It is essential to monitor the condition of critically ill patients in hospitals. This task can be complicated by having to make difficult, high-stakes decisions under pressure. Particularly in intensive care, every second counts.
An algorithm could be able to fill this role, according to a recent study. Researchers suggest that software could be used to detect changes in the person’s behavior and alert them accordingly. consciousnessSimple physiological markers are already being recorded as a matter-of-course.
Although vital signs like heart rate, blood pressure, and heart rate can be continuously monitored using monitors, brain function, and consciousness, are more difficult to monitor. This is because it involves hours-long assessments by medical teams.
A computer system could monitor the brain function continuously, and can detect changes in status, which might be missed entirely or caught too late.
It’s still early days in devising such technology, but preliminary results suggest it’s a feasible approach – and it would be relatively easy and affordable to roll out in most intensive care units (ICU). It could be fitted in bedside monitoring equipment to complement the examinations by medical professionals.
“Consciousness isn’t a light switch that’s either on or off – it’s more like a dimmer switch, with degrees of consciousness that change over the course of the day,” Samantha Kleinberg is a computer scientistFrom the Stevens Institute of Technology (New Jersey).
“If you only check patients one time per day, then you only get one data point.” Our algorithm allows you to track consciousness continuously and gives you a much clearer picture.
Researchers developed an algorithm that could track data from various emergency room sensors. These sensors included those that measure heart rate, breathing rate and brain temperature. These stats can easily be monitored continuously, without the patient ever needing to be awake.
In the study, data from 239 hemorhage victims were analysed. The team was able to compare levels of consciousness with sensor readings and then use that data to develop an algorithm to determine which one is correct.
The algorithm was able to classify the states of consciousness of patients as well as trained clinicians and almost as well with more expensive, complex equipment such as lasers. Functional resonance imaging (fMRI) machines.
“That’s hugely important, because it means this tool could potentially be deployed in virtually any hospital setting – not just neurological ICUs where they have more sophisticated technology,” says Kleinberg.
There is still much to be done. The system was trained using data from clinical assessments. It has yet to prove that it can accurately predict consciousness 24/7.
The potential is there, but existing methods of checking on patients take a lot of time and are only intermittent. Many require patients to be responsive and/or have access to expensive equipment. All of these problems can be solved with this method.
The researchers believe that their algorithm will reduce the demand on health professionals and can improve patient outcomes. They also hope to inform future research into the mysterious state of consciousness.
“Consciousness can be difficult to study. Part of this is because there isn’t enough data to go on.” says Kleinberg. “Having data round-the-clock showing patients’ consciousness changes could help us to better treat them.”
The research was published in Neurocritical Care.
