JMIR Publications

ABSTRACT

Background:

Falls are a prevalent and serious health condition among older people in residential aged care facilities (RACFs) causing significant health and economic burden. However, the likelihood of future falls can be predicted, and thus, falls can be prevented if appropriate prevention programs are implemented. Current falls prevention programs in RACFs rely on risk screening tools with suboptimal predictive performance, leading to significant concerns regarding resident safety.

Objective:

Our aim was to develop a predictive, dynamic, dashboard to identify residents at risk of falls with associated decision support. This paper provides an overview of the technical process, including the challenges faced and the strategies employed to overcome them during the development of the dashboard.

Methods:

A predictive dashboard was co-designed with a major residential aged care partner in New South Wales, Australia. Data from resident profiles, daily medications, falls incidents, and falls risk assessments were utilised. A dynamic falls risk prediction model and personalised rule-based falls prevention recommendations were embedded in the dashboard. The data ingestion process into the dashboard was designed to mitigate the impact of underlying data system changes. This approach aims to ensure resilience against alterations in the data systems.

Results:

The dashboard was developed using Microsoft Power BI and advanced R programming by linking data silos. It includes dashboard views for those managing facilities and for those caring for residents. Data drill through functionality was utilised to navigate through different dashboard views. Resident level change in daily risk of falling, along with risk factors and timely evidence-based recommendations were output to prevent falls and enhance prescriptive decision support.

Conclusions:

This study emphasises the significance of a sustainable dashboard architecture and how to overcome the challenges faced when developing a dashboard amidst underlying data system changes. The development process utilised an iterative dashboard co-design process, ensuring successful implementation of knowledge into practice. Future research will focus on the implementation and evaluation of the dashboard's impact on health processes and economic outcomes.