Implementation and evaluation of a dashboard of predictive analytics and decision support to drive care quality and person-centred outcomes in aged care

We will conduct a two-arm, parallel-group, non-blinded, pragmatic cluster RCT. Randomisation will be stratified by the size and location of the facilities with a 1:1 allocation ratio. The unit of randomisation will be a cluster (i.e., residential aged care facilities). The intervention sites will receive the dashboard of predictive analytics and decision support while the control sites will remain on usual care (i.e., no dashboard). The 20 study sites (10 intervention and 10 control sites) will be randomly selected from a total of 24 facilities managed by Anglicare. The intervention will be introduced across all intervention sites at the same time in early 2023. A 1-month intervention wash-in period will be allowed to allow the integration of the dashboard into routine practice. Since the intervention is an add-on to an existing system, 1 month will be sufficient to allow users to familiarise themselves with the dashboard. During this wash-in period, we will conduct two 1-hour training – (1) to describe the nature of the dashboard (e.g., its contents) and (2) to demonstrate how it is used using various real-life scenarios. The training will be conducted for all staff involved in resident care across the intervention sites. The impacts of the dashboard will then be compared between the intervention and the control sites after 12 months (excluding the wash-in period data). The intervention involves implementing a dashboard of predictive analytics and decision support to be used by aged care staff to improve the care of residential aged care clients in relation to falls-related hospitalizations and quality of life. The dashboard is based on a dynamic risk predictive and monitoring tool that was developed using multiple electronic databases (e.g., medications, incident reports, demographic and health status). It provides real-time person-centred actionable recommendations to prevent falls. The dashboard will be used on a daily basis as part of routine resident care. Staff and Macquarie University researchers will embed the dashboard within the care management systems within facilities and access via routine avenues within the facility (i.e. computer/tablet). The dashboard utilizes data already collected within Anglicare's electronic care management system to provide information on well-being scores and incorporate a dynamic falls risk predictive tool to inform residents of daily falls risk. The dashboard will be used by staff in addition to other standard electronic and paper-based forms used to provide standard care. The dashboard will also include interventions or recommended actions to take to reduce resident falls risk based on clinical guidelines and the Peninsula Health Falls Risk Assessment Tool (PH-FRAT), commonly used in residential aged care. The content, design and functionality of the dashboard have been co-developed to ensure that it is suitable for implementation and use by staff. It is considered complementary to standard care.