Australian-first AI system keeps patients safe


A ground-breaking 'early-warning' monitoring system powered by artificial intelligence (AI) is helping to keep patients safe and healthy at Sydney Adventist Hospital. 

It is the first healthcare provider in Australia to implement this system running in real time for every patient, which allows staff to intervene before people's conditions worsen and require intensive care.

Developed by two doctors with degrees in computer science and mathematics, the Ainsoff Index allows early-warning scores to be integrated with a hospital electronic medical record to effectively predict patient deterioration.

“Importantly, what we have developed is a highly sensitive and specific tool that improves on just looking at a single set of observations that only alert when a deterioration has occurred,” said cardiothoracic surgeon Dr Levi Bassin, who designed the system with colleague Dr David Bell in collaboration with the hospital's information services and clinical teams.

“By taking into account the trend in observations and pathology results, as well as an individual patient’s age, sex and their personal statistics, it is a shift away from a ‘one size fits all’ approach to patient deterioration,” he added.

Any staff member coming onto a ward can see an overview of all patients and determine in seconds if anyone is at risk of deterioration, and quickly arrange appropriate care. 

“The Ainsoff Index for every patient is displayed on one page, which allows us to allocate senior staff to sicker patients, and also to ensure that unwell patients don’t get missed,” said senior nurses at the hospital, known as the San.

Initial results published in the Journal of Critical Care Medicine show the statistically-derived index is superior to other early-warning scores at predicting adverse events while there is still time to intervene. 

The San's 12-month clinical trial of the system has recently ended, and the results will be reported in a forthcoming publication.

“We see the Ainsoff Index as part of the new era in medical informatics, where AI is being used to assist staff,” Dr Bassin said. 

“Given our results showing it is superior to currently-available early-warning systems, it could be considered as an eventual replacement of these less sensitive systems.”

Dr Bassin said the index also helped to reduce the problem of 'alert fatigue' in hospital clinical decision support, producing just 10 percent of false alarms compared to other mechanisms and correctly identifying more unwell patients.

“So we are intervening before people get very sick, to keep them out of the ICU, and using staff time more efficiently. This should lead to improved health outcomes for patients, a more efficient use of the health workforce, and savings for hospitals,” he said.

The index has been bought from Dr Bassin and Dr Bell's health analytics company by Australia-based technology firm Beamtree, which has global interests and aims to facilitate widespread adoption of their creation.

It stems from the doctors' desire to develop an algorithm that would improve on the early-warning score system used in New South Wales public hospitals, known as ‘Between The Flags’.

The AI model was developed using anonymised patient demographics, ward-based observations, laboratory values and their trends. 

“When we looked back over patient observation data, we could see that there were trends in patient deterioration that were not raising alerts,” Dr Bassin said.

“This was particularly true at night when fewer staff are on duty. David and I, who both come from a computer-modelling background, set out to build a model using machine-learning that could pick up a deteriorating trend earlier.”

Read more: New support for prostate cancer patients

Read more: Global recognition for San's cancer services


Comments are closed.