Screening references is a time‐consuming step necessary for systematic reviews and guideline development. Previous studies have shown that human effort can be reduced by using machine learning software to prioritise large reference collections such that most of the relevant references are identified before screening is completed. We describe and evaluate RobotAnalyst, a Web‐based software system that combines text‐mining and machine learning algorithms for organising references by their content and actively prioritising them based on a relevancy classification model trained and updated throughout the process. We report an evaluation over 22 reference collections (most are related to public health topics) screened using RobotAnalyst with a total of 43 610 abstract‐level decisions. The number of references that needed to be screened to identify 95% of the abstract‐level inclusions for the evidence review was reduced on 19 of the 22 collections. Significant gains over random sampling were achieved for all reviews conducted with active prioritisation, as compared with only two of five when prioritisation was not used. RobotAnalyst's descriptive clustering and topic modelling functionalities were also evaluated by public health analysts. Descriptive clustering provided more coherent organisation than topic modelling, and the content of the clusters was apparent to the users across a varying number of clusters. This is the first large‐scale study using technology‐assisted screening to perform new reviews, and the positive results provide empirical evidence that RobotAnalyst can accelerate the identification of relevant studies. The results also highlight the issue of user complacency and the need for a stopping criterion to realise the work savings.

No abstract

This article focuses on how the National Institute for Health and Care Excellence (NICE) quality standard on ‘Community engagement: improving health and wellbeing’ (QS148) may be used to support local areas with pandemic recovery planning. This article sets the standard in the context of the coronavirus pandemic, explores some of its content and highlights additional NICE resources to support its use across the health and care system.

NICE's guideline on shared decision making, currently under development, endeavours to support shared decision making as part of routine health care practice. In this article, we summarize our learning to date, gained through the scoping of the guideline, on the key challenges that need to be addressed in the guideline. The production of a scope is the first stage in the development of a NICE guideline, setting the parameters for what will be considered in the guideline. The process for scoping the shared decision making guideline involved discussion with early recruited committee members and engagement with registered stakeholders, through both a workshop and formal consultation. Important, and sometimes divergent, viewpoints about shared decision making were revealed through this process. The key challenges centred on the issues of a need for a common definition of shared decision making, measurability, opportunities, barriers to implementation, and feasibility. Recognizing these challenges aided the refinement of the scope in terms of what the guideline will cover, draft questions and main outcomes for consideration.

Background Good mental wellbeing is important throughout the life course, including in older ages. This study aimed to assess the cost-eff ectiveness of friendship programmes to improve wellbeing and reduce loneliness of older people. Methods A descriptive cost-consequence analysis and a cost-utility analysis were used to assess the cost-eff ectiveness of a friendship enrichment programme for older women (53-86 years) comprising 12 lessons that focused on friendship-related topics such as self-esteem (n=60), versus no intervention (waiting list [control], n=55). The analysis drew on an original study of the intervention, which analysed participants at baseline, after the intervention, or 3 months after baseline, and 9-10 months after baseline. The cost-consequence analysis reported outcomes covering elements of friendships, self-esteem, loneliness, and subjective wellbeing. The cost-utility analysis used a decision analytical model, and was populated with published data on the eff ect of loneliness on health outcomes, including depression, stroke, and coronary heart disease; it adopted a lifetime horizon and health service perspective.