Blog icon

The challenge

Hospitals are overcrowded

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

The Patient Admission and Prediction Tool helps to cut hospital waiting times.

Overcrowded hospitals are unsafe hospitals, and in order for patients to receive timely and quality care, whole-of-hospital strategies are needed to manage demand and optimise resources.

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

Our response

Developing tools to predict hospital demands

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 www.csiro.au]

Dr James Lind describes how this tool helps hospitals manage patient load.

Share & embed this video

Link

http://vimeo.com/116316088

Copied!

Embed code

<iframe src="//player.vimeo.com/video/116316088" width="640" height="360" frameborder="0" allow="autoplay; fullscreen" allowfullscreen></iframe>

Copied!

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

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

Using a hospital's historical data, PAPT provides an accurate prediction of the expected daily patient load as well as patients' medical urgency and specialty, and how many will be admitted and discharged.

This can help an entire hospital run more smoothly and efficiently, helping to ensure patients have access to quality care and a hospital bed, and minimising waiting times.

The results

Improving health outcomes

Following successful trials, PAPT was made available to public hospitals within Queensland and embedded within information systems managed and operated by Queensland Health's Healthcare Improvement Unit.

Using software developed by our scientists, hospitals can predict how many patients will arrive in emergency and how many will be admitted or discharged.

The tool has been shown to have over 90 per cent accuracy in forecasting daily bed demand, and is used effectively for:

  • staff resourcing
  • scheduling of elective surgery
  • identifying when demand is likely to exceed capacity
  • detecting the start and duration of the annual winter bed crisis
  • detecting disease outbreaks.

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.

It has been estimated that, in 2011, PAPT technology implemented in Queensland benefited the economy $97 million per annum due to improved patient outcomes (reduced mortality) and $3 million per annum due to improved service efficiency.

What's next for PAPT?

We have since applied the fundamentals of PAPT technology to deliver a similar system for Austin Health in Victoria, following funding from the Victorian Government Technology Innovation Fund.

In partnership with Victorian-based SME 'HealthIQ' (now owned by Telstra Health), the new system combines forecasts generated by PAPT with HealthIQ's patient flow software to deliver an enhanced product.

We are extending this work by developing new prediction models for bed and operating theatre demand in Western Australia.

We expect that by predicting the number of emergency and elective surgeries in operating theatres, we can improve patients' access to surgery and enable better theatre management. Analytics can also help us to understand the relationship between emergency and elective surgery scheduling to determine what can be improved to help hospitals achieve their emergency surgery targets.

Do business with us to help your organisation thrive

We partner with small and large companies, government and industry in Australia and around the world.

Contact us now to start doing business

Contact us

Find out how we can help you and your business. Get in touch using the form below and our experts will get in contact soon!

CSIRO will handle your personal information in accordance with the Privacy Act 1988 (Cth) and our Privacy Policy.


This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

First name must be filled in

Surname must be filled in

I am representing *

Please choose an option

Please provide a subject for the enquriy

0 / 100

We'll need to know what you want to contact us about so we can give you an answer

0 / 1900

You shouldn't be able to see this field. Please try again and leave the field blank.