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