Researchers in Switzerland have developed a machine learning model that analyses data to predict signs of deterioration in intensive care patients.
Specifically the tech driven solution alerts staff to imminent circularity failure. The team from ETH Zurich and Inselspital, Bern University Hospital, announced today it is achieving success by combining data on key medical information and the ‘patient’s various vital signs’. The goal is to create an early warning system medical professionals can use to take effective action.
“The algorithms and models we developed were able to predict 90% of all circulatory failures in the dataset we used. In 82% of the cases, the prediction came at least two hours in advance, which would have given doctors at least two hours to intervene,” said Gunnar Rätsch, Professor of Biomedical Informatics at ETH Zurich.
The breakthrough was made possible thanks to the amount of data being collected by the Department of Intensive Care Medicine at Bern University Hospital. Since 2005 it has been storing digital data on intensive care patients, and the researchers dipped into it to mine anonymised data from 36,000 admissions to intensive care units. It came entirely from patients who had agreed for it to be used in this way.
“Preventing circulatory failure is a crucial aspect of patient treatment in intensive care. Even short periods of inadequate circulation significantly increase the mortality of patients,” added Tobias Merz, research associate and former senior physician at the Department of Intensive Care Medicine at the University Hospital in Bern, who now works at Auckland City Hospital. “In intensive care units today, we have to deal with a multitude of alarm systems, but they’re not very accurate. Often, they trigger false alarms or they give us only a short advance warning, which can delay initiation of adequate measures to support a patients circulation.”
The researchers plan to provide more targeted alarm systems to replace the multitude that currently exist and Rätsch said a prototype is already in place. Before it can be rolled though, the system must first by tested out fully in clinical studies.
