Engaging children and young people on the potential role of artificial intelligence in medicine.

INTRODUCTION: There is increasing interest in Artificial Intelligence (AI) and its application to medicine. Perceptions of AI are less well-known, notably amongst children and young people (CYP). This workshop investigates attitudes towards AI and its future applications in medicine and healthcare at a specialised paediatric hospital using practical design scenarios. METHOD: Twenty-one members of a Young Persons Advisory Group for research contributed to an engagement workshop to ascertain potential opportunities, apprehensions, and priorities. RESULTS: When presented as a selection of practical design scenarios, we found that CYP were more open to some applications of AI in healthcare than others. Human-centeredness, governance and trust emerged as early themes, with empathy and safety considered as important when introducing AI to healthcare. Educational workshops with practical examples using AI to help, but not replace humans were suggested to address issues, build trust, and effectively communicate about AI. CONCLUSION: Whilst policy guidelines acknowledge the need to include children and young people to develop AI, this requires an enabling environment for human-centred AI involving children and young people with lived experiences of healthcare. Future research should focus on building consensus on enablers for an intelligent healthcare system designed for the next generation, which fundamentally, allows co-creation. IMPACT: Children and young people (CYP) want to be included to share their insights about the development of research on the potential role of Artificial Intelligence (AI) in medicine and healthcare and are more open to some applications of AI than others. Whilst it is acknowledged that a research gap on involving and engaging CYP in developing AI policies exists, there is little in the way of pragmatic and practical guidance for healthcare staff on this topic. This requires research on enabling environments for ongoing digital cooperation to identify and prioritise unmet needs in the application and development of AI.

A 19-SNP coronary heart disease gene score profile in subjects with type 2 diabetes: the coronary heart disease risk in type 2 diabetes (CoRDia study) study baseline characteristics.

BACKGROUND: The coronary risk in diabetes (CoRDia) trial (n = 211) compares the effectiveness of usual diabetes care with a self-management intervention (SMI), with and without personalised risk information (including genetics), on clinical and behavioural outcomes. Here we present an assessment of randomisation, the cardiac risk genotyping assay, and the genetic characteristics of the recruits. METHODS: Ten-year coronary heart disease (CHD) risk was calculated using the UKPDS score. Genetic CHD risk was determined by genotyping 19 single nucleotide polymorphisms (SNPs) using Randox's Cardiac Risk Prediction Array and calculating a gene score (GS). Accuracy of the array was assessed by genotyping a subset of pre-genotyped samples (n = 185). RESULTS: Overall, 10-year CHD risk ranged from 2-72 % but did not differ between the randomisation groups (p = 0.13). The array results were 99.8 % concordant with the pre-determined genotypes. The GS did not differ between the Caucasian participants in the CoRDia SMI plus risk group (n = 66) (p = 0.80) and a sample of UK healthy men (n = 1360). The GS was also associated with LDL-cholesterol (p = 0.05) and family history (p = 0.03) in a sample of UK healthy men (n = 1360). CONCLUSIONS: CHD risk is high in this group of T2D subjects. The risk array is an accurate genotyping assay, and is suitable for estimating an individual's genetic CHD risk. Trial registration This study has been registered at ClinicalTrials.gov; registration identifier NCT01891786.

Effectiveness of a self-management intervention with personalised genetic and lifestyle-related risk information on coronary heart disease and diabetes-related risk in type 2 diabetes (CoRDia): study protocol for a randomised controlled trial.

BACKGROUND: Many patients with type 2 diabetes fail to achieve good glycaemic control. Poor control is associated with complications including coronary heart disease (CHD). Effective self-management and engagement in health behaviours can reduce risks of complications. However, patients often struggle to adopt and maintain these behaviours. Self-management interventions have been found to be effective in improving glycaemic control. Recent developments in the field of genetics mean that patients can be given personalised information about genetic- and lifestyle-associated risk of developing CHD. Such information may increase patients' motivation to engage in self-management. The Coronary Risk in Diabetes (CoRDia) trial will compare the effectiveness of a self-management intervention, with and without provision of personalised genetic- and lifestyle-associated risk information, with usual care, on clinical and behavioural outcomes, the cognitive predictors of behaviour, and psychological wellbeing. METHODS/DESIGN: Participants will be adults aged 25-74 years registered with general practices in the East of England, diagnosed with type 2 diabetes, with no history of heart disease, and with a glycated haemoglobin level of ≥6.45% (47 mmol/mol). Consenting participants will be randomised to one of three arms: usual care control, group self-management only, group self-management plus personalised genetic- and lifestyle-associated risk information. The self-management groups will receive four weekly 2-hour group sessions, focusing on knowledge and information sharing, problem solving, goal setting and action planning to promote medication adherence, healthy eating, and physical activity. Primary outcomes are glycaemic control and CHD risk. Clinical data will be collected from GP records, including HbA1c, weight, body mass index, blood pressure, and HDL and total cholesterol. Self-reported health behaviours, including medication adherence, healthy eating and physical activity, and cognitive outcomes will be assessed by questionnaire. Measures will be taken at baseline, 3 months (questionnaire only), 6 months and 12 months post-baseline. DISCUSSION: This study will determine whether the addition of personalised genetic- and lifestyle-associated CHD risk information to a group self-management intervention improves diabetes control and CHD risk compared with group self-management and usual care. Effectiveness of the combined intervention on health behaviours cognitions theorised to predict them, and psychological outcomes will also be investigated. TRIAL REGISTRATION: This study has been registered at ClinicalTrials.gov; registration identifier NCT01891786 , registered 28 June 2013.