Abstract
The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.
Highlights
Continuous intracranial pressure (ICP) monitoring is a routine practice in neuro ICUs in attempts to identify increases in ICP associated with decreased cerebral perfusion [26]
This study clearly demonstrated that Machine Learning algorithms (ML) can integrate a multitude of multidimensional datasets to improve their predictive performance
Koren et al [35] showed that the MLbased software called Neurotrend, had good detection accuracy for certain seizure activity while reducing time for Continuous EEG (cEEG) review; inter-agreement between users was poor for rhythmicperiodic waves and unequivocal EEG patterns
Summary
There have been several reviews summarizing the role of ML in neurology/neurosurgery [4,5,6]. This review will [1] briefly summarize ML and compare the different types of ML commonly used in neuro ICU research, [2] review recent ML applications to improve neuro ICU management and [3] describe the future implications of ML to neuro ICU management. STANDARD STATISTICAL APPROACHES “Medicine is a science of uncertainty and an art of probability” - Sir William Osler [7]. The first and most important distinction for clinicians to understand is the difference between ML and standard statistical approaches (SSA), such as linear and logistic regression
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have