Low-cost solution could provide round-the-clock monitoring, relieve stress on clinicians and enable new treatments – ScienceDaily


Visit the Neurological Intensive Care Unit during the consultant’s morning rounds, and you are likely to see doctors perform strenuous tests to assess each patient’s level of consciousness. These tests are the only way to accurately gauge a patient’s prognosis, or to identify vital warning signs that a patient’s health is deteriorating — but with each test taking up to an hour to complete, they place a significant burden on clinical teams.

Now, researchers at Stevens Institute of Technology have developed an algorithm that can accurately track patients’ level of consciousness based on simple physiological signs that are already routinely monitored in hospital settings. Although still in its early stages, the team’s work – published in the September 15th issue of neurological care It promises to significantly reduce pressure on medical staff, and can also provide vital new data to guide clinical decisions and enable the development of new treatments.

“Awareness is not a light switch that turns on or off — it is more like a dimmer switch, with degrees of consciousness that change throughout the day,” said Samantha Kleinberg, assistant professor in the Department of Computer Science at Stevens. . “If you only examine patients once a day, you only get one data point. With our algorithm, you can track consciousness continuously, which gives you a much clearer picture.”

To develop their algorithm, Kleinberg and her Ph.D. Student Louis A. Gomez and Jan Clasen, MD, director of critical care neurology at Columbia University, collect data from an array of ICU sensors — from simple heart rate monitors to sophisticated devices that measure brain temperature — and use it to predict the results of a clinician’s assessment of a patient’s level of consciousness. . The results were amazing: Using only the simplest physiological data, the algorithm has proven to be as accurate as a trained clinical examiner, and slightly less accurate than tests performed using expensive imaging equipment such as functional magnetic resonance imaging (fMRI) machines.

“This is very important, because it means that this tool could potentially be deployed in almost any hospital – not just neurological intensive care units where they have more sophisticated technology,” Kleinberg explained. She noted that the algorithm can be installed as a simple software module on bedside patient monitoring systems, making it relatively cheap and easy to use on a large scale.

Besides providing clinicians with better clinical information, and giving patients’ families a clearer idea of ​​their loved one’s prognosis, ongoing monitoring can help inform new research and ultimately improve patient outcomes.

“Consciousness is incredibly hard to study, and part of the reason is that there simply isn’t a lot of data to work with,” Kleinberg said. “Having around-the-clock data shows how changing patients’ consciousness could one day make it possible to treat these patients more effectively.”

More work will be needed before the team’s algorithm can be deployed in clinical settings. The team’s algorithm was trained based on data collected right before the clinician’s assessment, and further development will be needed to show it can accurately track consciousness around the clock. Additional data will also be needed to train the algorithm for use in other clinical settings such as pediatric intensive care units.

Kleinberg also hopes to improve the algorithm’s accuracy by cross-referencing different types of physiological data, and studying the way they match or lag each other over time. Some of these relationships are known to correlate with consciousness, making it possible to validate algorithmic assessments of consciousness during periods when assessments of human clinicians are not available.

For now, though, Stevens’ team is thrilled to have found a simple and widely applicable model for automatically assessing patient consciousness in clinical settings. “It was a high-risk, high-return project,” Kleinberg said. “It was very exciting to find that we can use these signals to categorize patients’ levels of consciousness.”

Story source:

Materials Introduction of Stevens Institute of Technology. Note: Content can be modified according to style and length.



Source link

Related Posts

Precaliga