From Big Data to the Bedside: answering big questions in emergency department pain care using artificial intelligence and patient-reported outcomes

One of the main reasons that acute pain is not well treated in the emergency department (ED) setting is that pain is difficult to measure. While patient-reported outcome measures (PROMS) are commonly used to help guide treatment of pain in settings such as chronic pain care, cancer care and migraine care, there are no similar tools available for patients with acute pain in the ED. Further hampering efforts to provide better ED pain care is poor overall understanding of the numbers and types of patients that experience pain.

Since it is a symptom rather than a diagnosis, information about pain is not systematically collected and is often obscured within free-text clinical notes. The lack of readily-available data makes it difficult to determine who exactly has experienced pain, and to design research studies to evaluate new and existing treatments.

Researchers aim to validate a PROM for pain care in the ED by administering to 400 patients who present with pain to one of two large hospital EDs. The aim is to find out the incidence and characteristics of patients who present with pain to the Royal Brisbane and Women’s Hospital ED, by using novel machine- and deep-learning techniques to process free-text information from clinical notes. This study will provide new knowledge and techniques that are essential for clinician-researchers to design and conduct studies that will ultimately improve pain care in the ED.

Quality linking of health data to evaluate patient and health service outcomes and key performance indicators following the implementation of patient flow strategies.

In order to understand the effectiveness of health service delivery, and the impact of changes in processes and procedures, it is important to first be capable of analysing the data that documents patients’ journeys through the hospital. This project will bring together key data from multiple disjointed information systems so that analysis can be undertaken on the flow of patients through the Gold Coast Hospital (GCH); from the ambulance, through the Emergency Department, and admission to a ward, including the operating rooms, radiology, pathology, and pharmacy that they encounter up to their departure. With this holistic view of patients’ journey of care, the baseline and measure impact of initiatives will be determined to ensure that patients flow through the environments with minimal delay and improved outcomes.

The impact of a new emergency department on patient presentations and ambulance service delivery

This research aimed to investigate the impact of opening a new ED within a health service district. The study involved linking ambulance, emergency department (ED) and hospital data from three EDs to better understand the patient journey and patient and health service outcomes when a new ED opens within the health service. The project aims were to:
1. Describe and compare patient and health service outcomes at three EDs before and 12 months after Robina ED opening;
2. Describe and compare outcomes for patients arriving to ED by ambulance based on whether off stretcher time is/is not delayed by >30 mins.

Impact of the Emergency Department Patient Admissions Predictive Tool (EDPAPT)

Hospital occupancy rates regularly approach 100%, with resultant access block, ambulance bypass, and the last-minute cancellation of elective surgery patients. More efficient management of inpatient beds to reduce these predicaments is imperative. This project will evaluate the impact of a patient admission forecasting system - the Emergency Department Patient Admissions Predictive Tool (EDPAPT) - that has been developed from analysis of historical admissions data at the Gold Coast Hospital.

The aim of the project will determine whether a model that forecasts patient admissions can assist with the allocation of inpatient beds to alleviate one of the major problems of most Emergency Department (ED)s: overcrowding and access block. Specifically it will determine whether the number of elective surgery cancellations and ambulance bypass occurrences are impacted by using a prediction tool, and what impact there is on ED and bed management work practices. The study will also determine if bed managers will make use of prediction tools or whether there are barriers to their use of it, such as perceived inaccuracies, preferences to rely on own judgements or default to current, familiar modus operandi.

The project was a collaboration with CSIRO’s Australian eHealth Research Centre and Queensland Health, with support from Griffith University and the Queensland University of Technology.

Evaluation of the Emergency Department Ambulance Offload Nurse (EDAOLN) in Queensland

Queensland Health have recognised that patient flow strategies are required for emergency departments in order to i) improve the patient journey and experience; ii) reduce delays and increase access to health care services; and iii) provide best clinical practice across the state. An Emergency Department Ambulance Off-Load Nurse (EDAOLN) role was commenced on Friday 17 August 2012 at the Gold Coast Hospital. The aim of this advanced nursing role was to provide rapid triage and assessment for patients arriving to the ED by ambulance and to commence initial meaningful treatment as required (such as X-rays, pathology, analgesia) on a 24/7 basis.

A retrospective study of all ED presentations (n=21,454) made to the Hospital, during July 9, 2012 - November 2, 2012; 39 days before (T1), during (T2) and after (T3) the introduction of the trial of an EDAOLN role. The primary outcome of interest was time to be seen by a clinician.