A new method that uses machine learning to evaluate patient data in intensive care units can predict circulatory failure hours before it occurs, researchers report.
Patients in a hospital’s intensive care unit stay under close observation: clinicians continuously monitor their vital signs such as their pulse, blood pressure, and blood oxygen saturation.
This furnishes doctors and nurses with a wealth of data about the condition of their patients’ health. Nevertheless, using this information to predict how a patient’s condition will develop or to detect life-threatening changes far in advance is anything but easy.
The new method combines a patient’s various vital signs with other medically relevant information. In the future, researchers hope to use the method for real-time evaluation of hospital patients’ vital signs to provide an early warning system for the medical staff on duty, who, in turn, can take appropriate action at an early stage.
The researchers developed the new approach using data from the intensive care medicine department at Bern University Hospital. In 2005, it became the first large intensive care unit in Switzerland to start storing granular, high-resolution data for intensive care patients in digital form.
For the new study in Nature Medicine, researchers used anonymized data from 36,000 admissions to intensive care units. All patients agreed to their data being used for research purposes.
The researchers analyzed the data using machine learning methods. “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,” says Gunnar Rätsch, professor of biomedical informatics at ETH Zurich.
For each patient, the researchers had several hundred different variables combined with other medical information at their disposal.
“However, we were able to show that just 20 of these variables are sufficient to make accurate predictions. These include blood pressure, pulse, various blood values, the patient’s age, and the medication administered,” says Karsten Borgwardt, professor of data mining.
Lots of false circulatory failure alarms
To further improve the quality of the predictions, the researchers plan to incorporate patient data from other large hospitals into future analyses. In addition, they will make the anonymized dataset, the algorithms, and the models available to other scientists.
“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,” says Tobias Merz, research associate and former senior physician in the intensive care medicine department at the University Hospital in Bern.
“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,” he says.
With their approach, the researchers aim to replace the large number of alarms with a few, highly relevant, and early alarms. This is possible, as the study showed that the new method could cut the number of alarms 90%.
Some further development work is required to make the method ready for use as an early warning system. Rätsch explains that the first prototype already exists, but before the system can be employed in everyday clinical practice, its reliability must be demonstrated in clinical studies.
The Swiss National Science Foundation funded the work.
Source: ETH Zurich