Artificial intelligence (AI)-based clinical decision support systems (CDSSs) are currently being developed to aid prescribing in primary care. There is a lack of research on how these systems will be perceived and used by healthcare professionals and subsequently on how to optimise the implementation process of AI-based CDSSs (AICDSSs).

To explore healthcare professionals’ perspectives on the use of an AICDSS for prescribing in co-existing multiple long-term conditions (MLTC), and the relevance to shared decision making (SDM).

Qualitative study using template analysis of semistructured interviews, based on a case vignette and a mock-up of an AICDSS.

Healthcare professionals prescribing for patients working in the English National Health Service (NHS) primary care in the West Midlands region.

A purposive sample of general practitioners/resident doctors (10), nurse prescribers (3) and prescribing pharmacists (2) working in the English NHS primary care.

The proposed tool generated interest among the participants. Findings included the perception of the tool as user friendly and as a valuable complement to existing clinical guidelines, particularly in a patient population with multiple long-term conditions and polypharmacy, where existing guidelines may be inadequate. Concerns were raised about integration into existing clinical documentation systems, medicolegal aspects, how to interpret findings that were inconsistent with clinical guidelines, and the impact on patient-prescriber relationships. Views differed on whether the tool would aid SDM.

AICDSSs such as the OPTIMAL tool hold potential for optimising pharmaceutical treatment in patients with MLTC. However, specific issues related to the tool need to be addressed and careful implementation into the existing clinical practice is necessary to realise the potential benefits.

The necessity of enhancing resuscitation training has been encouraged by The International Liaison Committee on Resuscitation and the American Heart Association to reduce mortality, disability and healthcare costs. Resuscitation training is a complicated approach that encompasses various components and their mixture. It is essential to identify the most effective of these components and their combinations, to measure the corresponding effect size and to understand which participant groups may enjoy the greatest advantage.

We will systematically search 12 databases and two clinical trial registries for randomised controlled trials (RCTs) that examine different resuscitation training methods from inception to April 2025. The analysis will be carried out using the standard network meta-analysis and component network meta-analysis models. Resuscitation skills of staff will be the primary outcome of this analysis. Paired reviewers will independently screen and extract data. A consensus will be sought with the principal investigators to resolve any disagreements that cannot be achieved through regular meetings. Each intervention in each RCT will be decomposed according to its constituent components, such as delivery method, interactivity, teamwork, digitalisation and type of simulator. The analysis will be conducted using the frequentist and bayesian approach in the R environment. RoB V.2.0 and Confidence in Network Meta-Analysis will, respectively, be used to assess the risk of bias and the certainty of the evidence.

As we will use only aggregated secondary data without individual identities, ethical approval is not required. Results of this review will be shared through a peer-reviewed publication and presentation of papers at any relevant conferences.

CRD42024532878