: Survival from out of hospital cardiac arrest (OHCA) is lower in the UK than in several developed nations. Bystander cardiopulmonary resuscitation (CPR) is associated with increased rates of survival to hospital discharge following OHCA, prompting the introduction of several initiatives by the UK government to increase rates of bystander CPR, including the inclusion of Basic Life Support (BLS) teaching within the English national curriculum. While there is clear benefit in this, increasing evidence suggests poor retention of skills following BLS teaching.

Right Ventricular Dysfunction and Its Association With Mortality in Coronavirus Disease 2019 Acute Respiratory Distress Syndrome.

Objectives: To assess whether right ventricular dilation or systolic impairment is associated with mortality and/or disease severity in invasively ventilated patients with coronavirus disease 2019 acute respiratory distress syndrome.

Design: Retrospective cohort study.

Setting: Single-center U.