Lack of adherence to medication or treatment regimens is a global health concern and is a major clinical issue worldwide. Many existing adherence-improving strategies are not very successful, especially in the long term, and this mainly attribute to a lack of personalised and interactive communication. Based on the results from a prior study conducted on the effectiveness of an avatar-based mobile intervention, we designed and developed a Facebook Messenger chatbot - Reminder Bot, with the aim to further improve adherence and user satisfaction through a more sophisticated, personalised and interactive communication. Results from the trial conducted on participants taking health supplements as a surrogate to medication showed promising results, indicating that the Facebook Messenger chatbot has the ability and potential to support medication and treatment adherence

The implementation Electronic Medication Management Systems (eMeds) in hospitals has reduced certain types of medication errors, whilst simultaneously introducing new system-related errors; errors that were not possible with the use of paper records. Little is known about how and why these errors emerge and what approaches have been taken to reduce them, therefore we sought to classify updates made to an eMeds system in a NSW Local Health District (LHD), and establish a link between these changes and the potential system-related errors or workflow blocks they sought to prevent.

Clinical predictive tools quantify contributions of relevant patient characteristics to derive likelihood of diseases or predict clinical outcomes. When selecting predictive tools for implementation at the clinical practice or for recommendation in clinical guidelines, clinicians are challenged with an overwhelming and ever-growing number of tools, most of which have never been implemented or assessed for comparative effectiveness. To overcome this challenge, I have developed a conceptual framework to Grade and Assess Predictive tools (GRASP) that can provide clinicians with a standardised, evidence-based system to support their search for and selection of efficient tools. In this presentation I am going to tell you more about developing the GRASP framework, validating the framework, then evaluating the GRASP framework through an RCT to show the impact of using the framework on decisions made by clinicians and other healthcare professionals in selecting best clinical predictive tools.

Hospital-acquired complications and patient harms such as falls and pressure sores are a huge burden on healthcare. These events can be prevented if the patients at risk are identified and interventions are placed in time. Currently, nurses use several decision support systems (DSS) to assess patients for risks of these harms. However, these assessments are manual, not in real time and are often missed. In this talk, I’ll share findings of a systematic review that looks at automation in current nursing DSS, followed by interview reports about nurses’ perceptions of the same. Additionally, I will explain design of an online experiment with a simulated DSS for nurses that automates information acquisition, analysis, and decision selection in the risk assessment process.

My research is investigating the role of diet in secondary stroke prevention. I’ll present an overview of the topic, how we co-designed (alongside stroke survivors) a Mediterranean dietary intervention to be delivered 100% by telehealth and the preliminary results from the pilot trial.