free counter
Health And Medical

Low-cost solution could provide round-the-clock ICU patients’ consciousness monitoring

Low-cost solution could provide round-the-clock ICU patients' consciousness monitoring

Search for a neurological ICU throughout a consultant’s morning rounds, and you might see physicians conducting painstaking tests to assess each patients’ degree of consciousness. These tests will be the only solution to accurately gauge a patient’s prognosis, or even to spot vital indicators a patient’s health is decliningbut with each test taking so long as an hour to perform, they place a massive burden on clinical teams.

Now, researchers at Stevens Institute of Technology are suffering from an that may accurately track patients’ degree of predicated on simple physiological markers which are already routinely monitored in hospital settings. Though still in its first stages, the team’s workpublished in the Sept. 15 problem of Neurocritical Carepromises to significantly ease any risk of strain on , and may provide vital new data to steer clinical decisions and enable the development of new treatments.

“Consciousness is not a light switch that’s either on or offit’s similar to a dimmer switch, with levels of consciousness that change during the period of your day,” said Samantha Kleinberg, a co-employee professor in Stevens’ department of Computer Science. “In the event that you only check patients once each day, you merely get one data point. With this algorithm, you can track consciousness continuously, providing you a far clearer picture.”

To build up their algorithm, Kleinberg and her Ph.D. student Louis A. Gomez partnered with Jan Claassen, director of Critical Care Neurology at Columbia University, to get data from the selection of ICU sensorsfrom simple heartrate monitors around sophisticated devices that measure brain temperatureand used it to forecast the outcomes of a clinician’s assessment of a patient’s degree of consciousness. The outcomes were startling: only using the easiest physiological data, the algorithm proved as accurate as a tuned clinical examiner, and only slightly less accurate than tests conducted with expensive imaging equipment such as for example fMRI machines.

“That’s hugely important, since it means this tool may potentially be deployed in any hospital settingnot just neurological ICUs where they will have more sophisticated technology,” Kleinberg explained. The algorithm could possibly be installed as a straightforward software module on existing bedside patient-monitoring systems, she noted, rendering it relatively cheap and an easy task to roll out at scale.

Besides giving doctors better clinical information, and patients’ families a clearer notion of their loved ones’ prognosis, continuous monitoring may help to operate a vehicle new research and ultimately improve patient outcomes.

“Consciousness is incredibly hard to review, and area of the reason is that there simply isn’t much data to utilize,” said Kleinberg. “Having round-the-clock data showing how patients’ consciousness changes could 1 day be able to take care of these patients a lot more effectively.”

More work will undoubtedly be needed prior to the team’s algorithm could be rolled out in clinical settings. The team’s algorithm was trained predicated on data collected immediately in front of you clinician’s assessment, and additional development will undoubtedly be had a need to show that it could accurately track consciousness night and day. Additional data may also be necessary to train the algorithm for used in other clinical settings such as for example pediatric ICUs.

Kleinberg also hopes to boost the algorithm’s accuracy by cross-referencing different types of physiological data, and studying the direction they coincide or lag each other as time passes. Some such relationships are recognized to correlate with consciousness, potentially to be able to validate the algorithm’s consciousness ratings during periods when assessments by human clinicians aren’t available.

For the present time, though, the Stevens’ team is thrilled to possess found a straightforward, broadly applicable model for automatically assessing patient consciousness in clinical settings. “It had been a high-risk, high-reward project,” Kleinberg said. “It had been extremely exciting to get we’re able to use these signals to classify patients’ degrees of consciousness.”

More info: Louis A. Gomez et al, Classification of Degree of Consciousness in a Neurological ICU Using Physiological Data, Neurocritical Care (2022). DOI: 10.1007/s12028-022-01586-0

Citation: Low-cost solution could provide round-the-clock ICU patients’ consciousness monitoring (2022, September 16) retrieved 18 September 2022 from

This document is at the mercy of copyright. Aside from any fair dealing for the intended purpose of private study or research, no part could be reproduced minus the written permission. This content is provided for information purposes only.

Read More

Related Articles

Leave a Reply

Your email address will not be published.

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker