The challenge: Emergency wards are overcrowded

Emergency departments are increasingly overcrowded and can struggle to respond to day-to-day arrivals in a timely manner.

Most hospitals would currently have difficulty meeting the four-hour National Emergency Access Target set by the Australian Government in its 2012 MyHospitals report.

Contrary to conventional wisdom that emergency patient volumes are unpredictable, we have found that the number of admissions per day can be predicted with remarkable accuracy.

Our response: Developing tools to predict hospital demands

Hospital patient admission prediction tool: Dr James Lind describes how this tool helps hospitals manage patient load.

Show transcript
Music plays and text appears: [Patient Admission Prediction Tool] [Image changes to Dr James Lind, Director of Access and Patient Flow, Gold Coast Hospital]

Dr James Lind: The Patient Admission Prediction Tool is a tool to look at exactly what it says, it predicts to about 95% accuracy which patients are coming in and when.

[Music plays and image changes to an outside shot of Robina Hospital, then to the Emergency Department with ambulances parked out the front]

We know today that there are 12 people coming in with broken arms and legs. Only one of them has come in up to date, but we know there’s another 11 out there, so what we’ve been able to do is set aside emergency theatre time for these people already, so we know that they’re coming, and we know we can treat them.

[Image changes to show a patient being wheeled through the hospital corridors in a bed] [Image changes to show a patient seated on a bed] [Image has changed back to Dr Lind]

Patient: At the moment I walked in I spoke to the person and I sat there for ten minutes, and the doctor called me in, and so here I am. So it was like less than half an hour I’m waiting to have my cast put on.

Dr James Lind: It was difficult at first because many people didn’t believe the tool could do what we said it could do.

[Image changes to show a cast being applied to the arm of a patient and then moves back to Dr Lind]

Up til recently a fallacy existed that all hospitals had to be at 85% occupancy for optimal patient flow. Using the mathematics of CSIRO we’ve actually dispelled that rumour, and we can actually show categorically that that’s not true, and we’ve actually worked out optimal occupancies for not just our hospital but other hospitals. Now people trust in the tool and it actually informs our strategy. The performance of this hospital, compared to the data from 2010, has actually increased its four hour score by 20%. We now run above the federal target, and we’re one of the largest HHS’s that actually is able to do that. The impact for staff is that this can be done within hours, so that it actually minimises the amount of overtime. It also minimises the amount of stress because it’s done in a well ordered fashion, and everyone knows their jobs and responsibility, and where the actual problems that we need to address are.

[Image changes to show Dr Lind and colleagues discussing graphs and information that’s displayed on a monitor]

One of the key points with the partnership with CSIRO is that we provide the clinical input, and the mathematics resource optimisation etcetera does come from the CSIRO expertise, but it’s marrying these two important areas together. You couldn’t do it without either one, and that’s where the partnership has been fantastic. The proof of the pudding really of this tool is we’re in the middle of winter; it’s the worst point for an emergency department because of the winter surge that occurs. Up til recently you would have seen pictures of ambulances queuing outside to get into emergency, and all the beds being full. If we look today, on one of our busiest winter’s day, you can see there are still free beds in the emergency department, and there’s only one ambulance outside, which has managed to offload its stretcher.

[Camera pans over the Emergency ward beds and staff and then moves to show the stationary ambulance parked outside]

What we’re able to do with this tool is show people that actually what happens in health care is very predictable on a day by day basis.

[Music plays and the CSIRO logo appears with the text: Big ideas start here]

We have developed new software tools to accurately forecast demand and help ensure access to emergency care and a hospital bed.

These tools use a hospital’s historical data to provide an accurate prediction of the expected patient load, their medical urgency and specialty, and how many will be admitted and discharged.

We are investigating how they can be used to help an entire hospital run more smoothly and efficiently, from reducing ‘bed block’ in emergency departments to minimising waiting time for elective surgery.

The first technology is called the Patient Admission and Prediction Tool (PAPT) and was developed at our Australian eHealth Research Centre in partnership with Queensland Health, Griffith University and Queensland University of Technology.

We are extending PAPT to predict diseases such as influenza and the hospital admissions of patients with chronic diseases.

Demand Prediction Analysis Tool is our second prediction technology and an adaptation of PAPT. It is being trialled in Victoria for the first time through the Victorian Government Technology Innovation Fund.

The results: Improving health outcomes

The tools have been shown to have a 90 per cent accuracy rate in forecasting bed demand. If the entire country was to adopt prediction tools like this, a huge $23 million in annual savings could be made across Australia.

PAPT is being used by more than 30 Queensland hospitals to assist with:

  • bed management
  • staff resourcing
  • scheduling of elective surgery.

For patients the system has delivered improved health outcomes such as:

  • timely delivery of emergency care
  • improved quality of care
  • less time spent in hospital.

PAPT also received the 2012 CeBIT Business Award for Innovation.