Healthcare efficiency: AI technology to reduce hospital readmissions

Monash University researchers are using Artificial Intelligence (AI) to better understand the cause of hospital readmissions, in turn improving health outcomes and reducing the financial burden on the health system.

In the biggest study of its kind in Australia, researchers applied AI technology to examine 10 years’ worth of patient medical records, looking at 14,000 records and examining the details of over 327,000 hospital readmissions.

They have now developed a prediction model that achieves state-of-the-art prediction accuracy on two patient cohorts – chronic liver disease and heart failure.

The results of this research could help health experts model the long-term prognosis of other diseases in the future.

The research is a joint collaboration between the Faculty of Information Technology (IT) and the Faculty of Medicine, Nursing and Health Sciences, specifically through the School of Clinical Sciences and Monash Health. Professor Wray Buntine, Senior Lecturer Dr Yuan-Fang Li, Lecturer Dr Teresa Wang, PhD student Bhagya Hettige and Gastroenterologist Dr Suong Thi Thanh Le, embarked on this research project through the support of the Monash Institute of Medical Engineering (MIME).

Project lead Wray Buntine, Professor of Data Science and AI in the Faculty of IT, said there was an increasing need by healthcare practitioners and patients to improve the quality of care and lower hospital costs.

“This study utilised a rich source of clinical patient data to infer medical risk predictions and improve the quality of patient healthcare,” Professor Buntine said.

“By examining these complex data sets, the machine learning algorithms we’ve developed can make predictions on medical risks, such as identifying if and when a patient will readmit and whether this can be avoided.”

Dr Suong Thi Thanh Le, Gastroenterologist at Monash Health and Senior Lecturer from the Faculty of Medicine, Nursing and Health Sciences explains that the high readmission rates are a recognised problem across Australia.

“Chronic disease accounts for 70% of Australian disease burden and high health care utilisation. The ability to accurately identify patients at risk of emergent readmission for chronic liver disease or heart failure may allow us to deliver timely interventions which prevent hospitalisation, thereby improving patient outcomes and contributing towards a sustainable healthcare system,” she said.

Initial findings of the research project will be published at the 24th European Conference on Artificial Intelligence (ECAI 2020) in August. The project is expected to be completed in 2021 and the findings of this research will be further validated in real-world hospital settings to assist with predicting patient readmissions.