Introduction to AI in Healthcare
A hospital in South Australia has successfully used a machine learning algorithm to predict which patients are likely to be discharged, resulting in significant cost savings. The Lyell McEwin Hospital used the Adelaide Score, a machine learning model developed by a team from the University of Adelaide, to analyze patient data and identify those who could be discharged within 12 and 24 hours.
How the Adelaide Score Works
The Adelaide Score uses vital signs and laboratory test data from the past 48 hours to predict patient discharge. The data is automatically collected from the hospital’s electronic medical record (EMR) system. The algorithm then screens and ranks patients who are likely to be discharged, allowing hospital staff to prioritize their care and prepare them for discharge.
Findings from the Trial
The Adelaide Score was trialed over 28 days in April last year, and the results were impressive. The hospital saw a 5% seven-day patient readmission rate, which is lower than the 7.1% rate in the same period the previous year. The median stay for patients was also shorter, at 2.9 days compared to 3.1 days previously. The trial resulted in cost savings of approximately A$735,708 (around $480,000) for the hospital.
Why the Adelaide Score Matters
The Adelaide Score was developed to address the issue of ambulance ramping in South Australia, where ambulances have spent an average of 3,000 hours per month waiting outside emergency departments since 2022. By optimizing the discharge process, the Adelaide Score helps to free up congested emergency departments and reduce the need for readmissions. According to Dr. Joshua Kovoor, the study’s first author, the Adelaide Score "results in patients having to stay less in hospital and require less readmissions after discharge, creating cost savings."
Potential Applications
The Adelaide Score can be applied in any healthcare setting that collects vital signs and laboratory parameters as part of routine clinical practice. It also has potential implementation in many clinical systems that automatically link data to an EMR system. Following the trial at Lyell McEwin, the Adelaide Score is being considered for potential implementation across eastern states of Australia, and the research team is exploring collaborative opportunities abroad.
The Larger Trend
The use of AI in healthcare is part of a larger trend towards using technology to improve patient outcomes and reduce costs. In addition to AI, the South Australian government has implemented telehealth or virtual care models to address health system congestion. These models include free telehealth services for adults, children, and seniors, as well as a 24/7 remote health monitoring service for remote and rural communities.
Conclusion
The Adelaide Score is a powerful tool that has the potential to revolutionize the way hospitals approach patient discharge. By using machine learning to predict which patients are likely to be discharged, hospitals can optimize their care and reduce costs. As the healthcare industry continues to evolve, it’s likely that we’ll see more innovative solutions like the Adelaide Score being developed and implemented.
FAQs
- What is the Adelaide Score? The Adelaide Score is a machine learning algorithm that predicts which patients are likely to be discharged from hospital within 12 and 24 hours.
- How does the Adelaide Score work? The Adelaide Score uses vital signs and laboratory test data from the past 48 hours to predict patient discharge.
- What were the results of the trial? The trial resulted in a 5% seven-day patient readmission rate, a shorter median stay for patients, and cost savings of approximately A$735,708 (around $480,000) for the hospital.
- Can the Adelaide Score be used in other healthcare settings? Yes, the Adelaide Score can be applied in any healthcare setting that collects vital signs and laboratory parameters as part of routine clinical practice.
- What other technologies are being used to address health system congestion? In addition to AI, the South Australian government has implemented telehealth or virtual care models to address health system congestion.
