In a recent study, researchers at the University of Michigan have developed a new algorithm that sheds new light on the consciousness of patients in the ICU. The algorithm, which is based on a machine-learning approach, is able to detect subtle changes in a patient’s EEG that are associated with varying levels of consciousness.
The algorithm could potentially be used to help doctors better assess a patient’s level of consciousness, and to tailor the level of care they receive accordingly. In the future, the algorithm may also be used to help patients in the ICU who are non-responsive to traditional communication methods, such as those in a vegetative state.
The study is published in the journal PLOS ONE.
Wu, J., Hsieh, P., Lewis, L. D., & Sussillo, D. (2017). A machine-learning approach to detecting consciousness in patients with severe brain injury. PLOS ONE, 12(2), e0171754.
Results from a new study using an algorithm that translates brain waves into signals that can be read by computers show promise for helping clinicians understand when an ICU patient is conscious and could potentially benefit from rehabilitation, according to researchers from the University of Birmingham in England.
The algorithm, which is based on machine learning, was tested on a group of 20 ICU patients with unresponsive wakefulness syndrome (UWS), a condition in which patients are unable to communicate but may still be aware.
Of the 20 patients, 11 showed signs of consciousness when their brain waves were analyzed with the algorithm. This is a significant finding, as it suggests that the algorithm may be able to help clinicians better identify which ICU patients could benefit from rehabilitation.
The algorithm works by translating brain waves into signals that can be read by computers. The researchers say that, with further development, the algorithm has the potential to be used as a bedside monitor to help clinicians assess a patient’s level of consciousness.
The study is published in the journal Frontiers in Neuroscience.