Site icon Wonderful Engineering

This Supercomputer In Australia Predicts ICU Patient Outcomes Before They Worsen

Perth Pawsey Supercomputer Predicts ICU Patient Outcomes Before They Worsen

The researchers discovered a “world first” algorithm that detects severe brain bleeds ahead of time with the help of Perth’s Pawsey supercomputing center.

The algorithm was created using a vast amount of patient data from 200 patients at Royal Perth Hospital, Alfred Hospital, and Royal Melbourne Hospital, according to Shiv Meka, head of data science at Royal Perth Hospital.

Meka and his team created 20 different data models before coming up with one that could forecast the development of a brain bleed and give emergency responders up to 20 minutes.

“So you make sense of this data, and then you train the model to predict an event. And based on that, the doctor decides whether this is a high-risk patient and if they have to intervene,” Meka said.

“The only way that this could have happened is because of Pawsey; if we used the cloud [storage], we would have burned a big hole in our budget,” he added.

Robert McNamara, an urgent care specialist at Royal Perth Hospital, claims that the new effort is a significant development in treating traumatic brain injuries.

“Across Australia, there are about 2,000 severe traumatic brain injuries a year with 60 to 80 of these patients treated at Royal Perth Hospital. Unfortunately, about half of those patients will have a bad outcome; they will either die or be severely disabled because of their injury, which led to a re-evaluation of how we actually managed brain injury in the intensive care unit,” said Dr. McNamara.

He noted that medical professionals are most often taken aback when a patient suffers an abrupt brain enlargement or bleeding. “You can be sitting in intensive care looking at some of the [brain] pressure that’s in the safe zone and with very little warning, or sometimes no warning at all, suddenly that patient’s pressures are in unsafe levels,” he said.

According to him, “like any bruise or broken bone, swelling to the brain occurs in about 12 to 24 hours after the injury. However, unlike your limbs, the brain is housed within the skull, which works as a closed box.” Dr. McNamara explained.

Thanks to advanced software, researchers can keep track of every vital sign of patients. “Suddenly, we’re generating considerably higher frequency data for analysis,” Dr. McNamara explained.

“So we had the data, and fortunately, we met Shiv, who gave it a go and succeeded were at least 40 or 45 other groups failed.”

“For the first time, we’re going to be able to intervene before it happens,” he said.

According to Mark Stickells, executive director of the Pawsey Supercomputing Research Centre, the new technique shows how data science and computing development through the study of astronomical data may save lives.

“We’re like a laboratory that uses a computer as its main tool. We do amazing science at the level of the universe with astronomers using advanced telescopes, developing insights into our universe — but this is right down to human scale,” he said.

“Increasingly, medical science has been informed by advances in computing, machine learning, and artificial intelligence.”

Exit mobile version